The Analysis Factor
Statistical Consulting, Resources, and Statistics Workshops for Researchers
Our analysis of linear regression focuses on parameter estimates, z-scores, p-values and confidence levels. Rarely in regression do we see a discussion of the estimates and F statistics given in the ANOVA table above the coefficients and p-values.
And yet, they tell you a lot about your model and your data. Understanding the parts of the table and what they tell you is important for anyone running any regression or ANOVA model.
[Read more…] about Member Training: The Anatomy of an ANOVA Table
The way to follow up on a significant two-way interaction between two categorical variables is to check the simple effects. Most of the time the simple effects tests give a very clear picture about the interaction. Every so often, however, you have a significant interaction, but no significant simple effects. It is not a logical impossibility. They are testing two different, but related hypotheses.
Assume your two independent variables are A and B. Each has two values: 1 and 2. The interaction is testing if A1 – B1 = A2 – B2 (the null hypothesis). The simple effects are testing whether A1-B1=0 and A2-B2=0 (null) or not.
If you have a crossover interaction, you can have A1-B1 slightly positive and A2-B2 slightly negative. While neither is significantly different from 0, they are significantly different from each other.
And it is highly useful for answering many research questions to know if the differences in the means in one condition equal the differences in the means for the other. It might be true that it’s not testing a hypothesis you’re interested in, but in many studies, all the interesting effects are in the interactions.
A well-fitting regression model results in predicted values close to the observed data values. The mean model, which uses the mean for every predicted value, generally would be used if there were no informative predictor variables. The fit of a proposed regression model should therefore be better than the fit of the mean model.
Three statistics are used in Ordinary Least Squares (OLS) regression to evaluate model fit: R-squared, the overall F-test, and the Root Mean Square Error (RMSE). All three are based on two sums of squares: Sum of Squares Total (SST) and Sum of Squares Error (SSE). SST measures how far the data are from the mean, and SSE measures how far the data are from the model’s predicted values. Different combinations of these two values provide different information about how the regression model compares to the mean model.
R-squared and Adjusted R-squared
The difference between SST and SSE is the improvement in prediction from the regression model, compared to the mean model. Dividing that difference by SST gives R-squared. It is the proportional improvement in prediction from the regression model, compared to the mean model. It indicates the goodness of fit of the model.
R-squared has the useful property that its scale is intuitive: it ranges from zero to one, with zero indicating that the proposed model does not improve prediction over the mean model, and one indicating perfect prediction. Improvement in the regression model results in proportional increases in R-squared.
One pitfall of R-squared is that it can only increase as predictors are added to the regression model. This increase is artificial when predictors are not actually improving the model’s fit. To remedy this, a related statistic, Adjusted R-squared, incorporates the model’s degrees of freedom. Adjusted R-squared will decrease as predictors are added if the increase in model fit does not make up for the loss of degrees of freedom. Likewise, it will increase as predictors are added if the increase in model fit is worthwhile. Adjusted R-squared should always be used with models with more than one predictor variable. It is interpreted as the proportion of total variance that is explained by the model.
There are situations in which a high R-squared is not necessary or relevant. When the interest is in the relationship between variables, not in prediction, the R-square is less important. An example is a study on how religiosity affects health outcomes. A good result is a reliable relationship between religiosity and health. No one would expect that religion explains a high percentage of the variation in health, as health is affected by many other factors. Even if the model accounts for other variables known to affect health, such as income and age, an R-squared in the range of 0.10 to 0.15 is reasonable.
The F-test
The F-test evaluates the null hypothesis that all regression coefficients are equal to zero versus the alternative that at least one is not. An equivalent null hypothesis is that R-squared equals zero. A significant F-test indicates that the observed R-squared is reliable and is not a spurious result of oddities in the data set. Thus the F-test determines whether the proposed relationship between the response variable and the set of predictors is statistically reliable and can be useful when the research objective is either prediction or explanation.
RMSE
The RMSE is the square root of the variance of the residuals. It indicates the absolute fit of the model to the data–how close the observed data points are to the model’s predicted values. Whereas R-squared is a relative measure of fit, RMSE is an absolute measure of fit. As the square root of a variance, RMSE can be interpreted as the standard deviation of the unexplained variance, and has the useful property of being in the same units as the response variable. Lower values of RMSE indicate better fit. RMSE is a good measure of how accurately the model predicts the response, and it is the most important criterion for fit if the main purpose of the model is prediction.
The best measure of model fit depends on the researcher’s objectives, and more than one are often useful. The statistics discussed above are applicable to regression models that use OLS estimation. Many types of regression models, however, such as mixed models, generalized linear models, and event history models, use maximum likelihood estimation. These statistics are not available for such models.
I was recently asked about when to use one and two tailed tests.
The long answer is: Use one tailed tests when you have a specific hypothesis about the direction of your relationship. Some examples include you hypothesize that one group mean is larger than the other; you hypothesize that the correlation is positive; you hypothesize that the proportion is below .5.
The short answer is: Never use one tailed tests.
Why?
1. Only a few statistical tests even can have one tail: z tests and t tests. So you’re severely limited. F tests, Chi-square tests, etc. can’t accommodate one-tailed tests because their distributions are not symmetric. Most statistical methods, such as regression and ANOVA, are based on these tests, so you will rarely have the chance to implement them.
2. Probably because they are rare, reviewers balk at one-tailed tests. They tend to assume that you are trying to artificially boost the power of your test. Theoretically, however, there is nothing wrong with them when the hypothesis and the statistical test are right for them.