PLEASE SEE UPDATES ON THE PAPER (AND ASSIGNMENT 3...)

ACCESS THE PAPER GUIDE FOR THE UPDATED DUE DATES. Thank you!
WATCH THESE SPACES FOR ANNOUNCEMENTS!

PRESENTATION SITE

 GUIDE 1: ISSUES IN MODELING
GUIDE 2: TERMINLOGY
GUIDE 3: THE LOWLY 2 X 2 TABLE
GUIDE 4: BASICS ON FITTING MODELS
GUIDE 5: SOME REVIEW, EXTENSIONS, LOGITS
GUIDE 6: LOGLINEAR & LOGIT MODELS
GUIDE 7: LOG-ODDS AND MEASURES OF FIT
GUIDE 8: LOGITS,LAMBDAS & OTHER GENERAL THOUGHTS		 READINGS

SUCH AS: 
PLEASE TURN ALL  CELL PHONES  OFF DURING  CLASS. THANKS!
(I will also try to remember)

 

EDF 6937-01       SPRING 2009
G158  Stone Building (new/remodeled classroom)
Thursdays  2:15-4:40 PM
THE MULTIVARIATE ANALYSIS OF CATEGORICAL DATA
Ref # 06161
Susan Carol Losh
Department of Educational Psychology and Learning Systems
Florida State University

 
Welcome to The Multivariate Analysis of Categorical Data! 

On this site are topics, readings, and dates for assignments for EDF 6937-01 Spring 2009. Watch this website over the semester for more information. Need more information NOW? Please contact me via email:

 
BOOKS
ASSIGNMENTS & GRADING
WE'RE ONLINE
READINGS & 
ASSIGNMENT DATES

 
BASIC COURSE INFORMATION
INSTRUCTOR: Professor Susan Carol Losh
307K Stone Building 
850-644-8778 Voice
850-644-8776 FAX

OFFICE HOURS: Exceptions to be announced
1:00-2:05 PM Tuesdays & Thursdays 
Generally Wednesday afternoons & by appointment

 CLICK HERE  to find the Stone Building
 
 
 

slosh@fsu.edu

 


Prerequisites (in addition to a basic statistics course, e.g., EDF 5400 or equivalent): a course in multiple regression OR the general linear model, OR analysis of variance or the equivalent (e.g., EDF 5401, EDF 5402, EDF 5406 etc)

MAIN TEXT: Alan Agresti, An Introduction to Categorical Data Analysis. SECOND EDITION! (Wiley, 2007; ISBN = 0471226185)

Because it differs considerably from the first edition, be sure to get the SECOND edition of Agresti.
 
 
NOTE: A more expanded version of Agresti, which is more mathematical, can be found at:

Alan Agresti, Categorical Data Analysis. SECOND edition, 2002. ISBN = 0471360937
 

Other readings from: Nigel Gilbert, Analyzing Tabular Data: Loglinear and Logistic Models (1993; ISBN = 1857280903; to be provided for you) and

Online Course Guides

The Agresti book can be found at Bill's and the FSU Bookstore. It is quite possible that you can find used copies online at Amazon and other sites for a good deal. I will make copies of the Gilbert chapters for you.

ALL MY COURSE LECTURES will be placed on the Internet and linked in with each course topic.

Course guides will be keyed to the readings. See the top of each Guide as it is posted.

The lecture urls have the general form of:

http://mailer.fsu.edu/~slosh/CatDataGuide1.html

Please type in course urls EXACTLY. There is no "www" in these urls.

Each Guide is linked to every other Guide so that it is easy to navigate from one to another.
Course Guides are also linked to course topics and will be placed on our class Blackboard site (please see below).

Although I may not cover all the material in each one during class time, you are responsible for ALL the material in each guide. That is why they are on the Internet.

I recommend that you read my online guides FIRST. They emphasize the portions of the material that I think are the most important for this course. I think it will be easier for you to understand the texts after you have read the associated guide.

Some of the material in the guides will be covered during class. However, class time will also be used for instruction related to each assignment, demonstrations, presentation, review, and assignment feedback.
 

COURSE ASSIGNMENTS

Here is information about  assignments, due dates, and course weights.

There will be four short equally weighted exercises.  While each exercise will focus on the immediately prior units, please be advised that this material is cumulative in nature.

Exercises have several purposes:

To familiarize you with terminology, basic operations, and associated computer programs.

To help practice your basic analysis and results interpretation skills. For example, logistic regression coefficients are often used and equally often misinterpreted.

To alert you to common problems that occur with different kinds of analyses and ways to solve these problems.

All four exercises put together will count a total of 40% toward your final grade.

Details on each assignment are posted to our course WEB site prior to the due date.

As exercises and exercise feedback sites are created and posted, watch the space at the top of the Guides for information and links.

An analytic paper will count 40% toward your final grade.

A presentation based on your analytic paper will count 20% toward your final grade.

In the paper, you will analyze data using course material and interpret your findings. The general format of the paper will resemble a journal article.

You may use your own data, data from your major professor, or one of the many data sets I have available.

I use plus and minus grading, throughout and for final grades.

If I think you are having trouble with the material, I will alert you immediately and I expect you will seek remedial help as quickly as possible. If you receive such an alert, please take it very seriously. Please do not tell me that you "really understand the material" and fail to seek help. I issue such alerts when the work makes it obvious the student DOES NOT understand the material.


 
 
EXERCISE
DUE DATE
COURSE WEIGHT
1: Terminology and purpose February 5 10 percent
2. Using a hierarchical loglinear program February 26 10 percent
3. Exercise on general loglinear models March 26   April 2 10 percent
4. Loglinear to logit transformations (includes program exercise) and logistic regression April 9 10 percent
PRESENTATION ON PAPER TOPIC & ANALYSIS April 9-23 20 percent
COURSE PAPER April 24 28 by NOON  5 PM 40 percent

 
IMPORTANT NOTE!    IMPORTANT!  EXERCISE DUE DATES

 
 
We are on a tight schedule so assignments must reach me BY THE DUE DATE. Because of the intensive nature of this course, late assignments are not accepted.

You can fax from the road or turn exercises in a day or two early. Because of our schedule, I try to return work as rapidly as possible. If you are late, I just might hand them back before you turn yours in.

PLEASE DO NOT BEGIN THE SEMESTER BY REQUESTING EXCEPTIONS TO THE EXERCISE DATES. It is impossible to change the times to accomodate everyone. You can fax exercises from virtually anywhere, including most Kinkos or Target Copy centers.
 

 
 

GETTING EXERCISES TO ME: see the SUBMITTING ASSIGNMENTS webpage here!

I ACCEPT HARD COPY EXERCISES ONLY.

PLEASE DO NOT SEND ME ANY EMAIL ATTACHMENTS. THEY WILL NOT BE OPENED!

ONE MORE NOTE ON EMAIL: Widespread viruses spread through email use subject lines such as "hi" "hello" "hi there" "thanks" or "my test" or no subject heading at all. If not a virus, some of these subject lines are used to camophage advertisements for products I neither use nor want (I received over 75 of these over Break!) PLEASE USE SOME OTHER SUBJECT LINE. I will delete without opening any emails that have subject lines such as "hi" or "my assignment." ("my edf6937 assignment" works fine)

INFORMATIVE SUBJECT LINES INCLUDE:

  • EDF6937 Exercise 1 question
  • Loglinear exercise question
  • Computer exercise question
  • Question about paper
 
 

WE’RE ONLINE!
Our course is WEB assisted through Blackboard FSU. You MUST be registered for edf6937-03 to access our statistics class Web site. To access our course most easily, here is what to do. Go online to:

http://campus.fsu.edu

(You will be forwarded to the new, more complicated url <http://campus.fsu.edu/webapps>. The above works and is easy to remember.) Enter your FSU username (USERNAME ONLY!) and password to log in. For example, I would enter "slosh" ONLY and omit the "@fsu.edu" part. Then click on:

MULTVAR ANAL CATEG D

to enter our site. Browse the diverse categories that are available.

Each Guide (lecture) will have links posted at the top to the Course Overview, Syllabus, and all prior course Guides. This makes getting around the course material easy. Watch the top of each Guide for announcements about assignments, generic feedback, and any schedule changes.

When sites are under construction, there will be a warning sign at the top. I recommend against copying sites until construction warnings are removed.
 

 

NOTES ON THE NET

I created our navigation system and guides, so that's why there's only one copy of each site. 

Thus, each url is CASE SENSITIVE so you must copy capital and small letters EXACTLY.

There is NO "www" in course WEB addresses so don't insert one. 

The number "0" is different from the letter "O". Don't confuse them!

Don't add any spaces to the web address. 

If you want, everything can be accessed through Blackboard so not to worry.
 

 
BASIC COURSE TOPICS, READINGS, AND IMPORTANT DATES

There may be some variations from this syllabus. Please check back weekly and watch Blackboard for any announcements.
DATES
TOPICS TO BE COVERED
READINGS & ASSIGNMENTS
January 8-15 Introduction: Issues in Modeling
Causal issues in experimental, nonexperimental and observational data and their implications for models
Some basic distributions		 Guide 1
Gilbert, preface and pp. 1-7
Agresti, pp. 1-6
Skim Agresti Chapter 11 for the history!
January 15-22 Bunches of basics:
terminology ; Odds-Ratios; MLEs; iteration; Chi-square as goodness of fit; poisson and multinomial distributions.
The basic two-way (2 X 2) cross-tabulation table recast		 Guide 2 (beginning glossary)
Gilbert, pp. 13-24; 27-33
Agresti, pp. 6-15; 21-41; 49-54
January 22-29 Review General Linear Model
Basic loglinear models. 
A probabilistic model for table cell counts.
 Begin with two way table, extend initially to three way (2 dichotomous, 1 not, then to multinomial).
Frequency equations; transformed to log-linear equations.		 Guide 3 (The 'Lowly' 2 X 2 Table)
Gilbert, pp. 39-49; 58-62
Agresti, pp. 65-75 (skim examples!)
84-90; 204-228
February 5 EXERCISE 1 Basic terminology exercise
February 5-12 N-way tables
Model construction and model testing in the loglinear model		 Guide 4
Gilbert, pp. 66-77; 101-110; 147-156
Agresti, pp. 137-152
February 12-19 Introduction to programs and analysis: 
Examples and demonstrations (output interpretation)		 Guide 5
February 26 EXERCISE 2 Program 1 and writing a loglinear equation
February 26-March 5 The logit model. 
Transformation from the loglinear to the logit model. 
Transform equations to logit model. 		 Guide 6
Gilbert, pp. 115-125
Agresti, pp.221-228
March 9-13 No class--Spring Break
March 19 Issues in testing logit models. 
Demonstrations		  
March 19 Paper precis What's your topic? What're your data? Information for the analytic paper
March 26
April 2		 EXERCISE 3 Nonhierarchical loglinear models
March 26-April 2 The special case of logistic regression. Dichotomous and polytotomous dependent variables. 
Poisson, binomial and multinomial regression.
More programs: Multinomial logistic regression 
Power		 Gilbert, pp. 131-142
Agresti, pp. 99-121
160-162
173-197
April 9 EXERCISE 4 Loglinear to logit transformation
Running a logit model program
April 9  16 First draft analytic paper
Presentations begin		  
April 9-23 Various extensions and special cases:
Model Fitting
Ordinal response variables versus nominal models; 
Sparse data;
Quasi independence; 
Structural versus sampling zeros

Odds and ends

 Guide 7
Agresti, pp. 41-45
Gilbert, pp. 167-175
Gilbert, pp. 82-95; 159-164
Agresti, pp. 152-160; 189-196; 228-232; 261-262
297-318

Guide 8
April 28 5 PM
April 24 NOON		 Analytic paper due Paper Guide

A LECTURE (AND ASSOCIATED MATERIALS) WILL BE LINKED WITH EACH TOPIC AS THE SEMESTER PROGRESSES.
 
 
 
OVERVIEW

This page was created with Netscape Composer.
There may be some minor changes as the semester progresses.
Your patience is appreciated.
Susan Carol Losh
January 5 2009
March 18 2009
Welcome back!