STAT303: Secs 508-510Fall 2006Exam #1Form AInstructor: Julie Hagen Carroll1. Don’t EVEN open this until you are told to do so.2. Be sure to mark your CORRECT section number and your test form on the scantron!3. Sign your name where indicated on your scantron. You may keep this exam.4. There are 20 multiple-choice questions on this exam, each worth 5 points. There is partial credit. Please mark youranswers clearly on the scantron. Multiple marks will be counted wrong.5. You will have 60 minutes to finish this exam.6. This exam is worth 100 points, and will constitute 15% of your final grade.7. If you are caught cheating or helping someone to cheat on this exam, you both will receive a grade of zero on theexam. You must work alone AND NOT discuss this exam with anyone until AFTER the grades are posted.8. Good luck!1STAT303: 510 Exam #1, Form A Fall 20061. A sample is to the population asA. a statistic is to a parameter.B.x is to µ.C. r is to ρ.D. All of the above are correct.E. Only two of the above are correct.2. Here is a two-way table of the numbers of college stu-dents (U.S. citizens only) classified by racial/ethnicgroup and by whether they attend a public or a pri-vate college. The entries are in thousands of students.Public Private TotalNon-Hispanic White 7094 1982 9076Non-Hispanic Black 831 290 1121Hispanic 336 47 383Asian 166 32 198Native American 68 9 77Total 8495 2360 10855How likely is a public college student to be non-Hispanicblack?A. 831/10855B. 831/1121C. 831/8495D. 1121/10855E. 8495/108553. Using the same table, how likely is a student to benative American and attend a private college?A. 9/10855B. 9/77C. 9/2360D. 77/10855E. 2360/108554. B¯LANK A in a sampling method means that the sampleresults will systematically misrepresent the populationin the same way when we take repeated samples. Forexample, if we contact only people listed in telephonedirectories, the sample suffers from BLANK B. If somepeople chosen for the sample refuse to participate, thesample suffers from BLANK C. Both BLANK B andBLANK C are common sources of BLANK A. B¯LANKA should readA. biasB. random sampling errorC. high variabilityD. undercoverageE. nonresponse5. If all of the boxplots have 100 observations, which onemost likely has the largest standard deviation?A. the first one since it has the worst (farthest awayfrom the median) outliersB. the second oneC. the third one since it has the most outliersD. the fourth oneE. the sixth one6. Which boxplot would have the tallest bins (bars) if wemade histograms of each? Again, there are 100 obser-vations in each dataset.A. the first oneB. the second oneC. the fourth oneD. the fifth oneE. the sixth one7. Which of the statements does not contain a statisticalblunder?A. There is a strong negative correlation between aperson’s gender and the amount that he or shepays for automobile insurance. Males must paymore for their insurance.B. The standard deviation of scores on the firstSTAT303 exam was s = −14 points.C. The mean height of young women is 64 inches, andthe correlation between their heights and weightsis 0.6 inches.D. The correlation between height and weight foradult females is about r = 1.2.E. All four statements contain blunders.2STAT303: 510 Exam #1, Form A Fall 20068. Which of the following is true? Consider all of thestatistics we have talked about: locations, spreads, z-scores, slope, intercept and correlation.A. Scale changes only affect measures of spread andthe slope.B. Shift changes only affect measures of location in-cluding the intercept.C. Outliers only affect the mean, standard deviationand range.D. Correlation and z-scores are not affected by anyof the above.E. Two of the above are true.9. Why are we not good randomizers?A. We allow prior knowledge to affect our choice.B. We allow our environment to affect our choice(think size and location).C. We know what our results should look like, so wepick our observations to fit.D. All of the above are reasons.E. Only two of the above are reasons.10. Which of the following is most likely the Five NumberSummary for the histogram above?A. 19,20,21,22,28B. 19,21,21,22,28C. 19,20,21,24,28D. 19,21,22,24,28E. You cannot tell from a histogram. You need astemplot.11. If the 28 year-old in the previous histogram was actually38, which of the following would be true?A. The median and IQR would be the same.B. The mean and standard deviation would both in-crease.C. If we created z-scores before (with 28) and after(with 38), they would be the same.D. All of the above are true.E. Only two of the above are true.12. Which of the following are true concerning the distri-bution of statistics?A. The shape is always normal if you take a randomsample.B. Bias has to do with the shape of the distribution.C. The larger the size of the sample, the less chanceyou have of getting a biased estimate.D. At least two of the above.E. None of the above are true.13. Corn variety #1 yielded 140 bushels per acre last yearat a research farm. This year, corn variety #2, plantedin the same location, yielded only 110 bushels per acre.Unfortunately, we don’t know whether the difference isdue to the superiority of variety #1 or to the effect ofthis year’s drought. This is an example ofA. bias due to voluntary response.B. random sampling error.C. confounding.D. the placebo effect.E. nonsampling error.14. If the correlation, r = 0, then it could beA. the scatterplot of x and y shows no pattern (justa random scatter of points).B. y is constant (sy= 0).C. there is a strong non-linear relationship between xand y.D. All of the above are possible.E. Only two of the above are possible.15. An article in the battalion said “Social drinkers makemore money than abstainers”. This is most likely truebecauseA. drinkers are more upwardly mobile than abstain-ers.B. all CEO’s are drinkers.C. high paying jobs are stressful and cause everyoneto drink.D. there’s a lurking variable to which both drinkingand income are related.E. It’s not true. The article was fabricated. (a lie)3STAT303: 510 Exam #1, Form A Fall 200616. If we wanted to show the relationship between drinking(yes or no) and income, which of the following shouldwe use?A. a two-way table with drinking as the column vari-able and income as the row variableB. side-by-side boxplots of income for drinkers andnonC. a scatterplot of income vs. drinks per weekD. two pie charts since drinking is a categorical vari-ableE. Any of the above would work.17. Which best describes
View Full Document
Unlocking...