O'Reilly logo

Statistics for Health Care Management and Administration by David A. Rosenthal, John F. Kros

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Chapter 14Analysis with a Dichotomous Categorical Dependent Variable

The chi-square statistic deals with categorical data in both the independent and the dependent variables. However, the general limitation is that only two variables—one independent and one dependent, or, occasionally, two independent and one dependent—can be analyzed at one time. Furthermore, the chi-square is limited by the need to retain relatively large values (at least five or more) in all the cells of the tables in the analysis. The t test and analysis of variance (ANOVA) deal with categorical data in the independent variable but require a numerical variable in the dependent variable. Again, though, t tests are limited to a single independent variable that can take on only two values, whereas ANOVA is usually limited to no more than one or two independent variables. Regression analysis, the topic of the three previous chapters, is more flexible than any of the other three analysis methods. Regression can deal simultaneously with a large number of independent variables, and these can be either numerical or categorical. In addition, regression has no particular cell size requirements. ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required