Overview

Description

CALENDAR DESCRIPTION:

A survey of advanced statistical techniques in criminological research. Specific topics may include: limited (e.g., categorical, ordinal, and count) dependent variables, multi-level modeling, longitudinal data techniques, spatial data analysis, missing values analysis, and propensity score matching. Attention will be given to the decisions involved in data exploration and preparation for statistical modeling purposes using the appropriate statistical software. There is an emphasis on conceptual foundations and application. A strong background in regression-based techniques is assumed.

COURSE DETAILS:

This course will address a range of statistical techniques, primarily parametric statistics. The seminars will allow the instructor to present one particular statistical technique, i.e.: purposes, assumptions, type of information provided, interpretation of the results, how to conduct such analysis using sophisticated statistical software: I will be using R, but you may use other software such as Stata or SAS. The seminar will also include a discussion on the technique using published scientific studies, i.e.: strengths and limitations of the statistical analysis, when to use (and not to use) such technique, as well as the interpretation of the findings.

Participation
This course is predicated on active and informed participation. Simply coming to class every week, occupying space, and warming the room is not enough. You are expected to have done the readings for each week before the class, and to be prepared to discuss them.

Course Structure
This course is set up as “BLENDED”. We will always be synchronous, but we will meet in person on odd weeks, starting 08 January 2024. There is one seminar (2 hours) per week, plus one 1-hour lab. These will consist of the first 2 hours of this course each week (seminar/discussion/lecture). We will then have a tutorial/seminar (I will be present but not providing new material). The tutorial will occur during the last hour of the course, 730pm – 820pm, beginning on the first day of classes, 08 January 2024.

Last day of class is April 8, 2024.

Grading

Materials

MATERIALS + SUPPLIES:

No official textbook for this course. I am providing a number of references below as resources for you.

I will also be using a set of books from the “Blue Book” series written by G. David Garson. These books are $5 for Kindle versions, but can be obtained for free by filling out a form requesting PDF copies; only two books may be requested per 48 hours.

The web page for these books, with information on the books is here:

http://statisticalassociates.com

And the list of these books is available here:

http://statisticalassociates.com/booklist.htm

We will be covering material from the following Blue Books:

• Multiple Regression
• Logistic Regression, Binary & Multinomial
• Ordinal Regression

If you are obtaining these books for free I suggest you get them early because there is a delay in obtaining access and you can only request two books per 48 hours.

The following books are all available in Full text - Unlimited user access from SFU Library and may prove to be useful (Ignore the math, unless you are interested!):

1. Lewis-Beck, Michael. Applied Regression: An Introduction. Thousand Oaks, CA: Sage Publications, 1980. ISBN: 9780803914940

2. Jaccard, James and Robert Turrisi. Interaction Effects in Multiple Regression. Thousand Oaks, CA: Sage Publications, 2003. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412984522

3. Berry, William D. and Stanley Feldman. Multiple Regression in Practice. Thousand Oaks, CA: Sage Publications, 1985. ISBN: 9780803920545

* Ignore: Measurement Error, Nonlinearity and Nonadditivity

4. Kaufman, Robert L. Heteroskedasticity in Regression: Detection and Correction. Thousand Oaks, CA: Sage Publications, 2013. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781452270128

5. Allison, Paul D. Fixed Effects Regression Models. Thousand Oaks, CA: Sage Publications, 2009. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412993869

6. Finkel, Steven E. Causal Analysis with Panel Data. Thousand Oaks, CA: Sage Publications, 1995. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412983594

7. Pampel, Fred C. Logistic Regression: A Primer. Thousand Oaks, CA: Sage Publications, 2000. ISBN: 9780761920106

* Ignore: Estimation and Model Fit, Probit Analysis

8. Menard, S. Applied Logistic Regression Analysis. Thousand Oaks, CA: Sage Publications, 2002. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412983433

9. Jaccard, James. Interaction Effects in Logistic Regression. Thousand Oaks, CA: Sage Publications, 2001. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412984515

10. Borooah, Vani K. Logit and Probit. Thousand Oaks, CA: Sage Publications, 2002. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412984829

11. Luke, Douglas A. Multilevel Modeling. Thousand Oaks, CA: Sage Publications, 2004. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412985147

12. Ward, Michael D. amd Kristian Skrede Gleditsch. Spatial Regression Models. Thousand Oaks, CA: Sage Publications, 2008. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781412985888

13. Pickup, Mark. Introduction to Time Series Analysis. Thousand Oaks, CA: Sage Publications, 2015. DOI: http://dx.doi.org.proxy.lib.sfu.ca/10.4135/9781483390857

The “Sage Little Green Books” are technical at times, but excellent resources for the material we will cover.

There may also be other required readings (books, book chapters, journal articles, etc.) available through Canvas. You are responsible to download, photocopy, or borrow these readings from the library.

REQUIRED READING NOTES: