Class Notes (866,423)
CA (523,205)
UTSG (45,221)
SOC (3,313)
SOC200H1 (95)

brief lect notes.docx

7 Pages

Course Code
Margaret Gassanov;

This preview shows pages 1 and half of page 2. Sign up to view the full 7 pages of the document.
Lecture 9 Surveys: activity that collects info in characteristics from all units of population using concepts, methods, procedures, compiles info into summary form Questionnaire: collect data in same format from all respondents Probability sampling Often done for quantitative analysis Many topics are appropriate Question types: open ended, close ended, question, statement, matrix, contingency Common errors: unclear, slang, irrelevant questions, long item, negative item, bias item Keep in mind: intro, order of item and subsection, instruction, introduction to subsection, layout, respondent indicate their response, pretest your questionnaire Survey method: mail, handout, fax, electronic (web) Interviewer admin: phone, face to face Self admin (Adv) - easy to admin - low cost - more time to give well thought answers - ppl feel more comfortable giving truthful answers to sensitive questions - fast response/processing time (web) - flexibility in questionnaire design (web) Self admin (disadv) - topic must be straightforward - cant clarify questions or probe answer - lower response rate than other method - inferential statistics 推 论 统 计 require large random sample: representativeness - bias/unrepresentative - only ppl who feel strong about an issue may be answering - restricted to online population (web) - multiple responses are possible (web) - no info about physical/psychological condition in which the person filled out the survey - no anonymity in email - less likely to get long answers to open ended qs Mail - return rate graph - follow up mailings - letter of encouragement to non respondents - copy of questionnaire - postcard method: for anonymity, with questionnaire – returned at the same time - keep track of independent answers for questionnaire - acceptable response rates - inferential statistics 推 论 统 计 require large random sample: representativeness Interviewer assisted (Adv) - higher response rate - better quality of data - decrease donno/no answer - question can be clarified - probing for altern answer - useful when self admin is difficult - reading / writing is not necessary on the part of the respondent - more complex questionnaire - allow flexible collection period: if data collect is going too slowly and needs to be sped up, more interviewer can be hired (disadv) - expensive/difficult to manage than self admin survey - poorly trained interviewers can cause response error - anonymity is impossible - less time for respondent to think and formulate response Phone (Adv) - moderate cost - less time wasted compare to in person - mask identity - willing to give socially non desirable answers on phone than in person - greater control over data collection: with CATI, data can be entered directly in pc - safer - access widely dispersed respondent (disadv) - limited length for complex qs - cant make direct observation - less personal - limited population - limited in phonebook - respondent may be suspicious: hang up - answer machine Face to face (Adv) - can reach a population, no fixed residence - interviewer can observe respondents/setting in interviewed - interviewer can verify the correct sampling unit - respondent are willing to complete lengthier interview (disadv) - time consuming - high cost: smaller sample size than self admin or phone - difficult to implement a quality control program for process - the way interviewer looks like may cause bias Strength - useful in describing characteristics of large population - make large samples feasible - flexible: qs can be asked on given topic/ decide later which variables use in your analyses - strong on reliability - researchers assume the qs item mean the same to every respondent (standardized stimulus) Weaknesses - research design cant change once the survey instrument is in the field - weak on validity - lack of understanding - standardized qs don’t hv flexibility to deal with complex topics - full picture is rarely captured - subject to artificiality人工: self reports - social desirability bias - reports of behavior rather than observations of behavior - inability to recall past events accurately - misunderstanding questions Secondary data - by primary investigator who collected the data - advantages - cheaper/faster - usually high quality data - opportunity for more complex analyses (subgroup, longitudinal) (disavd) - lack of familiarity data and how it was collected: often complex - validity: relying on data collected to answer another research qs - available in dataset operationalized different
More Less
Unlock Document
Subscribers Only

Only pages 1 and half of page 2 are available for preview. Some parts have been intentionally blurred.

Unlock Document
Subscribers Only
You're Reading a Preview

Unlock to view full version

Unlock Document
Subscribers Only

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.