Study Guides (248,413)
Canada (121,518)
POL2156 (11)

Final exam notes.doc

11 Pages
Unlock Document

Political Science
Stephanie Mullen

Survey ConstructionImportant pointsUse neutral Language this avoids bias or leadingBe clear What is your incomeunclearfamily individual gross after tax incomeKeep response categories mutually exclusiveexhaustive no overlap in categorieshave all choices available as a category otherno responseSelect the highest reliable level of measurement not always possibleincomePay close attention to question order what comes 1st will contaminate what comes afterleave intrusive questions to the end of surveyMinimize defensive reaction In some cases it is important to assure respondents that a socially incorrect response is all rightOpenended questions Advantages allows for a greater range of answers the respondent is not limited to or biased by preset response categoriesmay provide answers that lead the researcher into new theoretical watersDisadvantages there are many possible answers to any given question making data entry difficult respondents will spend more time on open questions making the questions less efficient and comparisons between individuals can be complicatedCloseended questionsAdvantages respondents can answer the questions quickly it is easy to compare the responses of different individualsdata entry is less complex Disadvantages asks respondents to give a simple response to a very complex issue and by providing categories for the respondent may encourage the statement of opinion or knowledge where none actually existsIntensity measureIntensity measure is useful in capturing how strongly respondents feel about certain issues at the point in time that the survey was conductedThe response categories is simply a number scale usually from 17No labels are attached to the 1 or 7 such as Strongly disagrees and Strongly agrees although we can imply that the lower number means that the issue is not important or not as important as other issues to themMatrix formatInstead of asking a direct question for each IV Control and DV you are interested in you can develop statements which you want respondents to give their feelings on and get deeper opinions Standard Question How strongly do you feel about gun control17 Matrix FormatGun controla is a waste of taxpayers dollars17b reduces violent crime 17Twodirectional Intensity ScaleWe now attach both negative and positive labels to the category numbers Onedirectional ScaleHow strongly do you feel about gun control17Twodirectional ScaleGun control is very important for a society 135Strongly DisagreeN Strongly Agree Always include a neutral category in the middleRanking QuestionsSometimes it may be interesting to ask people to rank or put into an order of preference a set of itemsExample From the list of policy issues below rank in order of importance to you DefenceImmigration Health Care UnemploymentDo not have respondents rank more than 5 items because it gets too complicatedNote Respondents intensity for each issue is not measured just the rank in order of importance to them In fact one respondents could be passionate about the rank items 15 whereas another respondent is only passionate about 1 itemWording of Questions Cautionary NotesDosDontsDirection of Statements Never use Always and NeverAvoid Doublebarreled ItemsAvoid LeadingLoaded QuestionsLanguagewriting for the education level of the respondentsHave Mutually exclusive and exhaustive categoriesDemographic QuestionsInclude only Relevant Questions Chose Appropriate Levels of MeasurementBe Aware of Sensitive Items IncomeMutually Exclusive and Exhaustive revisitedLevel of measurementNominalOne category is neither higher nor lower than any other categorythey are simply different categories No underlying continuum and the numerical values assigned are arbitrary and have no arithmetical meaningOrdinal Ranks categories therefore there is order to the valuesbut this does not assure equal gaps between the measurement pointsIt is important to note that scales of 110 are considered ordinal because the gap differences between 34 is not the same as between 8 9IntervalThe zero point is aligned with true zerozero incomemeans you have no income The gaps between categories are equal the gap is 1000 between 3000 and 4000 as it is between 8000 and 9000
More Less

Related notes for POL2156

Log In


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.