Page 1 of 1

Hypothesis Testing

Posted: Sat Nov 06, 2010 1:33 am
by sh34
Hello,

Its been a while since ive done hypothesis testing (would definitely appreiate some advice) and my aim is to find the best fit equation to explain whats going on in the data.

I have a probit model that looks like:
binary dependent variable [DECISION] = c + quantitative variable(abbreviated as qv) [Temperature] + qv [Probability] + qv [Budget] + binary variable [Decision(-1)], and Decision(-1) is the binary outcome of the previous turn.

First question:
Do I intially test each variable's beta [individual hypothesis test] or test all the variables' betas at once [joint hypothesis test, F-test]?

Any guidance would be appreciated.