Logistic and Poisson Regression
We can write a linear regression equation like this, but we shouldn’t. First, probabilities don’t go in a straight line forever; they are bounded by zero and one. Second, there’s…
Looking at the Data
FIGURE 2-1 Bar chart of the five least popular courses FIGURE 2-2 Figure 2-1 redrawn so that the categories are in order of preference and the tick marks are outside…
Principal Components and Factor Analysis
In psychological jargon, we call these attributes hypothetical constructs; in statistics, they are called factors or latent variables. One purpose of FA is to determine if numerous measures (these could…
Path Analysis and Structural Equation Modeling
A diagram of what this equation does is shown in Figure 20–1. For reasons that will become clear soon, we’ve drawn a box around each of the variables and a…
Measures of Association for Ranked Data
Measures of Association for Ranked Data This chapter reviews several measures of association for use with ranked data. Spearman’s rho is perhaps the most frequently used and is derived from…
Tests of Significance for Ranked Data
Tests of Significance for Ranked Data Data that can be ranked (ordinal data) should be treated differently from categorical data. This chapter reviews several ranking tests—the Mann-Whitney test (or Wilcoxon…
Probability
The empirical way is also the basis for the old diagnostic dictum that if you hear hoof beats, it’s more likely to be coming from a horse than from a…
Repeated-Measures ANOVA
However, because of the nature of the syndrome, we are at liberty to do the study a little differently than the usual approach. Assuming that committees meet only every week…
Comparing Two Groups
OFVARIANCE CHAPTER THE SEVENTH Comparing Two Groups The t-Test The t-test is used for comparing the means of two groups and is based on the ratio of the difference between…
Analysis of Longitudinal Data: Hierarchical Linear Modeling
You may wonder why we need three data points, since we can fit a perfectly straight line with only two. There are three answers to this: one methodological, one statistical,…
