This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Confidence Interval – 2 SIDED Don’t give 2-sided p-values for a one-sided test. Classwork When Y is transformed, it: Changes equal variance Changes distribution Changes shape We can look at measure of variability vs measure of mean. In essence, equal variance and distribution are tied together. When X is transformed, it only effects: the shape of the curve, nothing else. If red line sits on top of blue line, it is not statistically significant. If there is curvature on the dotted line, it means we have to transform the variable . Parameter estimates are for predicting (weights). Since there is log on Y even though there isn’t log in all of the X’s, the answer to predict will still be in terms of Log Y. In a residual plot, we should see randomness and if there is a pattern then something is not right....
View Full Document
- Winter '08
- Statistics, Statistical hypothesis testing, Statistical significance, alte rnative hypothesis, confidence inte rnal, variability vs measure