STAT303: Secs 102 and 103Summer I 2000Exam #4Form AInstructor: Julie Hagen Carroll1. Don’t EVEN open this until you are told to do so.2. Be sure to mark your section number and your test form (A, B, C or D) on the scantron!3. Sign your name where indicated on your scantron and write your section number, seat number andcomputer number beside it. You will get your scantrons back tomorrow in class. You may keep thisexam.4. There are 20 multiple-choice questions on this exam, each worth 5 points. There is partial credit. Pleasemark your answers clearly on the scantron. Multiple marks will be counted wrong.5. You will have 60 minutes to finish this exam.6. If you are caught cheating or helping someone to cheat on this exam, you both will receive a grade ofzero on the exam. You must work alone.7. This exam is worth 100 points, and will constitute 20% of your final grade.8. Good luck!1STAT303: 102 and 103 Exam #4, Form A Summer 20001. Suppose we ask a large(so the necessary assump-tions are met) random sample of people whetherthey would return the money if they found a wal-let on the street. To find out if age makes anydifference, we separated the sample into 5 agegroups. What test procedure should we use toanalyze the data?A. One way ANOVA on the multiple means.B. Case 9 since the sample is large and thereare no other assumptions.C. Case 6 since the data is categorical and thesample is large.D. Case 11 since the data is categorical and thesample is large.E. Chi-squared test since the data is categori-cal, and we have more than 2 proportions.2. What does the residual plot above tells us?A. The residuals are not linear, which is good.B. The linear relationship between fuel andpassenger load factor is not valid.C. The variance of the residuals is not con-stant.D. The assumption of normality of the residu-als may have been violated.E. The residual plot shows no problems.3. What does ‘statistical significance’ mean for aSimple Regression t-test?A. It means that the true slope is significant,definitely not 0.B. It means that the true mean of the y’s issignificant, definitely not 0.C. It means that the true mean of the y’s is 0.D. It means that the true slope is 0.E. None of the above are true.1=No| Summary of No. of fingercaffeine;| taps per minute2=100mg;|3=200mg| Mean Std. Dev. Freq.---------+------------------------------------1 | 244.8 2.394438 102 | 246.4 2.0655911 103 | 248.3 2.2135944 10---------+------------------------------------Total | 246.5 2.5964166 30Analysis of VarianceSource SS df MS F Pr > F----------------------------------------------Between 61.40 2 30.70 6.18 0.0062Within 134.10 27 4.97----------------------------------------------Total 195.50 29 6.74Bartlett’s test for equal variances:chi2(2) = 0.1877 Prob>chi2 = 0.9104. What are the null and alternative hypotheses forthe ANOVA test above?A. H0: µ1= µ2= µ3vs. HA: at least onemean is differentB. H0: µ1= µ2= µ3vs. HA: µ16= µ26= µ3C. H0: µ1= µ2vs. HA: µ16= µ2D. H0: µ1= µ2vs. HA: at least one mean isdifferentE. H0: µ1= µ2= µ3vs. HA: the means arenot all different5. What conclusion may be made from the previousoutput?A. The variances are not all equal.B. Drinking coffee makes you jittery.C. The more caffeine you consume, the jitterieryou get.D. There is a difference in the jitteriness, basedon finger taps, due to caffeine.E. None of the above are correct.6. What is the advantage of the paired t test overthe other 2 sample t tests?A. It uses less data.B. It has less variability.C. It has more degresses of freedom.D. All of the above are true.E. Exactly two of the above are true.7. Which of the following best describes the as-sumptions for the Chi-squared test in a contin-gency table?A. Each sample size must be at least 30.B. The variances must be equal.C. The means must be equal.D. The proportions must be equal.E. Each count must be at least 5.2STAT303: 102 and 103 Exam #4, Form A Summer 20008. An experiment was done with 15 students to seeif manual dexterity was better for the dominanthand compared to the non-dominant hand. Theexperiment consisted of tossing beans into a pa-per cup and counting how many beans made itin 15 seconds. The order in which the two handwere measured was randomized to compensatefor ‘learning’. How should the data be analyzed?A. Assuming that the data is normal, we canuse Case 2, the small sample t test.B. Assuming that the data is normal, we canuse Case 9, the 2 sample t test.C. Assuming that the data is normal, we canuse Case 8, the 2 sample t test since it’sprobable the variances are equal.D. Assuming that the data is normal, we canuse Case 10, the paired t test.E. Assuming that the true proportion isaround 0.5, we can use Case 11, the 2 sam-ple z test.9. Which of the following best describes what a p-value tells us for the Simple Regression t-test?A. The proportion of times we will get a sam-ple slope of 0 when the true slope is notzero.B. The proportion of times we will get a sam-ple slope of 0 when the true slope is zero.C. The proportion of times we will get a sam-ple slope as different from 0 as we got whenthe true slope is not zero.D. The proportion of times we will get a sam-ple slope that is not 0 when the true slopeis zero.E. The proportion of times we will get a sam-ple slope as different from 0 as we got whenthe true slope is zero.10. Why are the assumptions so important in statis-tical inference, i.e., hypothesis testing?A. They are the only rules we have to go by.B. They are what make the assumed distribu-tions valid.C. They are what minimize the Type I and IIerrors.D. They are what help us decide our conclu-sions.E. They are what help us decide which proce-dure to use.1=Yes, 0=NoWhether| Whether baby was rockedbaby cried| 0 1 | Total-----------+----------------------+----------0 | 78 15 | 931 | 48 3 | 51-----------+----------------------+----------Total| 126 18 | 144Pearson chi2(1) = 3.1618 Pr = 0.07511. What is the best conclusion about the outputabove?A. The p-value is NOT greater than 10%, sowe cannot assume that the variances areequal.B. At the 10% level, we can conclude thatrocking and crying babies are related.C. At the 10% level, we can conclude thatrocking causes babies to stop crying.D. Two of the above are true.E. None of the above are true.12. Assuming rocking and crying are independent,how many babies should we expect to cry eventhough they were rocked?A. 3B. 3/144C. (18/144)*(51/144)*144D. (3/18)*(3/51)*3E. (3/18)*(3/51)*14413. If I
View Full Document
Unlocking...