News - Rutgers - School of Health Professions

Department of Psychiatric Rehabilitation & Counseling Professions

Psychiatric Rehabilitation

PSRT6015 - General Linear Model

Course Description

The course is intended to provide students with the techniques of the general linear hypothesis. The courses will cover the types of problems they address including their basic assumptions and computer executions of these techniques. This is the second in the series of three courses: 1) Statistics; 2) General linear model; 3) Multivariate Statistics.

Credits/Modes of Instruction

Credits: 3

Lecture, classroom-based presentations and discussions, and computer activities.

Prerequisites

Admission to the doctoral program or permission of the instructor.

Course Goals and Outcomes:

Goals

1.Develop an understanding of the types of methodological problems that are addressed by the general linear model.
2.Comprehend the general linear hypothesis, its various applications, and its limitations.
3.Develop the prerequisites to understanding the application of multivariate techniques to research questions in psychiatric rehabilitation and related fields.
4.Use appropriate statistical computer package (e.g. SPSS) to manage data and execute analyses.
5.Understand linear effect size and its application to power analysis

Outcomes

By the end of this course, students will be able to:
1.Describe the assumptions of linear statistical techniques including simple regression, multiple regression, ANOVA, 2-way ANOVA, and analysis of covariance.
2.Apply appropriate techniques to a given research problem or question.
3.Design empirical projects with appropriate measurements for linear statistical techniques.
4.Develop actual data sets for these applications.
5.Execute appropriate computer routines and interpret output.
6.Interpret statistical findings based on design and technique.
7.Communicate verbally and in writing to explain findings to both “sophisticated” and naive audiences, that is other professionals not versed in statistics of general linear approaches.