Essentially, I have a statistical standardization method that I am running on data to show that the data is more significantly similar to the linear model Y=X AFTER standardization.

I have a p value of .1 before standardization, and a p-value of .6 after standardization. Although the p-value before standardization is > .05 (and thus does not reject the null hypothesis of Y=X), since it is closer to .05 than .6, can I draw any statistical conclusions from this?


You can directly answer this question by performing hypothesis testing comparing your two models (standardized and non-standardized). Your current p-values tell you that neither model is significantly different from the null linear model. You should now run a test to see whether one model is significantly different from the other.

I suspect you won't have enough evidence to conclude that the models are significantly different from one another. It is possible (but unlikely) that the models are such that neither is different from the null model, but they are different from one another.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.