I am looking at logistic regression output that shows Z test values. When can I use these to estimate the significance of coefficients, and when do I need to use a Wald chi-squared test?
Asked
Active
Viewed 3,783 times
1 Answers
7
They are almost certainly the same thing. The "Z test values" in your logistic regression output are probably Wald statistics, and the Wald chi-square statistic is probably just $Z^2$. This means that the Wald chi-squared test is the same as a two-sided test using the corresponding $Z$-value.
Gordon Smyth
- 12,807
-
1So just to be clear - if I need the Wald's Chi-Square value, all I need to do is take a square of the Z statistic from the output? – Indrajit Feb 05 '18 at 08:15