The University of Texas at Austin
School
of Social Work

Data Analysis and Computers II

Course Number: SW 388R7

Faculty: Jim Schwab

Unique Number: 63175

Office Number: SSW 2.228

Semester: Spring 2006

Office Phone: 471-9816

Time: Wednesday: 8:30am to 11:30am

Email: jimSchwab@mail.utexas.edu

Place: SSW 1.214
Instructional Technology Classroom

Office Hours: Wednesdays, 7:30 to 8:30am,
or by appointment

Course Description:

This course is designed to build upon the concepts and procedures introduced in Data Analysis and Computers I, to enable students to do a more thorough job of data analysis by introducing multivariate statistical procedures into their repertoire of statistical techniques. The primary focus is on using the SPSS statistical package for calculating multivariate statistics and the utilization of the statistical output in research findings.


Course Objectives:

1. To understand how the analysis of data derives from the statement of a research problem or hypothesis and the availability of empirical data.
2. To understand how to conduct a variety of statistical analyses, including testing of statistical assumptions, data transformations, and validation of statistical findings.
3. To understand how to present and interpret the results of statistical analyses.
4. To be able to design a data analysis strategy that answers a research question or hypothesis, including specifications for data elements, requirements of the statistic, and limitations to the interpretation.

Teaching Methods:

Course content will be covered using class lecture, focused discussions, computer demonstrations, and regular homework assignments involving data analysis exercises and computer applications. Students are expected to ask questions, share experiences, and actively participate in class discussions. While most statistical calculation will be done on the computer, some hand calculation is inherent in statistical analysis. Pocket calculators or Microsoft Excel can be used for to compute these calculations.

Course Website:

Course materials, announcements, assignments, and grading of homework problems will be done in BlackBoard. Through BlackBoard, the syllabus and any updates are available for downloading; datasets for problems are available for downloading; homework assignments and exams will be made available and completed online; your grades on exams and homework will be available online to you; a public bulletin board and access to email is supported for reporting problems on assignments, requesting assistance, and checking for announcements.

While the University has invested additional resources in support of BlackBoard, there are still periodic outages and slow-downs. If you wait until the last minute to complete assignments, you may encounter difficulties.


Required Texts and Materials:

The required text for the course is:

Hair, Joseph F., Jr; Black, William C.; Babin, Barry J.; Anderson, Rolph E.; and Tatham, Ronald L. Multivariate Data Analysis, Sixth Edition. Upper Saddle River, New Jersey: Prentice Hall. ISBN 0-13-032929-0.

In addition, you will need access to version 13.0 of SPSS on a PC computer and access to the Internet using either Internet Explorer, Firefox, or the Netscape browser. If you do not have a personal computer, the necessary hardware and software are available in the LRC computer lab in the School of Social Work.

All data sets used in this course will be available as SPSS system data files (".SAV") for downloading via the course web page.

Class Policies:

The University of Texas at Austin is proud of its students' commitment to academic integrity and their pledge to abide by it's policy on scholastic dishonesty. The tradition of scholastic honesty is maintained by the cooperation of students and faculty members. Official University policies on scholastic dishonesty are stated in Appendix C, Chapter 11 of The Institutional Rules on Student Services and Activities. These policies may be found in General Information, 2003-2004 and may also be accessed from the Student Judicial Services web site.

If a student has any questions concerning the application of the rules prohibiting scholastic dishonesty in regard to a particular assignment, it is the responsibility of that student to seek clarification from the instructor of the course. Violations of the University's policy on scholastic dishonesty will result in a grade of F for the course and may result in reporting to the Dean of the School of Social Work and the Dean of the Graduate School.

As part of professional social work education, students may have assignments that involve working in agency settings and/or the community. As such, these assignments may present some risks. Sound choices and caution may lower risks inherent to the profession. It is the student's responsibility to be aware of and adhere to policies and practices related to agency and/or community safety. Students should also notify instructors regarding any safety concerns.

All students should become familiar with the University's official e-mail student notification policy. It is the student's responsibility to keep the University informed as to changes in his or her e-mail address. Students are expected to check e-mail on a frequent and regular basis in order to stay current with University-related communications, recognizing that certain communications may be time-critical. It is recommended that e-mail be checked daily, but at a minimum, twice per week. The complete text of this policy and instructions for updating your e-mail address are available at http://www.utexas.edu/its/policies/emailnotify.html.

In this course e-mail will be used as a means of communication with students. You will be responsible for checking your e-mail regularly for class work and announcements. Note: if you are an employee of the University, your e-mail address in Blackboard is your employee address.

Students with disabilities who require special accommodations need to get a letter that documents the disability from the Services for Students with Disabilities area of the Office of the Dean of Students (471-6259 voice or 471-4641 TTY for users who are deaf or hard of hearing). This letter should be presented to the instructor in each course at the beginning of the semester and accommodations needed should be discussed at that time. Five business days before an exam the student should remind the instructor of any testing accommodations that will be needed. See following web site for more information: http://deanofstudents.utexas.edu/ssd/providing.php or contact the Office of the Dean of Students at 471-6259, 471-4641 TTY.

Religious holy days sometimes conflict with class and examination schedules. If you miss an examination, work assignment, or other project due to the observance of a religious holy day you will be given an opportunity to complete the work missed within a reasonable time after the absence. It is the policy of The University of Texas at Austin that you must notify each of your instructors at least fourteen days prior to the classes scheduled on dates you will be absent to observe a religious holy day.

Course Assignments:

Midterm and final exams will be given to assess your mastery of key concepts and procedures involved in the course The midterm and final examination will be in the format of questions anticipated to be on future departmental qualifying exams. In addition to outlining the analysis to solve a research problem, the qualifying exam includes interactive data analysis. Note, however, that there is no warranty, expressed or implied, between completion of this course and success on the qualifying exams. This course will help you prepare for the qualifying exam, but it is expected that your preparation for that exam will go beyond the limits of this course.

If any student requires an accommodation for taking tests, they must notify the instructor prior to the first exam.

Homework assignments requiring students to use SPSS to analyze data will be made available on the course web site after every class. Homework problems will be objective style questions on the datasets provided for the course. Each homework assignment draws from a large test bank from which a subset of problems are randomly selected. The homework assignment may be redone as many times as you wish. You will be given a different selection of questions each time you redo the assignment. You will find two identical versions of each homework assignment. Your grade for the assignment will be the higher grade on either version of the assignment. Since BlackBoard will record your grade for the last attempt, you can use the other version to retake the assignment to improve your grade.

Practice problems that go through each analysis step by step are also available, but the results do not count toward your grade for homework assignments. It is suggested that you begin your work with the practice problems first until you have mastered all of the steps required to complete a statistical analysis. The homework problems assume mastery of the practice problems.

Grading Policies:

Your grade will be based upon your performance on mid-term, final exam and regular homework assignments involving computer applications. The weighting for the final course grade will be as follows:

Homework

50%

Midterm Exam

25%

Final Exam

25%

 

Final grades will be assigned using the scale below:

100 - 94 = A
93 - 90 = A-
89 - 87 = B+
86 - 84 = B
83 - 80 = B-
79 - 77 = C+
76 - 74 = C
73 - 70 = C-
69 - 67 = D+
66 - 64 = D
63 - 60 = D-
59 and below = F

Assistance Outside of Class:

Blackboard supports an email system and I can post announcements for all class members to see. If you identify errors or ambiguities in my materials, please inform me and I will post the clarification announcement. You may want to consult announcements before raising an issue to see if it has already been asked and answered.

In addition to posting requests on the bulletin board, you may request help via personal email, which I check several times during a typical workday and generally once a day on weekends. Usually you may anticipate a response within 24 hour. My email address is listed at the top of this syllabus. If I think your question is of general interest to the class, I may post it as an announcement unless you explicitly request that I do not post it. If you need to meet with me individually, the best method for setting an appointment is via email.


Course Schedule:

The following schedule is the weekly sequence of activities for the semester. The instructor reserves the right to make adjustments to the course schedule if deemed necessary. Any changes will be made prior to the date of the class. Readings preceded by an asterisk are on electronic reserves. The password is the unique number for this course.

Class/Date

Readings and Tutorial Problems

Solving Problems in SPSS

Practice Problems

Homework Problems

Class 1
January 18

Chapter 1, “Introduction” in Multivariate Data Analysis, pages 1-34.

Chapter 2, “Examining Your Data”  in Multivariate Data Analysis., pages 35 – 73.

Analyzing Missing Data

Level of Measurement

Evaluating Missing Data

Level of Measurement

Missing Data Analysis

Class 2
January 25

Chapter 2, “Examining Your Data”  in Multivariate Data Analysis., pages 73 – 100.

Detecting outliers

Evaluation the assumption of normality

Evaluating the assumption of homoscedasticity

Evaluating the assumption of  linearity

 

Evaluating outliers

Assumption of normality

Assumption of homoscedasticity

Assumption of linearity

Outliers

 

Multivariate Assumptions

Class 3
February 1

Chapter 3, “Factor Analysis”  in Multivariate Data Analysis, pages 101-166.

Principal Components Analysis

Principal Components Analysis – Basic Relationships

Principal Components Analysis – Basic Relationships

Class 4
February 8

Principal Component Analysis – Validity, Outliers, and Reliability

 

Principal Component Analysis – Validity and Reliability

Principal Component Analysis – Validity and Reliability


 

Class 5
February 15

Chapter 4, “Multiple Regression”  in Multivariate Data Analysis., pages 169-268.

Multiple Regression – Basic Relationships

Multiple Regression – Basic Relationships

Multiple Regression – Basic Relationships

Class 6
February 22

Multiple Regression - Validation

Multiple Regression – Complete Analyses

Multiple Regression – Complete Analyses

Class 7
March 1

Multiple Regression – Hierarchical Models

Multiple Regression – Sequential Models

Multiple Regression – Sequential Models

Class 8
March 8

Multiple Regression – Stepwise Analysis

Multiple Regression – Statistical Models

Multiple Regression – Statistical Models

Class 9
March 22

Regression Exam

Class 10
March 29

Chapter 5, Multiple Discriminant Analysis and Logistic Regression in Multivariate Data Analysis, pages 269 – 355.

Discriminant Analysis – Basic Relationships

Discriminant Analysis – Basic Relationships

Discriminant Analysis – Basic Relationships

Class 11
April 5

Discriminant Analysis – Complete Analysis

Discriminant Analysis – Complete Analysis

Discriminant Analysis – Complete Analysis

Class 12
April 12

Chapter 5, Multiple Discriminant Analysis and Logistic Regression  in Multivariate Data Analysis, pages 355 - 382.

*Nancy Morrow-Howell and Enola K. Proctor, "The Use of Logistic Regression in Social Work Research." In David F. Gillespie and Charles Glisson, Eds., Quantitative Methods in Social Work: State of the Art. New York: The Haworth Press, Inc., 1992. Pages 87-104.

*Barbara G. Tabachnick and Linda Fidell, Using Multivariate Statistics, Fourth Edition. Chapter 12, Logistic Regression.

*SPSS Regression Models 10.0, Chapter 8, Logistic Regression Analysis Examples. 

 

Logistic Regression and Odds Ratios

Binary Logistic Regression – Basic Relationships

 

Binary Logistic Regression – Basic Relationships

Binary Logistic Regression – Basic Relationships

Class 13
April 19

 

Binary Logistic Regression – Complete Analysis

Binary Logistic Regression – Complete Analysis

Binary Logistic Regression – Complete Analysis

Class 14
April 26

 

Binary Logistic Regression – Sequential and Statistical Models

Binary Logistic Regression – Sequential and Statistical Models

Binary Logistic Regression – Sequential and Statistical Models

Class 15
May 3

*SPSS Regression Models 10.0, Chapter 9, Multinomial Logistic Regression Examples 

Multinomial Logistic Regression

Multinomial Logistic Regression – Basic Relationships

Multinomial Logistic Regression – Basic Relationships

May 16, 2 to 5 pm

Final Exam