Class Notes (836,293)
Canada (509,749)
Criminology (722)
CRM 204 (16)

CRM204: Week 7 (Oct. 24th).docx

4 Pages
Unlock Document

CRM 204
Smita Tyagi

th CRM 204 –Criminal Justice Research and Statistics (October 24 , 2012) How large should a sample be? ‘Depends’ (on research question, purpose of research, degree of accuracy required, population characteristics) Different approaches to choice of sample. For our purposes here is one guideline Gay. L.R (1996). Educational research: Competencies for analysis and application (5 ed). Upper Saddle River, NJ: Merrill Prentice-Hall If less than 100 survey entire population If population 500 sample 50% If population 1500 sample 20% If population 5000+ 12-15% Considerations in sampling - Sampling distributions - Sampling error - Systematic sampling error - Random sampling error - Confidence intervals and confidence limits - Inferential statistics - Descriptive statistics Sampling error - Difference between a sample and a population from which it is selected. Non-Sampling error - Difference between the sample and population caused by deficiencies in sampling such as inadequate sampling frame or non-response or poorly designed measures or from flawed data processing. Non-response - A source of non-sampling error that occurs whenever some members of the sample refuse to co-operate, cannot be contacted or cannot supply the data required. Chp 8: Survey Research (Widespread use of surveys) - Development of statistical techniques - Development of scales and indexes to measure quantitative data in a systematic way - Broad applications discovered - Versatility - Efficiency - Generalizability - Omnibus survey Survey Questions - Open-ended or interpretive questions - Closed ended or fixed choice questions Pre-testing is a MUST! Clear and Meaningful Questions - Be clear not ambiguous - Reframe potentially threatening - Check reading levels of respondents questions (Social desirability can cause first overreporting or underreporting) - Avoid leading questions - Choose wisely between open and - Avoid double barrelled questions closed questions - Avoid double negatives - Consider question order or sequence of - Avoid emotional language and prestige questions bias - Be aware of aiding respondent recall - Avoid asking questions beyond the - Consider using rating or ranking person’s capability questions - Avoid overlapping or unbalanced - Consider trade-off between gathering response categories lots of data and gathering less data but - Use contingency or skip questions accurate (and complete) data - Demographic questions (Tombstone data) Survey Questionnaires - Cover letter: - - Personalized - Credible - Interesting - Responsible Design of the Survey - Electronic surveys and web surveys (Refer class hand-out on online surveys) - Survey monkey Mailed Self-Administered Surveys (Page 232-233) - Attractive - Credible research sponsor - Less use of contingent questions - Identifying code on each questionnaire - Clear and understandable - Use of incentive - Less use of open-ended questions - Stamped self-addressed envelope - Personalized, professional cover letter
More Less

Related notes for CRM 204

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.