OptinMon 30 - Four Critical Steps in Building Linear Regression Models

Why report estimated marginal means?

August 18th, 2021 by

Updated 8/18/2021

I recently was asked whether to report means from descriptive statistics or from the Estimated Marginal Means with SPSS GLM.Stage 2

The short answer: Report the Estimated Marginal Means (almost always).

To understand why and the rare case it doesn’t matter, let’s dig in a bit with a longer answer.

First, a marginal mean is the mean response for each category of a factor, adjusted for any other variables in the model (more on this later).

Just about any time you include a factor in a linear model, you’ll want to report the mean for each group. The F test of the model in the ANOVA table will give you a p-value for the null hypothesis that those means are equal. And that’s important.

But you need to see the means and their standard errors to interpret the results. The difference in those means is what measures the effect of the factor. While that difference can also appear in the regression coefficients, looking at the means themselves give you a context and makes interpretation more straightforward. This is especially true if you have interactions in the model.

Some basic info about marginal means

  • In SPSS menus, they are in the Options button and in SPSS’s syntax they’re EMMEANS.
  • These are called LSMeans in SAS, margins in Stata, and emmeans in R’s emmeans package.
  • Although I’m talking about them in the context of linear models, all the software has them in other types of models, including linear mixed models, generalized linear models, and generalized linear mixed models.
  • They are also called predicted means, and model-based means. There are probably a few other names for them, because that’s what happens in statistics.

When marginal means are the same as observed means

Let’s consider a few different models. In all of these, our factor of interest, X, is a categorical predictor for which we’re calculating Estimated Marginal Means. We’ll call it the Independent Variable (IV).

Model 1: No other predictors

If you have just a single factor in the model (a one-way anova), marginal means and observed means will be the same.

Observed means are what you would get if you simply calculated the mean of Y for each group of X.

Model 2: Other categorical predictors, and all are balanced

Likewise, if you have other factors in the model, if all those factors are balanced, the estimated marginal means will be the same as the observed means you got from descriptive statistics.

Model 3: Other categorical predictors, unbalanced

Now things change. The marginal mean for our IV is different from the observed mean. It’s the mean for each group of the IV, averaged across the groups for the other factor.

When you’re observing the category an individual is in, you will pretty much never get balanced data. Even when you’re doing random assignment, balanced groups can be hard to achieve.

In this situation, the observed means will be different than the marginal means. So report the marginal means. They better reflect the main effect of your IV—the effect of that IV, averaged across the groups of the other factor.

Model 4: A continuous covariate

When you have a covariate in the model the estimated marginal means will be adjusted for the covariate. Again, they’ll differ from observed means.

It works a little bit differently than it does with a factor. For a covariate, the estimated marginal mean is the mean of Y for each group of the IV at one specific value of the covariate.

By default in most software, this one specific value is the mean of the covariate. Therefore, you interpret the estimated marginal means of your IV as the mean of each group at the mean of the covariate.

This, of course, is the reason for including the covariate in the model–you want to see if your factor still has an effect, beyond the effect of the covariate.  You are interested in the adjusted effects in both the overall F-test and in the means.

If you just use observed means and there was any association between the covariate and your IV, some of that mean difference would be driven by the covariate.

For example, say your IV is the type of math curriculum taught to first graders. There are two types. And say your covariate is child’s age, which is related to the outcome: math score.

It turns out that curriculum A has slightly older kids and a higher mean math score than curriculum B. Observed means for each curriculum will not account for the fact that the kids who received that curriculum were a little older. Marginal means will give you the mean math score for each group at the same age. In essence, it sets Age at a constant value before calculating the mean for each curriculum. This gives you a fairer comparison between the two curricula.

But there is another advantage here. Although the default value of the covariate is its mean, you can change this default.  This is especially helpful for interpreting interactions, where you can see the means for each group of the IV at both high and low values of the covariate.

In SPSS, you can change this default using syntax, but not through the menus.

For example, in this syntax, the EMMEANS statement reports the marginal means of Y at each level of the categorical variable X at the mean of the Covariate V.

UNIANOVA Y BY X WITH V
/INTERCEPT=INCLUDE
/EMMEANS=TABLES(X) WITH(V=MEAN)
/DESIGN=X V.

If instead,  you wanted to evaluate the effect of X at a specific value of V, say 50, you can just change the EMMEANS statement to:

/EMMEANS=TABLES(X) WITH(V=50)

Another good reason to use syntax.


Overfitting in Regression Models

August 9th, 2021 by

The practice of choosing predictors for a regression model, called model building, is an area of real craft.Stage 2

There are many possible strategies and approaches and they all work well in some situations. Every one of them requires making a lot of decisions along the way. As you make decisions, one danger to look out for is overfitting—creating a model that is too complex for the the data. (more…)


What are Sums of Squares?

January 9th, 2021 by

A key part of the output in any linear model is the ANOVA table. It has many names in different software procedures, but every regression or ANOVAStage 2 model has a table with Sums of Squares, degrees of freedom, mean squares, and F tests. Many of us were trained to skip over this table, but

(more…)


When Unequal Sample Sizes Are and Are NOT a Problem in ANOVA

December 18th, 2020 by

Stage 2

In your statistics class, your professor made a big deal about unequal sample sizes in one-way Analysis of Variance (ANOVA) for two reasons.

1. Because she was making you calculate everything by hand.  Sums of squares require a different formula* if sample sizes are unequal, but statistical software will automatically use the right formula. So we’re not too concerned. We’re definitely using software.

2. Nice properties in ANOVA such as the Grand Mean being the intercept in an effect-coded regression model don’t hold when data are unbalanced.  Instead of the grand mean, you need to use a weighted mean.  That’s not a big deal if you’re aware of it. (more…)


What It Really Means to Remove an Interaction From a Model

September 17th, 2020 by

When you’re model building, a key decision is which interaction terms to include. And which interactions to remove.Stage 2

As a general rule, the default in regression is to leave them out. Add interactions only with a solid reason. It would seem like data fishing to simply add in all possible interactions.

And yet, that’s a common practice in most ANOVA models: put in all possible interactions and only take them out if there’s a solid reason. Even many software procedures default to creating interactions among categorical predictors.

(more…)


Simplifying a Categorical Predictor in Regression Models

January 14th, 2020 by

One of the many decisions you have to make when model building is which form each predictor variable should take. One specific version of thisStage 2 decision is whether to combine categories of a categorical predictor.

The greater the number of parameter estimates in a model the greater the number of observations that are needed to keep power constant. The parameter estimates in a linear (more…)