This week, you have been introduced to several concepts of logistic regression, specifically the odds ratio. In this Application, you will report the odds ratio in a given test.
To prepare for this Application:
• Review Chapter 19 of the Field text for a description of logistic regression and the odds ratio.

• Review the media resources demonstrating the odds ratio.
The assignment:
Complete Smart Alex’s Task #5 on p. 812 of the Field text. Include only Burnout as the independent variable and Coping Style and Stress from Teaching as the two dependent variables. Report the odds ratio ONLY.
Use APA format according to the guidelines in the IBM SPSS Statistics Application Assignment Guidelines handout. The final document should be 2–3 pages long.
Submit your Application to the Week 8 Assignment submission link by Day 7.

Week 8: Introduction to Logistic Regression: The Odds Ratio

Introduction
"Well, what are the odds of that happening?"
That’s a phrase you probably hear often in your everyday life. As you know, odds are an important statistical concept for everyone from Las Vegas high rollers to medical researchers. Odds are used commonly in health research (for example, the odds ratio might be used to describe the odds that one ethnic group will contract some disease compared to another).
This week, you will learn the foundations of the odds ratio and determine when it is appropriate for use in your field.
Reminder: Your literature review for your Final Project will be due at the end of Week 9.

Learning Outcomes
By the end of this week, you will be able to (for linear multiple regression):
• State underlying assumptions

• Determine whether assumptions have been met
• Propose alternatives if assumptions are not met
• State null and alternative hypotheses
• Analyze data using IBM SPSS Statistics
• Interpret and report the results with IBM SPSS Statistics, including effect size
• Describe sample size
• Report results in APA format

Resources

SKIP TO COURSE MENUSKIP TO TOP FRAME TABS
Resources

Required Resources
• Course Text: Discovering Statistics Using IBM SPSS Statistics
•
o Chapter 19, "Logistic Regression" (pp. 760–792, 812)

This chapter describes the principles of logistic regression, including binary logistic regression, and provides an introduction to the odds ratio.

•
• Handout: Statistics Application Evaluation Criteria (Word document)

This handout will guide you in completing and submitting your odds ratio Application Assignment for this week.

• Software: IBM SPSS Statistics Standard GradPack (current version). Available in Windows and Macintosh versions. Please refer to the IBM SPSS Software area on the left navigation bar for more information on how to install, register, and license this software.

You will use this software to complete this week’s Application Assignment.

• Media:
o Advanced Multiple Regression — Conceptual (Adobe Captivate)

Dr. Jennifer Morrow explains the odds ratio and provides an example of calculating the odds ratio using PASW. This Flash-based demonstration will open in a new window.

Click here to download a transcript of this demonstration.

o Advanced Multiple Regression — Applied (Adobe Captivate)

Dr. Jennifer Morrow provides an example of a multiple regression. This Flash-based demonstration will open in a new window.

Click here to download a transcript of this demonstration.
Note: This media appears in the resources for both weeks 8 and week 9.

Research Toolkit
Research Design
• Website: Web Center for Social Research Methods
https://www.socialresearchmethods.net

This website is for people involved in applied social research and evaluation. You will find several resources and links to other locations on the web that deal in applied social research methods.

• Website: Cengage Research Methods Workshops
https://www.wadsworth.com/psychology_d/templates/student_resources/workshops/resch_wrk.html

This website offers many useful workshop topics such as experimental methods, reliability and validity, surveys, sampling methods, ethical issues, and evaluating published research.
Statistics and SPSS
• Website: SPSS Student Resource Center
www.ibm.com/software/analytics/spss/support/techsupport.html

The SPSS student support site provides a knowledgebase and allows students to request assistance from SPSS Technical Support staff. Since this site is produced and maintained by the creators of the PASW software, it is the best place to go when you have a question about the software.
• Website: UCLA’s ‘What Statistical Analysis Should I Use?’ Table
https://www.ats.ucla.edu/stat/mult_pkg/whatstat/default.htm

This statistics table shows general guidelines for choosing a statistical analysis, and links showing how to do such tests using SAS, Stata and PASW. This is a good place to go if you are not sure which statistical test would best answer the research question you have.

• Website: Statistics Hell
https://www.statisticshell.com/html/apf.html This site is Andy Field’s (the author of the main course text) online statistics resource. This site provides additional explanations beyond the textbook and more examples. This is the best place to go when you are confused about how to do a particular test.

• Website: Cengage Statistics Workshops
https://www.wadsworth.com/psychology_d/templates/student_resources/workshops/stats_wrk.html
This website offers many useful workshop topics such as experimental methods, reliability and validity, surveys, sampling methods, ethical issues, and evaluating published research.

• Text: Using Multivariate Statistics

o Chapter 1, "Introduction"

• Weblog Post: rlindsay. (2008, June 3). What is an odds ratio? Message posted to https://globalhealth.wordpress.com/2008/06/03/what-is-an-odds-ratio/

• Website: Uebersax, J. (2006). Odds ratio and Yule’s Q. Retrieved from https://www.john-uebersax.com/stat/odds.htm

The preceding three resources provide alternative explanations of the odds ratio.
Optional Resources

• Text: Publication Manual of the American Psychological Association

o Chapter 5, "Displaying Results"

• Media: Data Cleaning and Dealing with Assumptions (Adobe Captivate)

Dr. Jennifer Morrow explains the assumptions surrounding many of the tests you will study and explains ways that you can manage data that violates these assumptions. This Flash-based presentation will open in a new window.

Click here to download a transcript of this demonstration.

Smart Alex’s Solutions
Task 5
Four hundred and sixty-seven lecturers completed questionnaire measures of Burnout (burnt out or not), Perceived Control (high score = low perceived control), Coping Style (high score = high ability to cope with stress), Stress from Teaching (high score = teaching creates a lot of stress for the person), Stress from Research (high score = research creates a lot of stress for the person) and Stress from Providing Pastoral Care (high score = providing pastoral care creates a lot of stress for the person). Cooper, Sloan, and Williams’ (1988) model of stress indicates that perceived control and coping style are important predictors of burnout. The remaining predictors were measured to see the unique contribution of different aspects of a lecturer’s work to their burnout. Conduct a logistic regression to see which factors predict burnout. The data are in Burnout.sav.
Test
The analysis should be done hierarchically because Cooper’s model indicates that perceived control and coping style are important predictors of burnout. So, these variables should be entered in the first block. The second block should contain all other variables, and because we don’t know anything much about their predictive ability, we should enter them in a stepwise fashion (I chose Forward: LR).