Learn SPSS GLM Inside Out so you can run Linear Regressions and ANOVAs and Read Results Accurately, Efficiently, and With Confidence

Do you work in SPSS and get overwhelmed with all the options in GLM? Do you wonder which ones are applicable to your analysis? Do you ever worry that you're doing it wrong--leaving out something important?

SPSS GLM is extremely flexible in the types of models it can run. This is a good thing--you want the flexibility to choose the right options for your model. But the downside is that there are so many options, it's hard to know which apply to your analysis.

And even worse, there is so much output, and much of it is irrelevant to any given analysis. But you're still left feeling that you should be paying attention to some of these numbers, even though you don't know what they mean. And the manuals aren't very helpful.

Even for experienced SPSS users, the GLM is particularly confusing. But it's also very powerful.

Having a solid understanding of the univariate GLM will give you the skills, background knowledge, and confidence to run many statistical models effectively, efficiently, and correctly. Many other procedures in SPSS, such as Mixed Models and Generalized Linear Models, are based on the GLM.

In this workshop, we will go through the Univariate GLM in the context of two common general linear models--a multiple regression with a categorical predictor and an interaction and an analysis of variance with and without a continuous covariate.

We will work through first one, then the other example, and as we go, we will discuss the relevancy, meaning, and how to use each of the buttons and options in SPSS GLM.

We'll talk about how each of these relate to the syntax, and when that's easier to use.

We will then go over the output and see how making different analysis decisions affected the output.

You will complete the workshop with a much better understanding of how SPSS handles the GLM, what the defaults are and when to change them, and which options are appropriate for which analyses.

And although the focus of this workshop is on the software, you will also improve your understanding of the General Linear Model, and how regression and ANOVA fit into that overall framework.

Module 1: Univariate GLM overview:

The 5 boxes: Dependent Variable, Fixed Factors, Random Factors, Covariates, and WLS Weight

What you put into each one, when, and the defaults and language in SPSS.

The Options Button: Which of the 10 Display options are relevant to most GLM analyses. The definition, meaning and situations to use each.

The Model Button:

• The defaults in SPSS for interaction terms, how and when to override them, and how the order in which you build terms affects the meaning of the output.
• Type I and Type III Sums of Squares--what they are, what they mean, and when to use each one.

The Save Button: Saving Predicted Values, Residuals, and Diagnostics to test assumptions

Syntax: Using Syntax is usually more efficent than the menus, has more options, and gives you an audit trail of what you've done. We will talk about how to use the Paste button to create syntax, then how to modify it, and the basic logical structure of the Univariate GLM syntax.

Module 2 : Linear Regression Demonstration

In Session 2, I'll demonstrate a Multiple Regression Analysis with a dummy-coded categorical predictor first without, then with an interaction. You'll see how the choices you need to make and the output changes by including the dummy variable and the interaction.

We will go through the 5 boxes, the Options, Model, and Save in the specific context of a Linear Regression model.

We'll specifically run this example in both Regression and GLM to see the differences in options, default, and possible output. We'll also:

Comparison to Regression: The differences between SPSS GLM and SPSS Regression

Module 3: Analysis of Variance and Analysis of Covariance Demonstration.

We'll run an ANOVA with two categorical factors and a continuous covariate. You'll see how adding the covariate requires different options and output to interpret, and the similarities and differences between this analysis and the multiple regression.

This module will specifically cover sections of the SPSS GLM that are only relevant for ANOVAs:

Estimated Marginal Means--what they are, what they mean, and when you need them

The Plots Button: Profile Plots--how to do them, why to do them, and what they mean

The Post-Hoc Button:

• How and when to perform a post-hoc test
• How to read the results and what they mean
• Which Post-hoc tests you should never use, and when to use Tukey, Bonferroni, and Dunnett

The Contrasts Button: Definitions for each of the Contrasts, changing the reference group, and seeing how to do and interpret a Simple Contrast.

• Have worked with SPSS before. You should have a basic understanding of how variables and cases are set up in SPSS, and how to conduct basic analyses.
• Have used SPSS GLM and are confused by all the options. You wish you really understood what they mean, whether or not you should use them, and why.
• Run all your regression models in the Regression procedure, but spend hours creating dummy variables or interaction terms. You've heard that GLM can do this for you, but you don't understand the difference.
• Are working on, or will soon begin analyses for a research project that involves regression or ANOVA. Learn how to do it before you even start, and save hours, or even days of time.
• Are an experienced SPSS user, but would love to go back and really brush up on what all this means.
• Are pretty comfortable with SPSS menus, but haven't used Syntax much, and would love to learn how the menus correspond to the Syntax.
  

Prerequisites:

• You will get the most out of the workshop if you have had at least two statistics classes, some experience in data analysis using SPSS. This is not for total SPSS or statistics beginners.

• 3 Modules of training videos.
  
  
• 3 60-minute Webinar Q&A sessions. Just your questions and my answers. These are about a week after the training materials are released so you have time to watch the videos, do the exercises, and even try things out on your own data. Then come back with questions. It's when you use these techniques on your own data that you cement your learning.

There will be two Q&A series at two different days and times. You'll stick with the same series through the workshop, but you should be able to find one at a time that works for your schedule and time zone. Each Q&A session is limited to 25 participants to ensure we have time for all questions.

• PDF handouts of the presentations on which you can take notes.
  
  
• Data files and SPSS code to run, explore, and practice all of the workshop examples yourself.
  
  
• Access to our private workshop web site. Submit questions, get call-in information for Q&A sessions, ask for customer support, and download handouts, recordings, and bonus materials.
  
  
• You are encouraged to ask questions about implementing these techniques in your own analyses in addition to general questions about the topic.  (But please keep questions to the topic of the workshop so that they’re useful for everyone). 
  
  
• Exercises and answers.  (Yes, homework!).  You’ll get more out of the workshop if you participate fully by doing homework.  We suggest you use one of the data sets provided, so you can check answers, then redo them on your own. It's when you do statistics on your own data that it really starts to make sense.

Have a question about whether you're doing it right on your own data? Bring it to the Q&A session.

 

Each module will be released on:

• Tuesday, September 28
• Tuesday, October 5
• Tuesday, October 12

Sign up for one of the Question & Answer series:

Tuesdays @ 12pm (noon) EST (GMT-5) with Karen Grace-Martin  
10/5/10
10/12/10
10/19/10

OR

Mondays @ 8PM EST (GMT-5) with Lucy Fike
10/4/10
10/11/10
10/18/10

 

Your registration fee is fully refundable up to 72 hours in advance minus a $25 administration fee. Because enrollment is limited, no refunds will be granted after the program begins.

That said, your satisfaction is guaranteed. If you participate in the full workshop and find you are not satisfied for any reason, we will give you a full refund. Just notify us within 90 days of the conclusion of the program.