Default homogeneity test in stata epitab

[Valentino Santori]

Dear all,

I've checked the epitab manual and to perform Breslow-Day and Tarone's tests, a different option for each must be specified, in addition there is no reference to a particular homogeneity test; I wonder if the default homogeneity test performed by Stata epitab commands, is a standard chi-squared (using ir for instance).

[Rich Goldstein]

I'm not sure what you mean by "standard chi-squared" but exact formulae are given in the "Methods and formulas" section of the manual for the various tests - there are lots there as the section has many subsections:

Methods and formulas are presented under the following headings:
Unstratified incidence-rate data (ir and iri)
Unstratified cumulative incidence data (cs and csi)
Unstratified case–control data (cc and cci)
Unstratified matched case–control data (mcc and mcci)
Stratified incidence-rate data (ir with the by() option)
Stratified cumulative incidence data (cs with the by() option)
Stratified case–control data (cc with by() option, mhodds, tabodds)

[Valentino Santori]

Thanks, I've found the manual correct section.