Solved – use a regression model with ANOVA significance greater than 0.05

I have a multiple regression using SPSS. The significance of my model in the ANOVA table is p=0.174 which is >0.05. what does this mean for my model? Can I still use it and proceed in the interpretation of the results or not?

You can set any significance level you like before you start looking at the data. The higher you choose to set it, the greater the rate of Type I errors you're prepared to accept (that is, the more frequently you say you'd be prepared to claim a real effect in the presence of nothing but noise)

If you choose a high significance level, even before the fact, people will expect that choice to be justified — not least because they'll immediately suspect you're simply 'cheating' – trying to engineer a significant result out of a non-significant one by manipulating your significance level after the fact. Some kind of a power study and an argument based on the costs of the two types of error would be the least you'd need to do in many areas.

You can't choose your significance level after you've seen the p-value. You might as well forget statistical testing altogether; it doesn't have the claimed properties once you do…

what does this mean for my model?

A high p-value means 'an effect at least a big as this could easily have been due to chance'. That is, there's no particularly good reason to assert it isn't just chance.

Can I still use it and proceed in the interpretation of the results or not?

that depends on what you mean by 'use it'. You can certainly interpret the results, but the interpretation has to be in the context that your estimates may be nothing more than noise.

Similar Posts:

Rate this post

Leave a Comment