STATS 2B03 Lecture Notes - Analysis Of Variance, Interval Estimation, Prediction Interval
Document Summary
H0: no linear relationship between y and x. If h0 is not rejected then the regression line = 0hat + 1hatx should not be used. If h0 is not rejected there could be some other relationship between y and x, for example y = 0 + 1x + 2x2. If h0 is not rejected, we can not conclude that there is no linear relationship between y and x. we can only conclude that there is not strong evidence of a linear relationship based on the given data. Step 2: reject h0 if |tn-2|>tn-2, 1- . Example (continued): do not reject h0 since 2. 6988<4. 3027. The hypothesis h0: 1=0, ha: 1 0 can also be tested using the following procedure: Step 2: reject h0 if f1, n-2>f1, n-2, 1- . Example (continued): do not reject h0 since 7. 28<18. 51. Calculations for the above f-statistic are summarized in an anova table.