Textbook Notes (363,556)
Canada (158,423)
Sociology (1,671)


33 Pages
Unlock Document

Western University
Sociology 2206A/B
William Marshall

Research Methods Second Half of Text Chapter 10: Noncreative Quantitative Research and Secondary Analysis Introduction - Experiments and survey research are both reactive  that is the people being studies are aware of the fact - Noncreative  the people being studied are not aware that they are part of a research project  used by interpretive and critical researchers Noncreative Measurement The Logic of Noncreative Measurement - Critical thing about noncreative or unobtrusive measures is that PEOPLE being studied are not aware of it but leave evidence of their social behavior or actions “naturally” Varieties of Noncreative or Unobtrusive Observation - Researchers have examined family portraits in different historical eras to see how gender relations within the family are reflected in seating patterns -Anthropologists have examined the contents of urban garbage dumps to learn about lifestyles from what is thrown away - Researchers have studied differences in graffiti in males versus female’s high school restrooms to show gender differences in themes - High school yearbooks are examined to determine the activities of those who had psychological problems later in life versus those who did not Recording and Documentation - Follows logic of quantitative measurement  conceptualize construct, and then link the construct to noncreative empirical evidence, which is its measure - The operational definition of the variable includes how the researcher systematically notes and records observations - Because noncreative measures indicate a construct indirectly, the researcher needs to rule out reasons for the observation other than the construct of interest Quantitative Content Analysis What is Content Analysis? - Content analysis  technique for gathering and analyzing the content of text - Content  words, meanings, pictures, symbols, ideas, themes, or any message that can be communicated - Text  a general name for symbolic meaning within a communication medium measures in content analysis - Researchers uses objective and systematic counting and recording procedures to produce a quantitative description of the symbolic content in text - Content analysis is noncreative because the process of placing words, messages, or symbols in a text to communicate to a reader or receiver occurs with without influence from the researcher who analyzes its content - Researcher can compare content across many texts and analyze it with quantitative techniques - Content analysis involves random sampling, precise measurement, and operational definitions for abstract constructs - Coding  turns aspects of content that represent variables into numbers Topics Appropriate for Quantitative Content Analysis - Has been used to study  themes in popular songs and religious symbols in hymns, trends in the topics that newspapers cover and the ideological tone of newspaper editorials, sex role stereotypes in textbooks or feature films etc. - Content analysis cannot determine the truthfulness of an assertion or evaluate the aesthetic qualities of literature - It reveals content in text but it cannot interpret the contents significance - Content analysis useful for 3 types of research problems  1. Helpful for problem involving a large volume of text 2. Helpful when a topic must be studied “at a distance” 3. Can reveal messages in a text that are difficult to see with casual observation Measurement and Coding General Issues - Coding System  a set of instructions or rules used to explain how to systematically convert the symbolic content from text into quantitative data - Researcher tailors it to the specific type of text or communication medium being studied - Coding system also depends on the researchers unit of analysis Units - Can be a word, a phrase, a theme, a plot, a newspaper article, a character etc. - They also use  recording units, context units, and enumeration units  few differences among them and are easily confused, in simple projects all three are the same What is Measured? - Structured observation  systematic, careful observation based on written rules - Written rules make replication possible and improve reliability - Coding systems identify four characteristics of content  1. Frequency  counting whether or not something occurs and if it occurs, how often 2. Direction  nothing the direction of messages in the content along some continuum (positive or negative, supporting or oppose) 3. Intensity  strength or power of a message in a direction 4. Space  a researcher can record the size of a text message or the amount of space or volume allocated to it Coding, Validity, and Reliability Manifest Coding -Atype of content analysis coding in which a researcher first develops a list of specific words, phrases, or symbols and then finds them in a communication medium - Coding the visible surface content - Highly reliable because the phrase or word either is or is not present - Unfortunately manifest coding does not take the connotations of words or phrases into account - Dowler  used manifest coding to measure type of crime, stage of crime, region of story, and length of story - Coding Frame  is a list of all possible values that your codes may take  the definitions of the values in your coding from must be explicitly defined Latent Coding -Researcher looks for the underlying, implicit meaning in the context of a text  researcher identifies subjective meaning such as general themes or motifs in a communication medium - Tends to be less reliable than manifest coding  it depends on a coder’s knowledge of language and the social meaning - Training, practice, and written rules improve reliability - Validity of latent coding can exceed that of manifest coding because people communicate meaning in many implicit ways that depend on context not just on specific words -Aresearcher can use both manifest and latent coding - Latent coding requires much more subjective interpretation about the implied meaning of content - Quantitative approaches to content analysis usually focus mostly on manifest codes, while summative qualitative content analysis is qualitative content analysis technique that gives more attention to latent coding Intercoder Reliability -Analysis often involves coding information from a very large number of units -Aresearcher may hire assistants to help with coding -Aresearcher who uses several coders must always check for consistency across coders  by asking coders t code the same text independently and then checking for consistency across coders - Researcher measures intercoder reliability with a statistical coefficient that tells the degree of consistency among coders  coefficient of 0.80 or better is generally required, 0.70 may be acceptable for exploratory research - When it takes a long time the researcher also checks reliability by having each coder independently code samples of text that were previously coded How to Conduct Content Analysis Research Question Formulation - When the research question involves, variables that are messages or symbols, content analysis may be appropriate Units of Analysis  amount of test that is assigned a code Sampling - Researchers often use random sampling in content analysis Variables and Constructing Coding Categories - Example  “construct of an ethnic minority women portrayed in a significant leadership role”  must define significant leadership role in operational terms and express it as written rules for classifying people named in an article - We must determine the race and sex of people named in the articles - Our measures indicates whether the role was positive or negative  so we can use manifest coding or latent coding - Recording sheet  page on which researcher writes down what is coded in content analysis  each unit should have a separate recording sheet - Each recording sheet has a place to record the identification number of the unit and spaces for information about each variable Inferences - Content analysis describes what is in the text  it cannot reveal the intentions of those who created the text or the effects that messages in the text have on those who reveieve them Existing Statistics/Documents And Secondary Analysis Appropriate Topics - Difficult to specify topics that are appropriate for existing statistics because they are so varied  any topic on which information has been collected and is publicly available can be studied - Researchers creatively reorganize the existing information into the variable for a research question after first finding what data are available - Experiments are best for topics where the researcher controls a situation and manipulates an independent variable - Survey researcher is best for topics where the researcher asks questions and learns about reported attitudes or behavior - Content analysis is best for topics that involve the content of messages in cultural communication - Existing statistics researcher is best for topics that involve information routinely collected by large bureaucratic organizations  public or private organizations systematically gather many types of information - Existing statistics research is appropriate when a researcher wants to test hypothesis involving variables that are also on official reports of social, economic, and political conditions Social Indicators - 60s  some social scientists, dissatisfied with the information available to decision makers, spawned the “social indicators movement” to develop indicators of social well being - Researchers wanted to measure the quality of social life so that such information cold influence public policy - Statistics Canada produces a report Canadian Social Trends, the US has many measures of social well being in different nations - Social indicator  any measure of social wellbeing used in policy - Social indicators have been developed for the following  population, family, housing, social security and welfare, health and nutrition, public safety, education and training, work, income, culture and leisure, social mobility, and public participation - Specific example  unemployment rate - Can indicate negative and positive aspects of social life  infant mortality rate and job satisfaction Locating Data Locating Existing Statistics - Main source of existing statistics are government or international agencies and private sources  enormous volume and variety of information exists - Many existing documents are “free”  publicly available at libraries; however the time and effort it takes to search for specific information can be substantial - Valuable source of information about Canada is the Canada Yearbook  has been published annually (some exceptions) since 1867  compilation of many official reports and statistical tables produced by Canadian government agencies - Most government publish similar yearbooks - In addition to government documents there are dozens of other publications  many produced for business purposes and can be obtained only for high cost  include information on consumer spending, the location of high-income neighborhoods, tends in the economy etc. - Publications list characteristics of business or their executives  3 main publications 1. Dun and Bradstreet Principal Industrial Businesses  guide to approximately 51,000 business in 135 countries with information on sales, number of employees, officers, and products 2. Who Owns whom  comes in volumes for nations or regions  lists parent companies, subsidiaries and associated companies 3. Standard and Poor’s Register of Corporations, Directors, and Executives  lists 37,000American and Canadians companies  information on corporations, products, officers, industries, and sales figures - Biographical sources list famous people and provide background information on them Secondary Survey Data - Special case of existing statistics; it is the reanalysis of previously collected survey or other data that were originally gathered by others - The focus is on analyzing rather than collecting data - Inexpensive, permits comparisons across groups, nations, or time, it facilitates replication, and it permits asking about issues not thought of by the original researchers Limitations - One danger is that a researcher may use secondary data or existing statics that are inappropriate for his or her research question  researcher needs to consider units in the data, the time and place of data collection, the sampling methods used, and the specific issues or topics converted in the data -Asecond danger is that the researcher does not understand the substantive topic  because the data are easily accessible; researchers who know very little about a topic could make erroneous assumptions or false interpretations about the results - Third danger is that the researcher may quote statistics in great detail to give an impression of scientific rigor, this can lead to Fallacy of misplaced concreteness  occurs when someone gives a false impression of precision by quoting statistics in greater detail than warranted and “overloading” the details Units of Analysis and Variable Attributes - Common problem in existing statistics is finding the appropriate units of analysis  many statistics are published for aggregates not for individuals  i.e. table in a government document has information for the province, but the unity of analysis for the research question is the individual  potential for committing ecological fallacy is very real in this situation - Related problem involves the categories of variable attributes used in existing documents or survey questions  problem arises when the original data were collected in broad categories or ones that do not match the needs for a researcher Validity - Validity problems occur when a researchers theoretical definition does not match that of the government agency or organization that collected the information - Happens when a researcher uses a different definition of something  i.e. including cuts and bruises in work injury -Another problem arises when official statistics are a surrogate or proxy for a construct in which a researcher is really interested  necessary because a researcher cannot collect original data - Third problem arises because the researcher lacks control over how information is collected  all information even that in official government reports, is originally gathered by people in bureaucracies as part of their jobs -Aresearcher depends on them for collecting, organization, reporting and publishing data accurately - Systematic errors in collecting the initial information; errors in organizing and reporting information; and errors in publishing information all reduce measurement validity Reliability - Reliability problems develop when official definitions or the method of collecting information changes over time - Official definitions of work injury, disability, unemployment, and the like change periodically  even if the researcher learns of the changes, consistent measurement over time is impossible - Reliability can be a serious problem in official government statistics  goes beyond recognized problems such as the police stopping poorly dressed people more than well dressed people, hence poorly dressed, lower income people appear more often in arrest statistics - Researchers often use official statistics for international comparisons but national governments collect data differently and the quality of data collection varies Missing Data - Sometimes, the data were collected but have been lost  more frequently the data were never collected - Those who decide what to collect may not collect what another researcher needs in order to address a research question Issues of Inference - It is difficult to use unobtrusive measures to establish temporal order and eliminate alternative explanations - In content analysis the researcher cannot generalize from the content to its effects on those who read the text, but can only us the correlation logic o survey research to show an association among variables Ethical Concerns - Not at the forefront of most noncreative research because the people being studied are not directly involved - The primary concern is the privacy and confidentiality of using information gathered by someone else -Another ethical issue is that official statistics are social and political projects - Implicit theories and value assumptions guide which information is collected and the categories used when gathering it - Measures or statistics that are defined as official and collected on a regular basis are objects of political conflict and guide the direction of policy - The collection of official statistics stimulates new attention to a problem, and public concern about a problem stimulates the collection of new official statistics - Political and social values influence decisions about which existing statistics to collect - Most official stats are designed for top-down bureaucratic or administrative planning purposes  they may not conform to a researchers purposes or the purpose of people opposed to bureaucratic decision makers Chapter 13: Field Research Introduction -Also called participant-observation research -Aqualitative style in which a researcher directly observes and (usually) participates in small-scale social settings - Researcher also often uses qualitative intervening in the process of doing field research, although field research is a method that is distinct from pure qualitative interviewing - Researchers directly talks with an observes the people being studied - Through interaction over months or years the researcher learns about the, their life histories, their hobbies and interests, and their habits, hopes, fears, and dreams Questions Appropriate For Field Research - Is appropriate when the research question involves learning about, understanding, or describing a group of interacting people - It is usually best when the question is “how do people do Y in the social world?” or “what is the social world of X like?” - Field researchers study people in a location or setting Ethnography - Uses field research just as one technique, often combined with qualitative interviews - Ethnography An approach to field research that emphasizes providing a very detailed description of a different culture from the viewpoint of an insider in that culture in order to permit a greater understanding of it - May hear the term ethnography interchangeable with field research - Doing field research is a core part of ethnography but field research is usually just one part of an ethnographic study - Ethnography is often considered a methodology rather than a method, which means it is a collection of methods that are tied together by an underlying theoretical orientation overreaching theoretical orientation - Ethnography assumes that people make inferences - People display their culture through behavior in specific social contexts  displays of behavior does not give meaning; rather meaning is inferred, or someone figures out meaning - Cultural knowledge includes both explicit knowledge (what we know and talk about) and tacit knowledge (what we rarely acknowledge) - Explicit = social event  an event where most people can describe what takes place - Tacit = unspoken cultural norm for the proper distance at which to stand from others The Logic of Field Research What is Field Research? - Hard to pinpoint a specific definition because it is more of an orientation toward research than a fixed set of techniques to apply - Field research is based on naturalism, which is also used to study other phenomena - Naturalism  involves observing ordinary events in natural settings, not in contrived, invented, or researcher-created settings - Researchers goals is to examine social meanings and grasp multiple perspectives in natural social settings -Asingle individual usually conducts Field research, although small teams have been effective - Researcher is directly involved in and part of the social world studied, so his or her personal characteristics are relevant in research - The researchers direct involvement in the field has an emotional impact Steps in a Field Research Project - Naturalism and direct involvement mean that field research is less structured than quantitative research - It is essential for a researcher to be well organized and prepared for the field - Steps of a project are not entirely predetermined but serve as an approximate guide or road map - Flexibility is a key advantage of field research, as it lets a researcher shift direction and follow leads Preparing, Reading, and Defocusing - Field projects often begin with chance occurrences or a personal interest - Reading the scholarly literature helps the researcher learn about concepts, potential pitfalls, data collection methods, and techniques for resolving conflicts - Field research begins with a general topic, not specific hypothesis  researcher first empties his or her mind of preconceptions - They can expect anxiety, self-doubt, frustration, and uncertainty in the field - No fixed steps, but some common concerns arise in the early stages  - Selecting a site and gaining access to the site - Entering the field - Learning the ropes - Developing rapport with members in the field Selecting a Field Site an Gaining Access to It - Field site  is the context in which events or activities occur, socially defined territory with shifting boundaries  i.e. hockey team has more than one physical site ice, locker room, residence, gym, parties etc.  the field site would include all locations -Aresearcher selects a site, then identifies cases to examine within it - Three factors are relevant when choosing a field research site  1. Richness of data 2. Unfamiliarity 3. Suitability - Sites that present a web of social relations, a variety of activities, and diverse events over time provide richer, more interesting data - Physical access can be an issue for the researcher  some sites are public areas and others are closed and private  researcher may find that he or she is not welcome or not allowed on the site, or there are legal and political barriers to access Entering the Field and Establishing Social Relations with Members Level of Involvement - Field roles can be arranged on a continuum by the degree of detachment or involvement a researcher has with members -At one extreme is complete observer; at the other extreme is complete participant - Field researchers level of involvement depends on negotiations with members, specifics of the field setting, the researchers personal comfort, and the particular role adopted in the field - Many move from observer to semi-participant level with more time in the field - Complete Observer  researchers role is limited to simple observation, without any participation in the activities of his or her study group  reduces the time needed for acceptance, makes over-rapport less of an issue, and can sometimes help members open up - It can facilitate detachment and protect the researchers self identity - Complete Participant  researcher fully participates in all aspects of the study group’s activities as though a member  the goal of fully experiencing the intimate asocial world of a member is achieved -Alack of distance from, too much sympathy for, or over involvement what members is likely - Semi-participant  refers to the role of the researcher in field research when he or she participates to some degree in-group activities, but not as much as a full member  do not immerse themselves completely in the groups culture, giving priority to their role as a social researcher Strategy for Entering Planning - Field sites usually have different level or areas, and entry is an issue for each - Entry is more analogous to peeling the layers of an onion than to opening a door - Bargains and promises of entry may not remain stable over time - Gatekeeper  someone with the formal or informal authority to control access to a site  can be the gang leader on the street corner, an administrator of a hospital, or the owner of a business - Informal public areas rarely have gatekeepers - It is ethically and politically astute to call on gatekeepers - Dealing with gatekeepers is a recurrent issue as a researcher enters new levels or areas Negotiating - Social relations are negotiated and formed throughout the process of field work - Negotiation occurs with each new member until a stable relationship develops to gain access, develop trust, obtain information, and reduce hostile reactions - Deviant groups and elites often require special negotiations for gaining access - To gain access to deviant subcultures, field researchers have used contacts from the researchers private lives, gone to social welfare or law enforcement agencies where the deviants are processed, advertised for volunteers, offered a service in exchange for access, or gone to a location where deviants hang out and joined a group Disclosing - Researcher must decide how much to reveal about himself or herself and the research project - Disclosing ones personal life, hobbies, interests, and background can build trust an close relationships, but the researcher will also lose privacy and he or she needs to ensure that the focus remains on the events in the field - Covert observer  researcher who is secretly studying a group without the group members knowing that they are being studied - Overt observer  researcher who is studying the group members with their full knowledge - Researchers disclose the project to gatekeepers and others unless there is a good reason for not doing so, such as the presence of gatekeepers who would seriously limit or inhibit researcher for illegitimate reasons Adopting a Social Role and Learning the Ropes Presentation of Self - People explicitly and implicitly present themselves to others - The presentation of self sends a symbolic message  “in serious and hardworking” “I’m warm and caring” “I’m a cool jock” etc. - Field researcher is conscious of the presentation of self in the field - Researcher must be aware that self-presentation will influence field relations to some degree Researcher as Instrument - Researcher is the instrument for measuring field data - This has two implications  1. Puts pressure on the researcher to be alert and sensitive to what happens in the field and to be disciplined about recording data 2. Personal consequences An Attitude of Strangeness - It is hard to recognize what we are very close to - We manage by ignoring much of what is around us and by engaging in habitual thing - We fail to see the familiar as distinctive and assume that others experience relative just as we do - Field research in unfamiliar surroundings is difficult because of a tendency to be blinded by the familiar - Confrontation of cultures or culture shock as two benefits 1. It makes it easier to see cultural elements 2. Facilitates self discovery -Attitude of Strangeness  involves questioning and noticing ordinary details or looking at the ordinary through the yes of a stranger - Strangeness helps a researcher overcome the boredom of observing ordinary details - Strangeness also encourages a researcher to reconsider his or her own social world Building a Rapport - Rapport is built by getting along with members in the field - He or she forges a friendly relationship, shares the same language, and laughs and cries with members - Not always easy to build rapport Charm and Trust - Social skills and personal charm are necessary to build rapport - Trust, friendly feelings, and being well liked facilitate communication and help him or her to understand the inner feelings or others - Many factors affect trust and rapport  how a researcher presents himself or herself; the role he or she chooses for the field; and the events that encourage, limit, or make it impossible to achieve trust - Establishing trust is impotent, but it does not ensure that all information will be revealed Understanding - Rapport helps field researchers understand members, but understanding is a precondition for greater depth, not an end in itself - Once he or she attains an understanding of the member’s point of view, the next step is to learn how to think and act within a member’s perspective Roles in the Field Pre-existing Versus Created Roles - Some existing roles provide access to all areas of the site the ability to observe and interact with all members, the freedom to move around, and a way to balance the requirements or a research member -At other times, a researcher creates a new role or modifies an existing one Limits on the Role Chosen - The field roles open to a researcher are affected by a ascriptive factors and physical appearance - He or she can change some aspects of appearance, such as dress or hairstyle but not ascriptive features such as age, race, gender, and attractiveness - Kusow  reported that being a Somali immigrant required extra negotiations and hassles, even when studying other Somali immigrants in Canada - Since many roles are sex typed, gender is an important consideration  female researchers often have more difficulty when the setting is perceived as dangerous or seamy and where males are in control - Maintaining marginal status is stressful  it is difficult to be an outsider who is not fully involved, especially when studying settings full of intense feelings - Go native  drop the professional researchers role to become a full member of the group being studied  or researchers may feel guilt about leaning intimate details as members drop their guard, and may come to over-identify with members Normalizing Social Research - Field researcher is observed and investigated by group members as well - In overt field researcher, members are usually initially uncomfortable with the presence of a researcher -An over field researcher must normalize social research  that is help members redefine social research from something unknown and threatening to something normal and predictable Maintaining Relations Social Relations - Researcher develops and modifies social relationships -Afield researcher monitors how his or her actions and appearance affect members -Also a researcher must be able to break or withdraw from relationships as well  ties with one may need to be broken in order to form ties with others Small Favors - Exchange relationships  develop in the field in which small tokens or favors, including deference and respect, are exchanged Conflicts In the Field - Fights, conflicts, and disagreement can erupt in the field, or researchers may study groups with opposing positions  in these situations researcher will feel pressure to take dies and will be tested to see of he or she can be trusted - Other types of conflicts that can occur are those that relate to researcher participation  if the group is involved in illegal acts to what extent should the researcher participate? - Complete detachment from “core” activities of a group may result in the researchers being ethically conscious, but it may also may serve to distance the researcher from the group members and make the group members less likely to trust the intentions of the researcher Appearing Interested -Appearance of interest  a technique used in which researchers maintain relations in a field site by pretending to be interested and excited by the activities of those studied, event though they are actually uninterested or very bored Observing and Collecting Data Watching and Listening Observing - Researchers pay attention, watch and listen carefully - Use all senses  they become an instrument that absorbs all sources of information - Researchers carefully scrutinize the physical setting to capture its atmosphere  “color of the floor?” “how large is the room?” - Observation in the field is detailed, tedious work - Researcher observes people and their actions, noting each person’s observable physical characteristics: age, sex, race, and stature  they also note neatness, dress and hairstyle because they express messages that can affect social interactions - Context in which things happens will also be notes  who is present, was the room hot etc. - Serendipity is important  many times researcher does not know the relevance of what he or she s observing until later  two implications  1. The importance of keen observation and excellent notes at all times 2. The importance of looking back over time and learning to appreciate wait time  most researcher say that they spend a lot of time waiting Listening - Listen carefully to phrases, accents, and incorrect grammar, listening both to what is said and how it is said or what was implied Taking Notes - Most research data are in the form of field notes - Full field notes can contain  maps, diagrams, photographs, tape recordings, videotapes, memos, artifact or objects from the field, notes jotted in the field, and detailed notes written away from the field - Researcher makes it a daily habit to write note directly after field research Types of Field Notes - Five levels  1. Jotted Notes  written  short, temporary memory triggers, such as words, phrases, or drawings taken inconspicuously, scribbled on any convenient item  incorporated into direct observation notes but never a substitute for them 2. Direct Observation Notes  notes a researcher rites immediately after leaving the field, which he or she can add to later  ordered chronologically with date, time, and place  they serve as a detailed description of what the researcher heard and saw in concrete, specific terms  concrete details not a summary 3. Researcher Inference Notes Afield researcher listened to members in order to “climb into their skin” or “walk in their shoes”  3 step process 1. Researcher listens without applying analytical categories 2. He or she compares what is heard to what was heard at other times and to what others sat 3. Then the researcher applied his or her own interpretation to infer or figure out what it means - In ordinary interaction we do all three steps simultaneously and jump quickly to our own inferences  field researcher learns to listen without inferring 4. Analytic Notes  methodological ideas in these notes to record their plans, tactics, ethical and procedural decisions, and self critiques of tactics - Analytical memos  systematic digressions into theory, where a researcher elaborates on ideas in depth, expands on ideas while still in the field, and modifies or develops more complex theory by reading and thinking about the memos 5. Personal Notes  like a personal diary  personal feelings and emotional reactions become part of the data and color what a researcher sees or hears in the field  researcher records personal life events and feelings  they serve 3 functions 1. Provide and outlet for a researcher and a way to cope with stress 2. They are a source of data about personal reactions 3. They give him or her a way to evaluate direction observation or inference notes when the notes are later reread Maps and Diagrams - Two purposes  1. It helps a researcher organize events in the field 2. It helps convey a field site to others - Field researchers find three types of maps helpful 1. Spatial map  locates people, equipment, and the like in terms of geographical, physical space, to show where activities occur 2. Social map  shows the number or variety of people and the arrangements among them of power, influence, friendship, division of labor, and so on  can also be done with families to show relations 3. Temporal map  shows the ebb and flow of people, goods, services, and communications, or schedules Machine Recordings To Supplement Memory - They ever substitute of field notes or a researchers presence in the field - They cannot be introduced into all field sites and can be used only after a researcher develops a rapport - Recorders and videotapes provide a close approximation to what occurred and a permanent record that others can review - Listening to or reviewing tapes can be time consuming - Transcriptions of tape are expensive and not always accurate; they do not always convey subtle contextual meanings or mumbled words Data Quality Trustworthiness Of Data - Techniques used to assess reliability and validity in quantitative research are not directly applicable to qualitative research  nature of the research and the data are too different - Lincoln and Guba  suggested a set of alternative criteria by which qualitative studies could be assessed that generally correspond to the quantitative concerns of reliability, validity, objectivity, and generalizability  1. Credibility  concerned with how much truth-value the results of our qualitative study have  compared to validity - Member checking  means that we ask members of the group we are studying if they agree with out interpretations and conclusions - Prolonged engagement  a researcher stays in the field long enough to be able to make informed conclusions and interpretations about what he or she is studying - Negative case analysis  involves identifying data or cases that differ from the general pattern of findings and making attempts to explain these contradictory cases 2. Transferability  concerns the extent to which the findings of the study can applied to other contexts  comparable to the idea of external validity (generalizability) in qualitative research - Lincoln and Guba  transferability of a study can be established through thick description  which means that the researcher keeps very detailed accounts of his or her study, if sufficient detail is provided, it is possible to speculate with more certainty how the findings may be applicable to other settings or situations 3. Dependability  most closely associated with the quantitative idea of reliability, as it concerns how consistent our results would be if the study were repeated under similar conditions - Established through external audit  involves having the research materials examined by an external evaluator n order to see if he or she would draw the same conclusions from the data as the original researcher did 4. Confirmability  the trustworthiness aspect of confirmability concerns the extent to which the research is neutral and is not simply the product of the researchers biases or motivations - Established through and external audit - Audit trail  researcher should be transparent about his or her research techniques, keeping detailed notes and fully transcribed interviews - Reflexivity  being self-aware of the researchers role in the process of knowledge construction Focusing and Sampling Focusing - Researcher decides on specific research questions and develops hypotheses only after being in the field and experiencing it firsthand Sampling - Field researchers often use nonprobability samples, such as snowball sampling -Aresearcher may take a smaller, selective set of observations from all possible observations, or sample times, situations, type of events, locations, types of people, or contexts of interest -Aresearcher often samples locations because one location may give depth, but a narrow perspective  sitting or standing in different locations helps researcher get a sense of the whole site - Field researchers sample people by focusing their attention on different kinds of people -As a researcher identifies types of people, or people with opposing outlooks, he or she tries to interact with and learn about all types -Afield researcher also samples various kinds of events, such as, routine, special, and unanticipated - Routine events  happen everyday but should not be considered unimportant simply because they are routine - Special events  are announced and planned in advance  they focus member attention and reveal aspects of social life not otherwise visible - Unanticipated events  just happen to occur while a researcher is present Leaving the Field - Schatzman and Strauss  suggest that the end comes naturally when theory building ceases or reaches a closure; others feel that fieldwork could go on without end and that a firm decision to cut off relations is needed - Experienced field researchers anticipate a process of disengaging and exiting the field  depending on the on the intensity of involvement and the length of time in the field, the process can be disruptive or emotionally painful for both the researcher and the members - When a researcher decides to leave he or she chooses a method of exiting  quick exit, or can slowly withdrawal  also need to decide how to tell members and how much advance warning to give - The exit process depends on the specific field setting and the relationships developed  in general; a researcher lets members know a short period ahead of time Ethical Dilemmas of Field Research - Direct personal involvement of a field researcher in the social lives of other people raise many ethical dilemmas  they arise when a researcher is along in the field and has little time to make a moral decision Deception - Deception may arise in several ways in field research  the research may be covert; it may assume a false role, name, or identify; or it may mislead members in some way - Most hotly debated of ethical issues arising from deception is that of overt versus over field research - Some support covert seeing it as necessary for entering into and gaining a full knowledge of many areas of social life - Others oppose it and argue that it undermines a trust between researchers and society - Covert research is never preferable and never easier than overt research because of the difficulties of maintaining a front and the constant fear of getting caught Confidentiality - Researcher learns intimate knowledge that is given in confidents he or she has a moral obligation to uphold the confidentiality of data  keeping information confidential from others in the field and disguising members names in field notes - Sometimes you cannot take a direct quote from someone  one strategy is that, instead of reporting the source as in informant, the researcher can find documentary evidence that says the something and use the document as if it were the source of information Involvement with Deviants - Researchers who conduct field researchers on deviants who engage in illegal behavior face additional dilemmas - They know and may sometimes be involved in illegal activity = guilty knowledge - The researcher faces a dilemma of building trust and rapport with the deviants, yet not becoming so involved as to violate his or her basic personal moral standards Publishing Field Reports - The intimate knowledge that a researcher obtains and reports creates a dilemma between the right to privacy and the right to know -Aresearcher does not publicize member secrets, violate privacy, or harm reputations  yet the researcher still has to publish something  some researchers ask members to look at a report to verify its accuracy and to approve their portrayal in print -Acompromise position is for a researcher to publish truthful but unflattering material after consideration and only if it is essential to the researchers arguments Chapter 15: Analysis of Qualitative Data Introduction - Qualitative data comes in the form of written words, phrases, photos, symbols, images, or sounds describing or representing people, actions, and events in social life - Rarely use statistical analysis Comparing Methods of Data Analysis Similarities - Qualitative and quantitative styles of research involve inferring from the empirical details of social life - Infer  to pass judgment, to use reasoning, and to reach a conclusion based on evidence - Qualitative as well as quantitative analysis involves a public method or process - Both types of researchers collect large amounts of data, describe the data, and document how they collected and examined it -All data analysis is based on comparison  researchers compare features of the evidence they have gathered internally or with related evidence  they identify multiple processes, causes, properties, or mechanisms within the evidence as well as patterns and similarities Differences - Qualitative data analysis differs from quantitative in four ways  1. There are different types and numbers of analysis techniques  quantitative is more standardized than qualitative 2. There are different starting points for data analysis  3. There are different relationships between data and social theory  quantitative researchers manipulate numbers in order to see patterns or relationships 4. There are different degrees of abstraction or distance from the details of social life Explanations and Qualitative Data -Aqualitative researcher does not have to choose between a rigid idiographic/nomothetic dichotomy  that is between describing specifics and verifying universal laws  instead a researcher develops explanations or generalizations that are close to concrete data and contexts but are more than simple descriptions -Aqualitative researcher divides explanations into two categories  1. Highly unlikely 2. Plausible - The researcher is satisfied by building a case or supplying supportive evidence  he or she may eliminate some theoretical explanations from consideration while increasing the plausibility of other because only a few explanations will be consistent with a pattern in the data - Qualitative analysis can eliminate an explanation by showing that a wide array of evidence contradicts it Going And Concept Formation Conceptualization - Quantitative researchers conceptualize and refine variables in a process that comes before data collection or analysis  by contrast qualitative researcher form new concepts or refine concepts that are grounded in the data - Conceptualization is how a qualitative researcher organizes and makes sense of the data -Aqualitative researcher organizes data into categories on the basis of themes concepts or similar features he or she develops new concepts, formulates conceptual definitions, and examines the relationships among concepts and eventually he or she links concepts - In qualitative data analysis, ideas and evidence are mutually interdependent  cases are not given pre-established empirical units or theoretical categories apart from data; they are defined by data and theory - By analyzing the situation the researchers organizes data and applies ideas simultaneously to create or specify a case Coding Qualitative Data -Aquantitative researcher codes after all the data have been collected - Coding data has a different meaning in qualitative research  a researcher codes by organizing the raw data into conceptual categories and creates themes or concepts - Coding is two simultaneous activities  - Mechanical data reduction -Analytical data categorization - Coding data is the hard work of reducing mountains of raw data into manageable piles  it also allows a researcher to quickly retrieve relevant parts of the data - Data coded in qualitative projects are various types of texts  coding of all these data types involves the same general technique: organizing the data into themes and the refining and drawing links between the themes Open Coding - Is performed during a first pass through recently collected data - Researcher locates ideas in the data and assigns initial codes  slows reads field notes, historical sources, or other data looking for critical terms, key events, or themes, which are then noted - Next he or she writes a preliminary concept or label at the edge of a note card or computer record and highlights it with brightly colored ink or in some similar way - Open coding bring themes to the surface from deep inside the data - In open coding the researcher can develop literally hundreds of codes  ones with the most evidence that are usually considered the strongest codes or themes Axial Coding - This is the “second pass” through the data - During the open coding, a researcher focuses on the actual data and assigns code labels for themes - In axial coding the researcher begins with an organized set of initial codes or preliminary concepts - In the second pass he or she focuses on the initial coded themes more than on the data - Researcher looks at relationships between open codes in order to see how they may cluster together into larger theses or categories - During axial coding a researcher asks about causes and consequences, conditions and interactions, and strategies and processes and looks for categories or concepts that cluster together -Axial coding not only stimulates thinking about linkages between concepts or themes but it also raises new questions  it can suggest dropping some themes or examining others in more depth Selective Coding - Involves scanning data previous codes and determining a core category around which the remaining categories all “fit” Analytical Memo Writing -Analytical memo is a special type of note  a memo or discussion of thoughts and ideas about the coding process that a researcher writes to himself or herself - The rough theoretical notes from the beginning of analytical memos - The analytical memo forges a link between the concrete data or raw evidence and more abstract, theoretical thinking - Contains a researchers reflections on and thinking about the data and coding - Each researcher develops his or her own method of writing an analytical memo  some make multiple copies or note, then cut them and place selections into an analytical memo file  others link the analytical memo file locations to the data notes where a theme appears Analytical Strategies for Qualitative Data - Strategies for qualitative data re more diverse, less standardized, less explicitly outlined by researchers - In general data analysis  means a search for patterns in data  recurrent behaviors, objects, or a body of knowledge - Qualitative researcher moves form the description of a historical event or social setting to a more general interpretation of its meaning The Narrative - Called the narrative in the last chapter (historical-comparative research) In field research it is also called a natural history or realist tale approach  the narrative is largely a theoretical description - The research-author “disappears” from the analysis and presents the concrete details in chronological order as if they were the product of a unique and naturally unfolding sequence of events - Some argue the narrative approach is a presentation of data without analysis  a researcher assembles the data in a descriptive picture or account or what occurred, but he or she largely leaves the data to speak for itself - Explanation resides not in abstract concepts and theories, but in a combination of specific, concrete details - In the narrative, data are analyzed or “explained” in the terminology and concepts of the people being studied  analysis appears in how a researcher organizes the data for presentation and tells the story - Debate over usefulness  on one hand, it provides rich concrete detail an clearly demonstrates the temporal ordering of processes or specific events  on the other hand,, many researchers criticize the narrative approach for being too complex, particular, and idiosyncratic Ideal Types - Max Webbers ideal type is used by many researchers  ideal types  are models or mental abstractions of social relations or processes  they are pure standards against which the data or “reality” can be compared -An ideal type is a device used for comparisons because no reality ever fits an ideal type - Webber’s method of ideal types also compliments John Stuart Mill’s method of agreement  with the method of agreement, a researches attention is focuses on what is common across cases, and he or she looks for common causes in cases with a common outcome Contrast Contexts - Researches making contrasts between contexts often choose cases with dramatic contrasts or distinctive features - When comparing contexts, researchers do not use the ideal type to illustrate a theory in different cases or to discover regularities  instead they accentuate the specific and the unique - Researchers can show how unique features shape the operation of general processes Analogies -An analogy  is a statement that two objects, processes, or events are similar to each other - Researchers use analogies to communicate ideas and to facilitate logical comparisons -Analogies transmit information about patterns in data by referring to something that is already known or an experience familiar to the reader - The use of analogies to analyze qualitative data serves as a heuristic device  a device that helps on learn or see Successive Approximation - Involves repeated iterations or cycling though steps, moving toward a final analysis - Over time, or after several interactions, a researcher moves from vague ideas an concrete details in the data toward a comprehensive analysis with generalizations - Researcher begins with research question and a framework of assumptions and concepts  then he or she probes into the data, asking questions of the evidence to see how well the concepts fit the evidence and reveal features of the data - He or she also creates new concepts by abstracting from the evidence and reveal features of the data - Each pass through the evidence is provisional or incomplete - The concepts are abstract, but they are rooted in the concrete evidence and reflect the context - The researcher cannot determine the number and size of periods and the breaks between them until after the evidence has been examined - The researcher reexamines the evidence with added data, readjusts the periodization, and so forth  after several cycles, he or she approximates a set of periods in 100 years on the basis of successfully theorizing and looking at evidence The Illustrative Method -Aresearcher applies theory to a concrete historical situation or social setting, or organizes data on the basis of prior theory - Pre-existing theory provides the empty boxes  a name for conceptual categories in an explanation that a researcher uses as part of the illustrative method of qualitative data analysis  the researcher sees whether evidence can be gathered to fill these empty boxes - The evidence in the boxes confirms or rejects the theory, which he or she treats as a useful device for interpreting the social world - There are two variations of the illustrative method 1. Show that the theoretical model illuminates or clarifies a specific case or single situation 2. The parallel demonstration of a model in which a researcher juxtaposes multiple cases (units of time or periods) to show that the theory can be applied in multiple cases Other Techniques Network Analysis - Qualitative researchers often “map” the connections among a set of people, organizations, events, or places - Using sociograms and similar mapping techniques, they can discover, analyze, and display sets of relations Time Allocation Analysis - Researchers examine the way people spend or invest time or reveal implicit rules of conduct or priorities - Researchers also document the duration or amount of time devoted to various activities -An analysis of how people groups, or organizations allocate the valuable resources they control can reveal a lot about their real, as contrasted with officially professes, priorities Flowchart and Time Sequence - Researchers analyze the order of events or decisions - Historical researchers have traditionally focused on documenting the sequence of events, but comparative an field researchers use the idea of a decision tree or flowchart to outline the order of decisions, and to understand how on event or decision is related to others Multiple Sorting Procedure - Technique similar to domain analysis that a researcher can use in field research or oral history - Its purpose is to discover how people categorize their experiences or classify items into systems of “similar” and “different” - The multiple sorting procedures has been adopted by cognitive anthropologists and psychologists - It can be used to collect, verify, or analyze data - Researcher gives those being studied a list of terms, photos, places, names of people, and so on and asks them to organize the lists into categories or piles Diagrams - Diagrams and charts help researchers organize ideas and systematically investigate relations in the data, as well as communicate results to readers - Miles and Huberman  argued that data display is a critical part of qualitative analysis  they suggested the use of flowcharts, organizational charts, and causal diagrams, and various lists and grids to illustrate analysis Software For Qualitative Data - Qualitative researchers moves to computers and diagrams only in the past decade or so (quantitative have used them for 40 years) - It is easier for qualitative researchers to search through documents on the computer - Some have hypertext capabilities  is a means of linking terms to other information - Code-and-retrieve programs allow a researcher to attach codes to lines, sentences, paragraphs, or blocks of text Chapter 11: Analysis Of Quantitative Data Dealing With Data Coding Data - Before a researcher examines quantitative data to test hypothesis, he or she needs to organize them in a different form - Coding  systematically reorganizing raw numerical data into a format that is easy to analyze using computers - Coding can be simple clerical task when the data are recorded as numbers on well-organized sheets - Researchers develop rules to assign certain numbers to variable attributes - Codebook  is a document describing the coding procedure and the location of data for variables - Precoding  means placing the code categories on the questionnaire Entering Data - Row = represents a respondent, subject, or case - Column = represents specific variables - Four ways to get raw quantitative data into a computer  1. Code sheet  gather the information, and then transfer it from the original source onto a grid format  type what is on the code sheet into a computer, line by line 2. Direct-entry method  as information is being collected, sit at a computer keyboard while listening t /observing the information and enter the information, or have a respondent /subject enter the information himself or herself 3. Optical scan  gather the information, then enter it onto optical scan sheets by filling in the correct dots  optical scan to transfer to computer 4. Bar code  gather the information and convert it into different widths of bars that are associated with specific numerical values, and then use a bar-code reader to transfer the information into a computer Cleaning Data -Accuracy is extremely important when coding data  errors in code threatens the validity of measures - Possible code cleaning  (wild code checking) involves checking the categories of all variables for impossible codes - Contingency cleaning  (consistency checking) involves cross classifying two variables and looking for logically impossible combinations Results With One Variable Frequency Distributions - Descriptive statistics  describe numerical data  can be categorized by the number of variables involved: univariate, bivariate, or multivariate - Univariate  describe one variable - Frequency distribution  easiest way to describe numerical data  a table that shows the distribution of cases into the categories of one variable - Information can also be displayed graphically  histogram, bar chart, pie chart Measures of Central Tendency - Mode  indicates the most frequent or common score  is the easiest to use and can be used with nominal, ordinal, interval or ratio data - If there are two scores that are tied for the most frequent, then it is called a bimodal distribution -Any distribution with more than one mode is called multimodal - Median  is the middle point  is the 50 percentile, or the point at which half of the cases are above it and half below it  can be used with ordinal, interval or ratio level data (not nominal) - Mean  the arithmetic average, is the most widely used measure of central tendency  only used with interval or ratio level data  add all scores and divide by number of scores - Normal distribution  a “bell shapes” frequency polygon for a distribution of cases, with a peak in the center and identical curving slopes on either side of the center  the measures of central tendency are equal to each other - Skewed distribution  a distribution of cases among the categories of a variables that is not normal  instead of an equal number of cases on both ends, more are at one of the extremes  more cases in the upper or lower scores - If most cases have lower scores with a few extreme high scores, the mean will be the highest the median in the middle, and the mode the lowest - If most cases are higher scores with a few extreme low scores, the mean will be the lowest, the median in the middle, and the most the highest Measures of Variation - Measures of central tendency are a one number summary of a distribution; however they give only its center -Another characteristic of a distribution is its spread, dispersion, or variability around the center - Two distributions can have identical measures of central tendency but differ in their spread around the center - Range  is the simplest  it consists of the largest and smallest scores  highest minus lowest score - Percentiles  tell the scores at a specific place within the distribution  median is a percentile  the 25 percentile is the score at which 25 percent of the items in the distribution have either that score or a lower score  If you have 100 people and want to find the 25 percentile you rank the scores and count up from the bottom until you reach number 25 - Standard Deviation  is the measure of dispersion most difficult to compute; it is also the most comprehensive and widely used - The range and percentile are for ordinal, interval, and ratio level data, but the standard deviation requires an interval or ratio level of measurement  standard deviation is based on the mea and gives an “average distance” between all scores ad the mean - The standard deviation is used for comparison purposes - The standard deviation and the mean are used to created z-scores  they let a researcher compare two or more distributions or groups  this score expresses points or scores on a frequency distribution in terms of a number of standard deviations from the mean Results With Two Variables A Bivariate Relationship - Bivariate variables  let a researcher consider two variables together and describe the relationship between variables - Bivariate statistical analysis shows a relationship between variables - Statistical relationships are based on two ideas  1. Correlation  he idea that two variables vary together, such that knowing the values in one variables provides information abut values found I another value 2. Independence  the absence of a statistical relationship between two variables (when knowing the values on one variables provides no information about the values that will be found on another variable)  no association between variables - Null hypothesis  the hypothesis is that there is independence  used in hypothesis testing and frequently found in inferential statistics - Three techniques help researchers decided whether a relationship exists between two variables  1.Ascatter gram, or graph or plot of the relationship 2. Cross tabulation, or a percentage table 3. Measures of association between two variables expressed as a single number Seeing the Relationship: The Scattergram What is a Scattergram (scatterplot)? - Scattergram  is a graph on which a researcher plots each case or observation, where each axis represents the value of one variable - It is used for variables measures at the interval or ratio level, rarely for ordinal variables, and never if either variable is nominal - Usually the independent variable goes on the horizontal axis and the dependent variable in the vertical axis (X and Y) What Can you Learn from the Scattergram? - Can se three aspects of a bivariate relationship on a Scattergram Form - Independent (no relationship)  looks like a random scatter with no pattern, or a straight line that is exactly parallel to the horizontal or vertical axis - Linear relationship  means that a straight line can be visualized in the middle of a maze of cases running from one corner to another - Curvilinear relationship  means that the center of a maze of cases would form a U curve, right side up or upside down, or an S curve Direction - Linear relationships can have a positive or negative direction - Positive relationship  looks like a diagonal line from the lower left to the upper right  higher values with X tend to go with higher values on Y - Negative  looks like a line from the upper left to the lower right  higher values on one variable go with lower values on the other Precision - Is the amount of spread in the points on the graph -Ahigh level of precision occurs when the points hug the line that summarizes the relationships -Alow level of occurs when the points are widely spread around the line Bivariate Tables What is a Bivariate Table? - Based on cross-tabulation  the cases re organized in the table on the basis of two variables at the same time  placing data for two variables in a contingency table to show the number or percentage of cases at the intersection of categories of the two variables - Contingency table  is formed b cross-tabulating two or more variables  it is contingent because the cases in each category of a variable get distributed into each category of a second variable - Three ways to a percentage table  by row by column, and for the total Reading a Percentaged Table - Researchers read Percentaged tables to make comparisons  comparisons are made in the opposite direction from that in which percentages are computed -As a rule of thumb is to compare across rows if the table is Percentaged down and to compare up and down in columns if the table is Percentaged across - If there is no relationship in a table, the cell percentages look approximately equal across rows or columns  a linear relationship looks like larger percentages in the diagonal cells - If there is a curvilinear relationship, the largest percentages form a patters across cells Bivariate Tables Without Percentages - Condense information into another kind of bivariate table with a measure of association (usually mean) instead of percentages - It is used when one variable is nominal or ordinal and another is measured at the interval or ratio level - The mean of the interval or ratio variable is presented for each category of the nominal or ordinal variable -All cases are divided into the ordinal or nominal variable categories; then the mean is calculated for the cases in each variable category from the raw data Measures of Association -Ameasure of association is a single number that expresses the strength, and often the direction, of a relationship - It condenses information about a bivariate relationship into a single number - Correct measure of association depends on the level of measurement - Meany measures are called by letters of the Greek alphabet  lambda, gamma, tau, chi, and rho are commonly used measures - The emphasis here is interpreting the measures, not on their calculation - If there is a strong association or relationship, then few errors are made predicting a second variable on the basis of knowledge of the first, or the proportion of errors reduced is large More Than Two Variables Statistical Control - Showing an association or relationship between two variables is not sufficient to say that an independent variable causes a dependent variable - In addition to temporal order and association, a researcher must eliminate alternative explanations  that can make the hypothesized relationship spurious - Experimental researchers do this by choosing a research design that physically controls potential alternative explanations for results - No experimental research, a researcher controls for alternative explanations with statistics  he or she measures possible alternative explanations with control variables, then examines the control variable with multivariate tables and statistics that help him or her decide whether a bivariate relationship is spurious -Aresearcher controls for alternative explanations in multivariate analysis by introducing a third variable  to test whether a relationship is actually due to sex, a researcher must control for gender; in other words, effects of sex are statistically removed  then you can see whether the bivariate relationship between height and attitude toward sports remains -Aresearcher controls for a third variable by seeing whether the bivariate relationship persists within categories of the control variable - If the bivariate relationship weakens or disappears after the control variable is considered it means that the original bivariate relationship was spurious - Until a researcher considers control variables, the bivariate relationship could be spurious The Elaboration Model of Percentaged Tables Constructing Trivariate Tables -Atrivariate table has a bivariate table of the independent and dependent variable for each category of the control variable  the new tables are called partials  the number of partials depends on the number of categories in the control variable  they look like bivariate tables but they use a subset of the cases - Trivariate tables have three limitations  1. They are difficult to interpret if a control variable has numerous categories 2. Control variables can be at any level of measurement, but interval or ration control variables must be grouped , and how cases are grouped can affect the interpretation of effects 3. The total number of cases is a limiting factor because the cases are divided among cells in partials - Elaboration paradigm  is a system for reading percentaged trivariate tables  it describes the pattern that emerges when a control variable is introduced - Replication pattern  is the easiest to understand  it is when the partials replicate or reproduce the same relationship that existed in the bivariate table before considering the control variable  means that the control variable has no effect - Specification Pattern  next easiest  occurs when one partial replicates the initial bivariate relationship but other partials do not - Interpretation pattern  describes the situation in which the control variable intervenes between the original independent and dependent variables  contingency tables shows a relationship but the partials show no relationship and the control variable is intervening in the causal explanation - Explanation pattern  looks the same as interpretation  the difference is the temporal order of the control variable  in this pattern, a control variable comes before the independent variable in the initial bivariate relationship - Suppressor variable pattern  occurs when bivariate tables suggest independence but a relationship appears in one or both of the partials  no relationship appears in a bivariate contingency table but the partials show a relationship between the variables Multiple Regression Analysis - Requires interval or ratio level data - Discussed for two reasons  1. It controls for many alternative explanations and variables simultaneously 2. It is widely used in social science - Multiple regression results tell the reader two things  1. The results have a measure called R-squared, which tells how well a set of variables explains a dependent variable  explain means reduced errors when predicting the dependent variables scores on the basis of information bout the independent variables 2. The regression results measure the direction and size of the effect of each variable on a dependent variable - The effect on the depend variable is measured by a standardized regression coefficient or the Greek letter beta  similar to correlation coefficient  the beta coefficient for two variables equals r correlation coefficient - Researchers use the beta regression coefficient to determine whether control variables have an effect  next the researcher statistically considers four control variables  if the beta remains 0.75 then the four variables have no effect Inferential Statistics The Purpose of Inferential Statistics - Inferential statistics use probability theory to test hypothesis formally, permit inferences from a sample to a population, and test whether descriptive results are likely to be due to random factors or to a real relationship - Inferential statistics rely on principles from probability sampling, where a researcher uses random process to select cases from the entire population - Inferential statistics are precise means of talking about how confident a researcher can be when inferring from the results in a sample to the population Statistical Significance - Statistical significance means that results are not likely to be due to chance factors  it indicates the probability of finding a relationship in the sample when there is non in the population - Because probability samples involves a random process, it is always possible that sample results will differ from a population parameter -Aresearcher wants to estimate the odds that sample results are due to a true population parameter or to chance factors of random sampling - Statistical significance only tells us what is likely it cannot prove anything with absolute certainty  it states that particular outcomes are more or less probable Levels of Significance - Researchers usually express statistical significance in terms of levels rather than giving the specific probability - The level of statistical significance (0.05, 0.01, 0.001) is a way of talking about the likelihood that results are due to chance factors  that is, that a relationship appears in the sample when there is none in the population - Significant at the 0.05 level means the following  - Results like these are due to chance factors only 5 in 100 times - There is a 95 percent chance that the sample results are not due to chance factors alone, but reflect the population accurately - The odds of such results based on chance alone are 0.05 or 5 percent - One can be 95 percent confident that the results are due to a real relationship in the population, not chance factors - These all say the same thing in different ways - Probability theory lets us predict what happens in the long run over many events when a random process is used  It allows precise prediction over many situations in the long run, but not for a specific situation Type I and II Errors - The logic of statistic significance is based on stating whether chance factors produce results - 0.05 confidence level = 5 percent chance that randomness could cause the results  scientific community has informally agreed to use 0.05 as a rule of thumb for most purposes  being 95 percent confident of results is the accepted standard for explaining the social world - Type I error  occurs when the researcher says that a relationship exists when in fact non exists  it means falsely rejecting a null hypothesis - Type II error  occurs when a researcher says that a relationship does not exist, but in reality it does  it means falsely accepting a null hypothesis -As the odds of making one type of error decline, the odds of making the opposite error increase -An overly cautious researcher sets a high level of significance and may use the 0.0001 level  such a high standard means that the researcher is most likely to err by saying results are due to chance when in fact they are not = falsely accept null hypothesis when there is a causal relationship - Contrast  risk taking researchers sets a low level of significance such as 0.10  his or her results indicate a relationship would occur by chance 1/10 times  would be likely to error by saying that a causal relationship exists, when in fact random factors actually cause the results Chapter # 8: Survey Research - Survey is the most widely used data gathering technique in sociology Research Questions Appropriate for a Survey - Survey research developed within the positivist approach to social science - Survey is appropriate for research questions about self reported beliefs or behaviors - They are strongest when the answers people give to questions measures variables - Categories overlap  the following can be asked 1. Behavior 2.Attitudes/beliefs/opinions 3 Characteristics 4. Expectations 5. Self-classification 6. Knowledge - Researchers warn against using surveys to ask “why?” questions -An important limitation of survey research is that it provides data only of what a persons or organizations says, and this may differ from what he or she actually does The Logic of Survey Research What is a Survey? - Survey researchers sample many respondents who answer the same questions, in the same order, in the same way - Survey research is often called correlational - Survey researchers use questions as control variables to approximate the rigorous test for causality that experimenters achieve with their physical control over temporal order and alternative explanations  control variables are other characteristics that the researcher accounts for so as to minimize the possibility of spuriousness Steps in Conducting a Survey - The survey researcher follows a deductive approach  he or she begins with a theoretical or applied research problem and ends with empirical measurement and data analysis - Step 1 - Develop hypotheses - Decide on type of survey (mail, interview, telephone) - Write survey questions - Decide on response categories - Design layout - Step 2 - Plan how to record data - Pilot-test survey instrument - Step 3 - Decide on target population - Get sampling frame - Decide on sample size - Select sample - Step 4 - Locate respondents - Conduct interviews - Carefully record data - Step 5 - Enter data into computers - Recheck all data - Perform statistical analysis on data - Step 6 - Describe methods and finding in research reports - Present findings to other for critique and evaluation -Asurvey researcher conceptualizes and operationalizes variables as questions - When preparing a questionnaire, the researcher thinks ahead to how he or she will record and organize the data for analysis - Pilot test  give questionnaire to a small group  asks the participants in this test whether the questions were clear etc. - Survey research can be complex and expensive and it can involve coordinating many people and steps - The administration of survey research requires organization and accurate record keeping  meticulous bookkeeping and labeling are essential Constructing The Questionnaire Principles of Good Question Writing - There are three principles for effective survey questions - Keep it clear - Keep it simple - Keep the respondent’s perspective in mind - Questions that do not mesh with a respondents viewpoint or that respondents find confusing are not good measures - Researchers face a dilemma  they want all respondents to hear exactly the same questions, but will the questions be equally clear, relevant, and meaningful to all respondents? - Twelve things to avoid  1. Jargon, slang, and abbreviations 2. Avoid ambiguity, confusion, and vagueness  “what is your income?” can mean different things 3. Avoid emotional language  words that have implicit connotative as well as explicit denotative meanings  neutral language 4. Avoid prestige bias  prestige bias = a problem in survey research question writing that occurs when a highly respected group or individual is linked to one of the answers 5. Avoid double-barreled questions  consists of two or more questions joined together  makes a respondents answer ambiguous 6. Do not confuse beliefs with reality  do not confuse what they believe with what you, the researcher has measured 7. Avoid leading questions  a question that leads the respondent to choose on response over another by its wording  “you don’t smoke do you?” 8. Avoid asking questions that are beyond respondents capabilities  asking something that few respondents know frustrates respondents and produces poor-quality responses 9. Avoid false premises  Do not begin a question with a premise with which respondents may not agree and then follow it by choices regarding it  respondents who disagree with the premise will be frustrated and not know how to answer 10. Avoid asking about intentions in the distant future  asking people what they might do under hypothetical circumstances far in the future 11. Avoid double negatives  they are grammatically incorrect and confusing  “I aint got no job” 12. Avoid overlapping or unbalanced response categories  make response categories or choices mutually exclusive, exhaustive, and balanced  mutually exclusive means that response categories’do not overlap Aiding Respondent Recall - Survey researchers recognize that memory is less trustworthy than was once assumed - Memory is affected by many factors  the topic, events occurring simultaneously and subsequently, the significance of an event for a person, situational conditions, and the respondents need to have internal consistency - The complexity of respondent recall does not mean that survey researchers cannot ask about past events; rather, they need to customize questions and interpret results cautiously Types of Questions and Response Categories Threatening Questions - Survey researchers sometimes ask about sensitive issues or issues that respondents may believe threaten their presentation of self, such as questions about sexual behavior, drug or alcohol use, mental health problems, or deviant behavior - Respondents may be reluctant to answer questions or to answer completely and truthfully - Threatening questions  are part of a larger issue of self-presentation and ego protection  respondents often try to present a positive image of themselves to others  they may be ashamed, embarrassed, or afraid to give truthful answers, or find it emotionally painful to confront their own actions honestly, let alone admit them to other people - People are likely to underreport having an illness or disability, engaging in illegal or deviant behavior, or revealing their financial status - Researchers should ask threatening questions only after a warm up when an interviewer has developed rapport and trust with the respondents, and they should tell the respondents that they want honest answers Socially Desirable Questions - Social desirability bias  occurs when respondents distort answers to make their reports conform to social norms - People tend to over report being cultured (reading, attending high-culture events), giving money to charity, having a good marriage, loving their children, and so forth - Questionnaire writers try to reduce social desirability by phrasing question in ways that make norm violation appear less objectionable and the present a wider range of behavior as acceptable - They can also offer multiple response categories that give respondents “face saving” alternatives - Mode of delivery  means by which a survey is conducted  can affect response to questions that may be affected b social desirability - Individuals who have less direct personal contact with an interviewer may be less swayed to give “desirable” answers Knowledge Questions - Studies suggest that a large majority of the public cannot correctly answer elementary geography questions or identify important political documents - Researchers sometimes want to fin out whether respondents know about an issue or topic, but knowledge questions can be threatening because respondents do not want to appear ignorant - Surveys may measure opinions better if they first ask about factual information, because many people have inaccurate factual knowledge - Simple questions such as “how many people in the household?” can be answer incorrectly  a marginal person i.e. boyfriend, adult child who left after an argument, uncle who walked out after dispute  they may not have another permanent residence Skip or Contingency Questions - Contingency question  is a two (or more) part question - The answer to the first part of the question determines which of the two different questions a respondent next receives - They select respondents for whom a second question is irrelevant - Can be called screen or skip questions Open Versus Closed Questions - Open-ended (unstructured, free response) question  asks a question to which respondents can give any answer - Closed ended (structured, fixed response) question  both asks a question and gives the respondent fixed responses from which to choose -Advantages Vs. Disadvantages table on page 164 -Aresearchers choice to use an opened or closed ended question depends on the purpose and the practical limitations of a research project - The demands of using open-ended questions, with interviewers writing verbatim answers followed by time consuming, coding, may make them impractical for a specific project - Large scale surveys have closed-ended questions because they are quicker and easier for both respondents and researchers - The disadvantage of a question form can be reduced by mixing open ended and close-ended question in a questionnaire - Having interviewers periodically use probes to ask about a respondents thinking is a way to check whether respondents understand the questions as the researcher intended - Partially open questions  which allows respondents to offer an answer that the researcher did not include  respondents are given a fixed set of answers to choose from, but in addition, an “other” category is offered so that they can specify a different answer - Open-ended questions are especially valuable in early exploratory stages of research - For large-scale surveys, researchers se open questions in test pilots  then they develop closed question responses from the answers given to the open questions Nonattitudes and the middle Positions - Survey researchers debate whether to include choices for neutral, middle, and nonattitudes  two types of errors can be made  1.Accepting a middle choice or “no attitude” response when respondents hold a non-neutral opinion 2. Forcing respondents to choose a position on an issue when they have no opinion about it - Many researchers fear that respondents will choose non-attitude choices to avoid making a choice - By offering a nonattitudes choice, researchers identify those holding middle positions or those without opinions - Three types of attitude questions  1. Standard format question  categories fail to include a “no opinion” or “don’t know” 2. Quasi –filt
More Less

Related notes for Sociology 2206A/B

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.