# HW_08 - Garcia 1 Victor Garcia STAT 312-074 HW 08: Due...

This preview shows pages 1–4. Sign up to view the full content.

Garcia 1 Victor Garcia STAT 312-074 HW 08: Due Monday, 15 Nov 2010 §9.7: P. 446 # 9.35, 9.36 §10.4: PP. 484-486 # 10.2, 10.3, 10.4, 10.5 §9.7 #9.35: Ho: µ a b c d ; Ha: not all µ’s are equal Drug Regimen Obs. Result A B C D Totals Severe 714 785 754 820 3073 Not Severe 9630 9543 9042 9557 37772 Totals 10344 10328 9796 10377 40845 a) At α=0.05, the χ 2 test on the ti-83 yeilds: (if Ho is true) Drug Regimen Exp. Result A B C D Totals Severe 778.24 777.03 737.01 780.72 3073 Not Severe 9565.76 9550.97 9058.99 9596.28 37772 Totals 10344 10328 9796 10377 40845 This also yields a p-value of .0387 and a test statistic of 8.383 (which is just outside the critical value for this distribution). Since the p-value is less than α=0.05, there is evidence to suggest that there is a significant difference between the four drug regimens with respect to the proportion of patients suffering severe adverse events. b) It may be worth it for an investigation of which method is the most effective. TPA costs 10 times as much as streptokinase does, and if it turns out to be just as or less effective than the streptokinase the community can save a large amount of money on this drug regimen. #9.36: Ho: µ 1 2 3 4 5 ; Ha: not all µ’s are equal Parts inspection Obs. Result Monday Tuesday Wednesday Thursday Friday Defective 12 7 7 10 14 Acceptable 88 93 93 90 86 Totals 100 100 100 100 100

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Garcia 2 a) At the 0.05 level of significance, the χ 2 test reveals (p-value=.3767)>(α=.05), and the test statistic=4.2222 (using df=4) is well inside the critical value for χ 2 . This lets us conclude that there is not enough evidence of a significant difference (and thus to reject the null hypothesis) in the proportion of defective parts produced on the various days of the week. b) If on Friday 24 defective parts were produced, then the χ 2 test statistic is 18.75 (well outside the 95% C.I. for chi-squared) and the p-value is well below alpha, indicating that there is a significant evidence to reject the null hypothesis and conclude that one day of the week is significantly different than the rest with respect to defective parts produced.
Garcia 3 §10.4 # 10.2: One-way ANOVA: Distance versus Design a) Ho: µ 1 2 3 4; Ha: not all µ’s are equal At the 0.05 level of significance, there is (rounded) a p-value=0.000 probability of obtaining a f statistic larger than 53.03 if the null hypothesis is true. Because of this we reject the null hypothesis. There is evidence of a

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## HW_08 - Garcia 1 Victor Garcia STAT 312-074 HW 08: Due...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online