ILLINOIS STATE UNIVERSITY

|HOME|WebCT|

EAF 512:  RESEARCH METHODOLOGY AND STATISTICS IN EDUCATION IV

FALL 2005

Instructor: Dr. John K. Rugutt

Place of work: 323 DeGarmo

Phone: (309) 438-2051

Office Hours: By appointment (Email preferable).

Class Meets: Thursday 5:30-8:20 pm, Room: DEG 331F

Email: jkrugut@ilstu.edu

 |Course Schedule |Course Description |Class Format | Text and Software |Prerequisites |Required Student Tasks |

 |Student Performance Evaluation Methods |Outline of Topics |Course Delivery System |

                                                Topical/Content Outline...Subject to Change!!

The instructor reserves the right to make changes to the course syllabus as necessary. 

It is the student's responsibility to keep up with changes to the syllabus

                                                         Course Schedule

Note:   * Based on student’s article posted for discussion and/or notes from the instructor

            ** The instructor will provide the SPSS syntax to be used in data analysis

|Top | Home|

1   Analyzing Multivariate Data

1.1 Course Description

This is a Ph.D/Ed.D graduate-level introduction to multivariate data analysis. My goal will be to teach you how to use the most common techniques, how to make them work for you, how to read and understand papers that use them.  This is a hands-on, down-to-earth approach.  We will not cover proofs and time spent on matrix algebra will be minimal. The course will emphasize the application of multivariate statistical techniques.  Topics reviewed include factorial ANOVA, repeated measures ANOVA, analysis of covariance (ANCOVA), multivariate analysis of variance (MANOVA), multivariate analysis of covariance (MANCOVA), multiple regression, discriminant function analysis (DFA), logistic regression, canonical correlation, principal components, and factor analysis.  Before getting to the multivariate material however, we need to finish the spillover from EAF511.

1.2 Class Format

The format of the course will be a combination of lectures, seminar, and computer time. Each topic that we cover will have a combination of lecturing by me, to give you the necessary background for the topic, lab exercises so that we can learn how to interpret output, and a discussion period where we all read papers that apply the topic and then talk about its practical application. Each graduate student will lead one discussion section on one of our core topics. The scope that I've outlined is ambitious. And there is a lot that I think is important that we won't even get to! But we can speed up or slow down as we need to. The nice thing about having the syllabus all electronic is that it can change instantly! 

1.3 Texts and Software

Required texts are:

(M)  Mertler. C. A. & Vannatta, R. A. (2005). Advanced and Multivariate Statistical Methods:

 Practical Application and Interpretation (3^rd ed). Pyrczak Publishing, CA: Glendale.

(S) Green, S. B., & Salkind, N. J. (2004):  Using SPSS for Windows and Macintosh:

Analyzing and Understanding Data (4th).   Pearson Education, Inc.

ISBN: 0-13-146597

Recommended texts:

Dictionary of Statistics and Methodology, 3rd edn. (Sage Publications, 2005) by Paul W. Vogt

Applied Multivariate Statistics for the Social Sciences by James P. Stevens

Using Multivariate Statistics by Barbara G. Tabachnik and Linda S. Fidell
Applied Multivariate Statistical Analysis by Richard A. Johnson and Dean W. Wichern

Multivariate Data Analysis with Readings by Joseph F. Hair, Rolph E. Anderson, Ronald L.

            Tatham & William C. Black

Primary software: SPSS (Statistical Package for the Social Sciences). We will use the Windows version as much as possible. The examples I will offer in class and the lab computer exercises will be computed in SPSS.

|Top | Home |

1.4 Prerequisites

A strong background in data analysis and use of SPSS for data analysis is essential. Successful experience analyzing data is required.  A willingness to tackle new problems and use of computer statistical programs is also needed.

1.5 Required Student Tasks

Course Requirements and Required Student Tasks:

1.                Participate in all class activities, complete all assigned readings, and be   prepared to discuss them in class;

2.               Complete the assignments by the due dates;

3.               Complete a final paper and deliver presentation of the paper in class).

1.       Class Participation/Attendance.  Attendance and active participation in class is very important and will be part of your grade.  Note that work on data analysis using computers will be primarily an in-class activity, so attendance on days we will work in the computer lab is particularly crucial.  Class participation and attendance will also involve reading a research article, summarizing and leading class discussion.  Being sick will not count as an absence.  You will receive a maximum of 20 points for class participation and attendance.

2.      Assignments.  Each student will complete a series of five assignments that together describe a process for using data and appropriate research methods to address a major problem derived from the data provided by the instructor.  More details will be provided later and also posted on the assignment link within the WebCT courseware. 

|Top |Home |

1.6 Student Performance Evaluation Methods

The following point allocation will be used to determine final grades for the class:

            1.         Class participation/attendance                                    20 points

            2.         Assignments 1-4                                              20 points

            3.         Midterm                                                           10 points        

            3.         Final Project                                                    20 points

            4.         Presentation of Final Project                           10 points

            5.         Final Exam                                                      20 points

Assignments.  Assignments 1-4 are worth 5 points a piece for a maximum of 20 points.  Handing in a well thought out and well written assignment on the due date is worth 5 points.  Assignments turned in late will receive half-credit of 2.5 points if well done.  A high-quality final paper submitted on time will receive 20 points.  Final papers turned in one day late will receive a maximum of 15 points and final papers turned in more than one day late will receive half-credit, or a maximum of 10 points.  A well-done final presentation of your results will receive 10 points.  Students who do not present their results in class will not receive credit for the presentation. 

 Preparation for discussion on selected topic will involve completing the following steps.

1. Use Milner Library electronic databases to find one paper that applies (topic assigned for each week, for instance multiple regression). Find something related to your field of interest.
2. Post the reference and the web address on the WebCT discussion forum.
3. Let each one of you try to find different papers to read.
4. On the discussion day for (for instance, during the week multiple regression is due for discussion in class), come prepared to present a synopsis of the paper. If you don't fully understand what the author did, then that would be a good time to ask.
5. If you are the discussion leader for this topic (e.g., multiple regression), then be prepared to give an overview on the topic and to lead the discussion. In that case, you should fully understand how the technique was used before the class discussion.

Letter grades will be assigned in accordance with the following scheme:

             Points                 Letter Grade
            90-100                         A (Exceptional Performance)

            80-89                           B (Above Average Performance)
            70-79                           C (Average Performance)
            60-69                           D (Below Average Performance)
            0-59                             F (Failing)

|Top | Home|

1.7 Outline of Topics

1. Complete remaining topics from EAF 511
2. Factorial analysis of variance (ANOVA)
3. Repeated Measures ANOVA
4. Multivariate analysis of variance (MANOVA)
5. Multivariate analysis of covariance (MANCOVA)
6. A brief introduction to matrix  algebra
7. Multiple regression
8. Canonical correlation
9. Factor Analysis
10. Discriminant analysis
11. Logistic regression

1.8 Delivery System

This course will be presented using a variety of delivery systems:  The class will combine lecture, seminar/discussion (in-class and through online), statistical computing and student presentation.

|Top | Home |