| Session Title: Applying Binary Logistic, Ordered and Unordered Multinomial Logistic Regression Models to Illuminate Learning From Evaluation in Practice |
| Demonstration Session 416 to be held in Carroll Room on Thursday, November 8, 3:35 PM to 5:05 PM |
| Sponsored by the Social Work TIG |
| Presenter(s): |
| Mansoor Kazi, University at Buffalo, mkazi@buffalo.edu |
| Tom Nochajski, University at Buffalo, thn@buffalo.edu |
| Carrie Petrucci, California State University, Los Angeles, cpetruc@calstatela.edu |
| Abstract: This demonstration will illustrate new data analysis tools drawn from both the efficacy and epidemiology traditions to investigate patterns in relation to outcomes, interventions and the contexts of practice. The demonstration will include three different applied categorical data analyses: when the outcome is dichotomous (logistic regression), when the outcome has three or more unordered categories (nominal multinomial logistic regression), and when the outcome has three or more ordered categories (ordinal multinomial logistic regression) (Hosmer & Lemeshow, 2000; Kazi, 2003; Jaccard & Dodge, 2004). The presenters will use datasets from their completed evaluations from California, New York and United Kingdom, and discuss real-world applications of the analyses and their contribution to learning from evaluation. The didactic approach will be interactive, guiding the workshop participants through the requirements and limitations of each method, and demonstration its use from practice examples, e.g. human service evaluations of driving whilst intoxicated (DWI) programs. |