Class Notes (836,365)
Canada (509,756)
Sociology (3,253)
SOC200H1 (95)
Lecture 7

Sociology Lecture 7.docx

11 Pages
Unlock Document

Alexandra Marin

What is a SurveyData collection methodRespondents receive a uniform questionnaire not your subjectsMost common source of quantitative data in sociologyUse probability sampling methods to allow for clearer conclusions from quantitativeSurveys ARE NOT experimentsAsk a Research QuestionUseful for explanatory and descriptive researchFor example how many high school students smokeWhat proportion of adult Canadians are unemployedNot useful for exploratory research because in a survey you enter the research with some idea of what the answers to the questions are and what to look forDerive one or more HypothesesNot always possible or necessary if your research is descriptiveState hypotheses as comparisons between people who have different values on the independent variableThere can sometimes be more than one hypothesisH1 people who have had frequent exposure to violence are more likely to be depressed than people who have little or no exposure to violenceH2 the more violence a person has been exposed to the higher his or her depression score will beSometimes there are reasons that suggest one hypothesis and equally compelling reasons to support anotherH1 couples with higher combined incomes are more likely to divorce than couples with lower combined incomesH2 couplesSurvey ModeSelfAdministered1Mail in Questionnaire2Web SurveyInterviewer Administered1Phone Survey2FacetoFace InterviewChoosing a SampleStrength of probability sampling is that it makes it possible to generalizeConsider the units of analysis will the data be aggregated If so need to include enough units within each aggregated groupEnsure that the sample includes enough people with attributes to be studied if age is to be studied there needs to be enough people in each age group about which conclusions will be drawnYou know how but how manyQ how many do you need for whatA to be reasonable certain that the sample statistic that you get accurately reflects the corresponding population parameterProblem is that whatever you find could be a flukeLevel of ConfidenceImpossible to rule out a fluke but we can have an idea of how likely it is that our sample is a flukeCalculate the confidence interval which is a range of values within which we expect the population parameter will be with some level of confidenceExample These findings are accurate3 percentage points 19 times our of 20Thewould be the confidence interval while the 1920 would be the level of confidenceSampling DistrubutionImagine that at U of T the average student is taking 35 courses
More Less

Related notes for SOC200H1

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.