This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Stat 231 Chapter 4 2. a) A Poisson distribution is a likely probability distribution, since the data involves counts of eggs. b) For data with a Poisson distribution the square root transformation is often a good variance stabilizing transformation. c) The slope of the LOG(SD) vs. LOG(mean) plot is 0.57813 m = , indicating that 1-m is approximately 1/2. This agrees with the value in part (b). [The Fmax HOV test is significant at the .05 level, although the BF HOV test has a p- value just above 0.05. Also, the QQ plot shows a heavy right tail for the distribution of the residuals.] d) After the square root transformation [x_eggs=SQRT(eggs)] the Fmax HOV test is no longer significant and the BF HOV test is highly non-significant. The QQ plot of the residuals also looks better. SAS output for Problem #2 : c) Brown and Forsythe's Test for Homogeneity of eggs Variance ANOVA of Absolute Deviations from Group Medians Sum of Mean Source DF Squares Square F Value Pr > F strain 2 115941 57970.7 57970....
View Full Document