CHAPTER 13 Taking a Closer Look at Fourfold Tables 173

Chapter 13

Taking a Closer Look

at Fourfold Tables

I

n Chapter 12, we show you how to compare proportions between two or more

groups with a cross-tab table. In general, a cross-tab shows the relationship

between two categorical variables. Each row of the table represents one partic-

ular category of one of the variables, and each column of the table represents one

particular category of the other variable. The table can have two or more rows and

two or more columns, depending on the number of different categories or levels

present in each of the two variables. (To refresh your memory about categorical

variables, read Chapter 8.)

Imagine that you are comparing the performance of three treatments (Drug A,

Drug B, and Drug C) in patients who could have four possible outcomes: improved,

stayed the same, got worse, or left the study due to side effects. In such a case,

your treatment variable would have three levels so your cross-tab would have

three rows, and your outcome variable would have four levels so your cross-tab

would have four columns.

But this chapter only focuses on the special case that occurs when both categorical

variables in the table have only two levels. Other words for two-level variables are

dichotomous and binary. A few examples of dichotomous variables are hyperten-

sion status (hypertension or no hypertension), obesity status (obese or not obese),

and pregnancy status (pregnant or not pregnant). The cross-tab of two

IN THIS CHAPTER»

» ^{Beginning with the basics of fourfold}

tables»

» ^{Digging into sampling strategies for}

fourfold tables»

» ^{Using fourfold tables in different}

scenarios