STA 6166 – Exam 2 – Fall 2009 PRINT Name ______________________Researchers wished to compare the yields (in pounds) of 3 varieties of 4-year old orange trees in an orchard. They obtain random samples of 10 trees of each variety from the orchard and obtain the following results. Due to the skew of the distributions, they choose to use the appropriate non-parametric test.- Give the test statistic for testing H0: Variety Medians all equal versus HA: Variety Means not all equal- We reject H0 at the -=0.05 significance level if it falls in what range __________________- The P-value for this test is greater than / less than 0.05 (circle correct answer).Is cocaine deadlier than heroin? A study was conducted where rats were randomly assigned to receive unlimitedsupplies of cocaine or heroin. Of the 200 rats assigned to cocaine, 80% died in 30 days. Of the 200 rats assignedto heroin, 50% died in 30 days. - Compute a 95% Confidence Interval for -C - -H . Difference in population mean 30-day death rates for rats assigned to cocaine versus heroin.- Do you feel this is evidence to conclude that cocaine is deadlier than heroin in this setting? Yes / NoAn experiment was conducted to compare 3 mixtures of components in making rocket propellant. Eight samplesof each mixture were obtained for testing. Eight investigators were sampled, and each investigator measured thepropellant thrust (Note each investigator measured each mixture once, in random order). - For this experiment the treatments are mixtures and the blocks are investigators. True / False- Complete the following ANOVA table:- Do you conclude that the mixture effects differ at the 0.05 significance level? Yes / No- Compute the Minimum significant Difference for comparing mixture means based on Bonferroni’s method:- Compute the Relative Efficiency of having used this Randomized Complete Block (RCB) design as opposed to a Completely Randomized (CR) Design. That is, compute RE(RCB,CR)- How many replicates would you have needed per mixture to have the same standard error for the difference between two mixture means for a Completely Randomized (CR) Design?The following partial ANOVA table was obtained from a 2-way ANOVA where three advertisements were being compared among men and women. A total of 30 males and 30 females were sampled, and 10 of each were exposed to ads 1, 2, and 3, respectively. A measure of attitude toward the brand was obtained for each subject.Source df Sum of Squares Mean Square FAds 1000Gender 500Ads*Gender 1200Error 54 ---Total 59 5400 --- ---- Complete the ANOVA table- Test whether the ad effects differ among the genders (and vice versa) (-=0.05).- Test Statistic: _________________________- Conclude interaction exists if test statistic is ________________________- P-value is above or below 0.05 (circle one)A test is to be conducted to determine whether the incidence rate of acute mountain sickness is affected by the drugs acetozalomide and ginkgo. 300 hikers were randomized so that 100 received a placebo, 100 received Ginkgo, and 100 received Acetozalomide. The results are given below (test at -=0.05 significance level):observed AMS=Yes AMS=No TotalPlacebo 35 65 100Ginkgo 30 70 100Acet 10 90 100Total 75 225 300 expected AMS=Yes AMS=No TotalPlacebo 100Ginkgo 100Acet 100Total 75 225 300- Compute and fill in the expected counts for all 6 cells- The rejection region for the chi-square statistic is:- The test statistic for testing whether incidence of AMS Is associated with drug is 18.67, do we concludeThat treatment is associated with AMS Incidence?- Chi-square contribution from Placebo/AMS=Yes- Chi-square contribution from
View Full Document
Unlocking...