252y0121 3/26/01 ECO252 QBA2 Name SECOND HOUR EXAM Hour of Class Registered (Circle) March 20, 2001 MWF 10 11 TR 12:30 2:00 I. (14 points) Do all the following. (Make diagrams!!!) x ~ N 6,9 16 6 3 6 z P 1.00 z 1.11 1. P 3 x 16 P 9 9 P1.00 z 0 P0 z 1.11 .3413 .3665 .7078 5 6 0 6 z P 0.67 z 0.11 2. P0 x 5 P 9 9 P0.67 z 0 P0.11 z 0 .2486 .0438 .2048 14 6 24 6 z P 3.33 z 0.89 3. P24 x 14 P 9 9 P3.33 z 0 P0 z 0.89 .4996 .3133 .8129 4 6 2 6 z P 0.89 z 0.22 4. P2 x 4 P 9 9 P 0.89 z 0 P 0.22 z 0 .3133 .0871 .2262 2 6 5. F 2 (The Cumulative probability up to 2) . Px 2 P z 9 Pz 0.44 Pz 0 P 0.44 z 0 .5 .1700 .3300 6. A symmetrical interval about the mean with 79% probability. We want two points x .895 and x.105 , so that Px.895 x x105 .7900 . Make a diagram showing 6 in the middle at the center of a 79% region split into two areas with probabilities of .3950. From the diagram, if we replace x by z, P0 z z.105 .3950 . The closest we can come is P0 z 1.25 .3944 or P0 z 1.26 .3962 . Since neither of these is much closer than the other, use z.105 1.255 , and x z.105 6 1.255 9 6 11.295 , or -5.295 to 17.295. To check this note that 17 .295 6 5.295 6 z P 5.295 x 17 .295 P 9 9 P1.295 z 1.2558 2P0 z 1.255 2.3950 .7900 x.008 We want a point x.008 , so that Px x.008 .008 . Make a diagram of z showing zero in the middle, .4920 between 0 and z.008 and .008 above z.008 . From the diagram, if we replace x by z, P0 z z.008 .4920 . The Normal table says P0 z 2.41 .4920 . So z.008 2.41 , and x z.008 6 2.419 27.69. To check this note 7. 27 .69 6 Px 27 .69 P z Pz 2.41 Pz 0 P0 z 2.41 .5 .4920 .008 9 252y0121 3/19/01 II. (6 points-2 point penalty for not trying part a.) Show your work! A test shopper goes to Miller's Supermarkets 8 times and to Albert's Supermarkets 8 times. The amount that was spent using a standardized shopping list is shown below. You can regard these data as two independent random samples from populations with a normal distribution. For Miller's, the sample mean is 115.25 and the sample standard deviation is 1.75255. xm xa Obs Miller's Albert's 1 112 119 2 115 121 3 115 122 4 117 120 5 117 122 6 117 124 7 115 122 8 114 122 a. Compute s a , the standard deviation for Albert's. (3) b. Compute a 99% confidence interval for the difference between the population means 1 and 2 assuming that the variances are equal for the two parent populations. According to your confidence interval, is there a significant difference between the population means (You must tell why!)? (3) c. (Extra Credit) (i) Redo the confidence interval on the assumption that the variances are not equal. (6) (ii) Use an F-test to tell whether you should have assumed that the variances were or were not equal. (2) Solution: a) Use x 2 for Albert's and x1 for Miller's. x 2 115 .25 and s 2 1.75255 , so s 22 3.07143 . Line 1 2 3 4 5 6 7 8 x1 119 121 122 120 122 124 122 122 972 x x12 14161 14641 14884 14400 14884 15376 14884 14884 118114 x12 n1x12 118114 8121 .50 2 16 972 121 .50 s12 2.2857 s1 1.51186 n1 8 n1 1 7 7 b) From Table 3 of the Syllabus Supplement: Interval for Confidence Hypotheses Test Ratio Critical Value Interval Difference H 0: 0 d t 2 sd d cv 0 t 2 sd d 0 t between Two H 1: 0 s 1 1 d Means ( sd s p n 1s12 n2 1s 22 1 2 n n 2 1 1 2 unknown, sˆ p n1 n2 2 variances DF n1 n2 2 assumed equal) x1 1 2 252y0121 3/19/01 x1 121 .50, s12 2.2857 , s1 1.51186 x 2 115 .25, s 22 3.0714 , s 2 1.75255 DF n1 n 2 2 8 8 2 14 d x1 x 2 121 .50 115 .25 6.25 sˆ 2p n1 1s12 n2 1s22 = 72.2857 73.0714 2.2857 3.0714 n1 n2 2 sd s p 1 1 n1 n2 14 2 2.67955 1 1 2.67955 .25 8 8 2.67955 .01, 14 t .005 2.977 0.6698875 0.818467 Confidence Interval: d t sd 6.25 2.977 0.81847 6.25 2.4366 or 3.81 to 8.69. The 2 interval does not include 0, so there is a significant difference between the means. H 0 : 0 H : 2 H : 2 0 Formally, our hypotheses are H 1 : 0 or 0 1 or 0 1 We reject H 0 . H 1 : 1 2 H 1 : 1 2 0 1 2 Solution: b) From the formula table; Interval for Confidence Hypotheses Test Ratio Critical Value Interval H 0 : 0 H 1: 0 d t 2 s d Difference between Two Means( unknown, variances assumed unequal) s12 s 22 n1 n2 sd DF s12 s22 n 1 n2 1 2 2 n1 n1 1 s 22 d 0 sd d cv 0 t 2 s d Same as H 0: 1 2 2 s12 t 2 n2 n2 1 H 1: 1 2 if 0 0 x1 121 .50, s12 2.2857 , s1 1.51186 x 2 115 .25, s 22 3.0714 , s 2 1.75255 .01 d x1 x 2 121 .50 115 .25 6.25 s12 2.2857 0.285714 n1 8 s 22 3.0714 0.383929 n2 8 sd s12 s 22 0.669643 0.8183172 n1 n 2 s12 s 22 0.669643 n1 n 2 DF s12 s 22 n1 n 2 2 2 2 s12 s 22 n1 n2 n1 1 n2 1 .669643 2 2.28571 2 .383929 2 4 13 .7052 , so use 13 degrees of freedom. 7 3 252y0121 3/19/01 13 t .005 3.012 Confidence Interval: The 2-sided interval is d t sd 6.25 3.012 0.669643 6.25 2.01 or 2 4.24 to 8.26 H : 2 s 2 2.2857 c) F test. 0 1 . To test this at the 1% significance level, test 12 0.7442 and s 2 3.0714 H 1 : 1 2 s 22 s12 1 7,7 . F 7,7 is not on our table but F 7,7 6.99 is, and F 7,7 must be 1.343 against F.005 .005 .001 .005 0.7442 7,7 , do not reject H . Conclude that we should have larger than 6.99. Since neither ratio is larger than F.005 0 assumed that the variances were equal. 4 252y0121 3/19/01 III. Do at least 3 of the following 4 Problems (at least 10 each) (or do sections adding to at least 30 points Anything extra you do helps, and grades wrap around) . You must do problem 1a! Show your work! State H 0 and H1 where applicable. Do not answer a question 'yes' or 'no' without citing a statistical test. Use a 95% confidence level unless another level is specified. 1a. Turn in your computer output from computer problem 1 only. (3 - 2 point penalty for not handing this in.) b. (Bowerman et. al.) A researcher knows that last year's average credit card interest rate was 18.3% but believes that, due to increased competition, current rates are better. She checks the interest rates on a random sample of credit cards and comes up with the data given as 'int' on the next page. What does the first test tell us about whether rates have improved? State the null and alternative hypotheses and, using a 5% significance level, tell whether the researcher is right. (3) c. She now wishes to compare these rates with rates she finds in a search of banks that advertise on the net. She assembles another random sample as 'int1' and runs a second test. Again state the hypotheses and conclusion. (2) d. Using the statistics that have been computed for you, verify the value of t in the second test and show graphically how the computer got the p-value. (3) Data Display int 15.6 15.8 17.8 18.1 14.6 16.6 17.3 17.0 18.7 15.3 16.4 18.4 17.6 14.0 19.2 12.3 14.1 12.9 15.7 11.4 15.3 10.2 15.3 10.5 20.5 17.0 16.5 14.1 18.3 MTB > print 'int1' Data Display int1 18.5 17.3 18.7 15.1 13.6 22.1 MTB > ttest mu=18.3 'int'; SUBC> alt=-1. First Test T-Test of the Mean Test of mu = 18.300 vs mu < 18.300 Variable int N 15 Mean 16.827 StDev 1.538 SE Mean 0.397 T -3.71 P-Value 0.0012 H 0 : 18 .3 b) Solution: Since the p-value is below .05, reject the null hypothesis of equality and H 1 : 18 .3 conclude that now interest rates are better (lower). 5 252y0121 3/19/01 Second Test MTB > twosample 'int''int1'; SUBC> alt=1. Two Sample T-Test and Confidence Interval Twosample T for int vs int1 N Mean StDev int 15 16.83 1.54 int1 20 15.47 3.22 SE Mean 0.40 0.72 95% C.I. for mu int - mu int1: ( -0.33, T-Test mu int = mu int1 (vs >): T= 1.65 3.04) P=0.055 DF= 28 c) Solution: If is the mean interest rate from the old population and 1 is the rate from the net H 0 : int int1 H : 1 population, 0 or . Since the p-value is above .05, do not reject the null H 1 : 1 H 1 : int int1 hypothesis of equality. Conclude that now interest rates on the net cannot be proved to be better (lower). d) Solution: If we are comparing two samples, from the formula table; Interval for Confidence Hypotheses Test Ratio Interval Difference between Two Means( unknown, variances assumed unequal) 2 s12 s 22 n1 n2 sd DF s12 s22 n 1 n2 s12 s22 n1 n2 1 2 s12 2 n1 s 22 t d 0 sd d cv 0 t 2 sd Same as H 0: 1 2 2 n1 1 sd H 0 : 0 H 1: 0 d t sd Critical Value 2 n2 n2 1 .40 2 .72 2 H 1: 1 2 if 0 0 .82365 t d 0 16 .83 15 .47 0 1.65 Make a diagram sd .82365 showing an almost-normal curve with a mean at zero. The p-value is the probability that t 1.65 , so shade the area above 1.65 and label it 5.5%. MTB > 6 252y0121 3/19/01 2. Bowerman, O'Connell and Hand tell us that (i) of 30 investors who invested in a bond fund, 7 were dissatisfied, (ii) of 30 investors who invested in a stock fund, 6 were dissatisfied and (iii) of 40 investors who invested in a tax-deferred annuity, 10 were dissatisfied. You may assume that those who were not dissatisfied were satisfied. Use a 99% confidence level. a. Do a two sided confidence interval for the difference between the proportion satisfied with the bond fund and with the stock fund. (3) b. Test that the proportion of investors who were satisfied with the stock fund was higher than the proportion who invested in the bond fund. (3) c. Test the hypothesis that the proportioned satisfied was the same for each investment (6) Solution: To summarize the information in the problem - .01 and Investment Bond Fund Stock Fund Annuity 23 24 30 Satisfied 7 6 10 Dissatisfied 30 30 40 Total .7667 .8000 .7500 Proportion satisfied We are comparing p1 .7667 , n1 30 and p 2 .8000 , n2 30. Interval for Confidence Hypotheses Test Ratio Interval Difference p p 0 p p z 2 sp H 0 : p p0 z between p H 1 : p p0 p p1 p2 proportions If p 0 p p p p1q1 p2 q 2 0 01 02 q 1 p s p p01q 01 p02 q 02 p n1 n2 or p 0 0 n n 1 Or use s p s p 2 Critical Value pcv p0 z 2 p If p0 0 p p0 q 0 1 n1 1 n2 n p n2 p2 p0 1 1 n1 n 2 p1 q1 p 2 q 2 .7667 .2333 .800 .200 .0059624 .0053333 .0112954 .10628 n1 n2 30 30 p p1 p 2 .0333 , p 0 23 24 n1 p1 n 2 p 2 30 .7667 30 .8000 .7833 , 30 30 n1 n 2 30 30 .01, z z.01 2.327, z 2 z.005 2.576. Note that q 1 p and that q and p are between 0 and 1. p p 0 q 0 1 a) p p z 2 .7833 .2167 130 130 .011316 .10638 s p .0333 2.576 .10628 .033 .274 or -.307 to .241. 2/3 of you were following n1 1 n3 the old exam so slavishly that you never realized that I had asked for a confidence interval! H 0 : p 0 H 0 : p1 p 2 H 0 : p1 p 2 0 b) Same as or (Only one of the following methods is H 1 : p 0 H 1 : p1 p 2 H 1 : p1 p 2 0 needed!) p p 0 .0333 0 0.313 Make a Diagram showing a 'reject' region below Test Ratio: z p .10638 -2.327. Since -0.131 is above this, do not reject H 0 . or Critical Value: pcv p0 z p 0 2.327 .10638 .2473 . Make a Diagram showing a 'reject' region below -.2473. Since -0.0333 is above this, do not reject H 0 . or Confidence Interval: p p z s p .0333 2.327 .10628 .2140 p .2140 is an interval that includes 0. In all cases do not reject H 0 . 7 252y0121 3/19/01 c) DF r 1c 1 12 2 H 0 : Homogeneousor p1 p 2 p 3 H 1 : Not homogeneousNot all ps are equal O Satisfied Not Total .2012 9.2103 Bond Stock Annuity Total p r 23 24 30 77 .77 7 6 10 23 .23 30 30 40 100 1.00 E Satisfied Not Total Bond Stock Annuity Total p r 23 .1 23 .1 30 .8 77 .77 6.9 9.2 23 .23 6.9 30 .0 30 .0 40 .0 100 1.00 The proportions in rows, p r , are used with column totals to get the items in E . Note that row and column sums in E are the same as in O . (Note that one way is needed.) O2 O E E 23 23.1 22.9004 7 6.9 7.1014 24 23.1 24.9351 6 6.9 5.2174 30 30.8 29.2208 10 9.2 10.8696 100 100.0 100.2447 2 0.2447 is computed two different ways here - only OE -0.10000 0.10000 0.90000 -0.90000 -0.80000 0.80000 0.00000 O E 2 E 0.000433 0.001449 0.035065 0.117391 0.020779 0.069565 0.24468 O E 2 100 .2337 100 0.2447 O2 n E E Since this is less than 9.2103, do not reject H 0 . (Diagram!) 8 252y0121 3/19/01 3. You have a sample of earned incomes for 9 couples, both of whom are teachers. You wish to test if the women make more than the men. (Look at problem 4 before you do this problem - the data are identical, what you do with it is different.) a. You decide to compare means. Test to see if the women make more than the men assuming that the data comes from a Normal distribution. (5) b. You are reminded that the income data is usually highly skewed, so you ought to compare medians instead of means. Repeat the test. (5) For your convenience, not only the raw data are provided, but the data is ranked from 1 to 20 in the columns r1 and r2 . If you need the ranks of the differences, r , you will have to do it yourself. Minitab gives us the following results: x1 61.64, s1 12.23 (These are the sample mean and sample standard deviation of x1 ), x 2 57.86, s 2 7.56, d 3.78, s d 16.57. You do not need all this information in every part of the problem. Data is in thousands. Row women rank men rank difference rank d r x1 r1 x2 r2 1 47.5945 2 65.6336 15 -18.0391 2 58.5687 8 59.8417 10 -1.2730 3 43.4502 1 59.6314 9 -16.1812 4 62.3263 13 53.1761 6 9.1501 5 60.3484 11 48.1425 3 12.2060 6 65.3845 14 50.6700 4 14.7145 7 80.1389 18 51.5944 5 28.5445 8 78.6558 17 61.0681 12 17.5877 9 58.2903 7 70.9990 16 -12.7087 Solution: This is paired data. a) Assume .05 . All tests of the mean or median in Problems three and four are one-sided. The following table may help you choose a method. Save it for the final exam! Comparing 2 Samples Paired Samples Independent Samples Location - Normal distribution. Method D4 Methods D1- D3 Compare means. Location - Distribution not Normal. Compare medians. Method D5b Method D5a Proportions Method D6 Variability - Normal distribution. Compare variances. Method D7 From the outline, there are three ways of approaching a problem involving two means. We know that s H : 2 16 .57 5.52333 . We are testing 0 1 d x1 x 2 3.78 , 1 2 , s d 16.57, s d d n 9 H 1 : 1 2 H 0 : 1 2 0 H 0 : 0 8 1.860 . or or , df n 1 8 , tn 1 t .05 H : 0 H : 0 2 1 1 1 (i) . Confidence Interval: d t 2 s d or 1 2 x1 x 2 t 2 s d . This interval becomes d t s d 3.78 - 1.860 5.52333 3.78 - 10.27 -6.49 . Since this interval includes zero, we cannot reject H 0 . 9 252y0121 3/19/01 (ii). Test Ratio: t t x x 2 10 20 d 0 or t 1 . sd sd d 0 3.78 0 0.684 . Make a diagram showing an almost Normal curve with a sd 5.52333 8 mean at zero and a 'reject' region above tn 1 t .05 1.860 . Since 0.684 is not in this region, we cannot reject H 0 . (iii). Critical Value: d CV 0 t 2 s d or x1 x 2 CV 10 20 t 2 s d . Because this is a one-sided test, we want one critical value above zero. The critical value formula becomes d CV 0 t s d 0 1.860 5.52333 9.734 Make a diagram showing an almost Normal curve with a mean at zero and a 'reject' region above 9.734. Since 3.78 is not in this region, we cannot reject H 0 . Note that only one of the three methods above is required. b) If the underlying distributions are not Normal and the two samples are paired, we should use a Wilcoxon Signed Rank test. difference rank H 0 : 1 2 Our hypotheses are . The signed d r H 1 : 1 2 -18.0391 8ranks of the differences are at right. If we add -1.2730 1-16.1812 6ranks with like signs, we get T 19 and 9.1501 2+ T 26 (Check: Their total is the sum of the 12.2060 3+ 910 14.7145 5+ 45 . ) numbers 1 through 9, which is 2 28.5445 9+ According to the Wilcoxon table for a 1-sided 17.5877 7+ -12.7087 45% test, reject the null hypothesis if the smaller of these totals is less than 8. Since neither of the totals is below 8, do not reject H 0 . 10 252y0121 3/19/01 4. You have two independent random samples of 9 incomes from each of two towns. You wish to test if the people in town 1 make more than people in town 2. (The numbers just happen to be the same as in the last problem) a. You decide to compare means. Test to see if the people in town 1 make more than the people in town 2 assuming that the data comes from a Normal distribution. (5) b. You are reminded that the income data is usually highly skewed, so you ought to compare medians instead of means. Repeat the test. (5) For your convenience, not only the raw data are provided, but the data is ranked from 1 to 20 in the columns r1 and r2 . If you need the ranks of the differences, r , you will have to do it yourself. Minitab gives us the following results: x1 61.64, s1 12.23 (These are the sample mean and sample standard deviation of x1 ), x 2 57.86, s 2 7.56, d 3.78, s d 16.57. You do not need all this information in every part of the problem. Data is in thousands. c. In part a of this question, what assumption did you make about the variances of x1 and x 2 ? Test it here. (3). d. Using the means and variances given above, but assuming that n1 n 2 160 do a 2-sided 98.4% confidence interval for 1 2 . (4) Row 1 2 3 4 5 6 7 8 9 Town 1 x1 47.5945 58.5687 43.4502 62.3263 60.3484 65.3845 80.1389 78.6558 58.2903 rank r1 2 8 1 13 11 14 18 17 7 Town 2 x2 65.6336 59.8417 59.6314 53.1761 48.1425 50.6700 51.5944 61.0681 70.9990 rank difference d r2 15 -18.0391 10 -1.2730 9 -16.1812 6 9.1501 3 12.2060 4 14.7145 5 28.5445 12 17.5877 16 -12.7087 rank r Solution: a) Assume .05 . All tests of the mean or median in Problems three and four are one sided. From the outline, there are three ways of approaching a problem involving two means. We know that H 0 : 1 2 H 0 : 1 2 0 H 0 : 0 or or . It is most d x1 x 2 3.78 . We are testing H 1 : 1 2 H 1 : 1 2 0 H 1 : 0 convenient to assume that 1 2 , though we really ought to test it in part c). It is not wrong to assume that variances differ, but the solution will only be provided to people who did so. If we assume that 16 1.746 , variances are equal we find n1 n2 9 , df n1 n 2 2 16, t .05 n 1s12 n2 1s 22 812.232 87.56 2 149 .5729 57.1536 s p2 1 103 .36325 and n1 n 2 2 16 2 1 1 1 1 103 .36325 22 .9696 4.7927 . s d s p2 9 9 n1 n 2 Only one of the following methods is expected. (i) . Confidence Interval: d t 2 s d or 1 2 x1 x 2 t 2 s d . This interval becomes d t s d 3.78 - 1.746 4.7927 3.78 - 8.368 -4.588 . Since this interval includes zero, we cannot reject H 0 . 11 252y0121 3/19/01 (ii). Test Ratio: t x x 2 10 20 d 0 or t 1 . sd sd d 0 3.78 0 0.7886 . Make a diagram showing an almost Normal curve with sd 4.7927 a mean at zero and a 'reject' region above t 16 1.746 . Since 0.7886 is not in this region, t .05 we cannot reject H 0 . (iii). Critical Value: d CV 0 t 2 s d or x1 x 2 CV 10 20 t 2 s d . Because this is a one-sided test, we want one critical value above zero. The critical value formula becomes d CV 0 t s d 0 1.746 4.7927 8.368 Make a diagram showing an almost Normal curve with a mean at zero and a 'reject' region above 8.368. Since 3.78 is not in this region we cannot reject H 0 . b) If the underlying distributions are not Normal and the two samples are independent, we should use a H 0 : 1 2 Mann-Whitney-Wilcoxon Rank test. Our hypotheses are . The rank total for Town 1 (gotten H 1 : 1 2 from adding the r1 column) is T1 91 and, for Town 2, T2 80 . (Check: Their total is the sum of the 18 19 171 . ) According to Table 6 (for a 1-sided 5% test), we do not 2 reject null hypothesis if the smaller of these totals ( W 80 ) is between 54 and 90. Since both of the totals are in that interval, do not reject H 0 . numbers 1 through 18, which is 2 H 0 : 1 2 s 2 12 .23 c) . To test this at the 5% significance level, test 12 2.617 and s 2 7.56 H 1 : 1 2 s 22 s12 1 8,8 4.43 . Since neither is larger than 4.43, do not reject 0.384 against F.025 H0. 2.617 d) If the confidence level is 98.4%, the significance level is 1 .984 .016 . Since our samples have a total number of degrees of freedom of df n1 n 2 2 160 160 2 318 , we can use z instead of t . s2 s2 12 .23 2 7.56 2 sd 1 2 160 n1 n 2 160 149 .5729 57 .1536 1.13668 . z z.008 , and we found 2 160 that it was 2.41 on page 1. Our confidence interval is d t 2 s d 3.78 2.411.13668 3.78 2.74. 12