Chapter 10 Statistical Inference About Means and Proportions with Two Populations Learning Objectives Be able to develop interval estimates and conduct hypothesis tests about the difference between two population means when and are known Know the properties of the sampling distribution of x1 x2 Be able to use the t distribution to conduct statistical inferences about the difference between two population means when and are unknown Learn how to analyze the difference between two population means when the samples are independent and when the samples are matched Be able to develop interval estimates and conduct hypothesis tests about the difference between two population proportions Know the properties of the sampling distribution of p1 p2 10 1 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 Solutions: a x1 x2 = 13.6 11.6 = 2 b z / z.05 1.645 12 22 n1 n2 x1 x2 1.645 (2.2) (3) 50 35 1.645 2 .98 c (1.02 to 2.98) z / z.025 1.96 1.96 (2.2)2 (3) 50 35 2 1.17 a z x1 (.83 to 3.17) x2 D0 2 n1 n2 (25.2 22.8) (5.2) 40 50 b pvalue = 1.0000 .9788 = .0212 c pvalue .05, reject H0. a z x1 x2 D0 2 n1 n2 (104 106) (8.4) (7.6) 80 70 2.03 1.53 b pvalue = 2(.0630) = .1260 c pvalue > .05, do not reject H0. a 1 = Population mean for smaller cruise ships = Population mean for larger cruise ships x1 x2 = 85.36 – 81.40 = 3.96 10 2 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations b z.025 12 22 n1 n2 1.96 (4.55) (3.97) 1.88 37 44 c 3.96 ± 1.88 a x1 x2 = 135.67 – 68.64 = 67.03 b z / c 67.03 17.08 (49.95 to 84.11) We estimate that men spend $67.03 more than women on Valentine’s Day with a margin of error of $17.08 (2.08 to 5.84) 12 22 (35)2 (20) 2.576 17.08 n1 n2 40 30 1 = Mean hotel price in Atlanta = Mean hotel price in Houston H0: 1 2 �0 Ha: 1 2 z x1 x2 D0 n1 n2 2 (91.71 101.13) 202 252 35 40 1.81 pvalue = .0351 pvalue .05; reject H0. The mean price of a hotel room in Atlanta is lower than the mean price of a hotel room in Houston a 1 = Population mean 2002 = Population mean 2003 H0: 1 0 Ha: 1 b c With time in minutes, x1 x2 = 172 166 = 6 minutes z x1 x2 D0 2 n1 n2 (172 166) 12 12 60 50 2.61 10 3 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 pvalue = 1.0000 .9955 = .0045 pvalue .05; reject H0. The population mean duration of games in 2003 is less than the population mean in 2002 d 12 22 n1 n2 x1 x2 z.025 (172 166) 1.96 6 4.5 122 122 60 50 (1.5 to 10.5) e Percentage reduction: 6/172 = 3.5%. Management should be encouraged by the fact that steps taken in 2003 reduced the population mean duration of baseball games. However, the statistical analysis shows that the reduction in the mean duration is only 3.5%. The interval estimate shows the reduction in the population mean is 1.5 minutes (.9%) to 10.5 minutes (6.1%). Additional data collected by the end of the 2003 season would provide a more precise estimate. In any case, most likely the issue will continue in future years. It is expected that major league baseball would prefer that additional steps be taken to further reduce the mean duration of games. a This is an upper tail hypothesis test H : 1 � H a : 1 z x1 x2 n1 n2 2 (76 73) 62 62 60 60 2.74 pvalue = area in upper tail at z = 2.74 pvalue = 1.0000 .9969 = .0031 Since .0031 � α = .05, we reject the null hypothesis. The difference is significant. We can conclude that customer service has improved for Rite Aid b This is another upper tail test but it only involves one population H : �75.7 H a : 75.7 10 4 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations z x1 75.7 n1 (76 75.7) 62 60 39 pvalue = area in upper tail at z = .39 pvalue = 1.0000 .6517 = .3483 c Since .3483 > α = .05, we cannot reject the null hypothesis. The difference is not statistically significant This is an upper tail test similar to the one in part (a) H : 1 � H a : 1 z x1 x2 n1 n2 2 (77 75) 62 60 60 1.83 pvalue = area in upper tail at z = 1.83 pvalue = 1.0000 .9664 = .0336 Since .0336 � α = .05, we reject the null hypothesis. The difference is significant. We can conclude that customer service has improved for Expedia d We will reject the null hypothesis of “no increase” if the pvalue ≤ .05. For an upper tail hypothesis test, the pvalue is the area in the upper tail at the value of the test statistic. A value of z = 1.645 provides an upper tail area of .05. So, we must solve the following equation for x1 x2 z x1 x2 62 62 60 60 x1 x2 1.645 1.645 62 62 1.80 60 60 This tells us that as long as the 2008 score for a company exceeds the 2007 score by 1.80 or more the difference will be statistically significant e The increase from 2007 to 2008 for J.C. Penney is not statistically significant because it is less than 1.80. We cannot conclude that customer service has improved for J.C. Penney a x1 x2 = 22.5 20.1 = 2.4 10 5 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 b s12 s22 2.52 4.82 n1 n2 20 30 df 45.8 2 2 2.52 4.82 s12 s22 19 20 29 30 n1 n1 n2 n2 Use df = 45 c t.025 = 2.014 s12 s22 2.52 4.82 2.014 2.1 n1 n2 20 30 t.025 d 10 a 2.4 2.1 t x1 (.3 to 4.5) x2 2 s s n1 n2 (13.6 10.1) 5.22 8.52 35 40 2.18 b s12 s22 5.22 8.52 n1 n2 35 40 df 65.7 2 2 5.22 8.52 s12 s22 34 35 39 40 n1 n1 n2 n2 Use df = 65 c Using t table, area in tail is between .01 and .025 twotail pvalue is between .02 and .05 Exact pvalue corresponding to t = 2.18 is .0329 d pvalue .05, reject H0 11 a x1 54 42 9 x2 7 6 b s1 ( xi x1 ) 2.28 n1 s2 ( xi x2 ) 1.79 n2 c x1 x2 = 9 7 = 2 10 6 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations d s12 s22 2.282 1.79 n1 n2 6 df 9.5 2 2 2.282 1.79 s12 s22 5 5 n1 n1 n2 n2 Use df = 9, t.05 = 1.833 x1 x2 1.833 2 2.17 12 a 2.282 1.792 6 (-.17 to 4.17) x1 x2 = 22.5 18.6 = 3.9 b s12 s22 8.42 7.42 n1 n2 50 40 df 87.1 2 2 8.42 7.42 s12 s22 49 50 39 40 n1 n1 n2 n2 Use df = 87, t.025 = 1.988 3.9 1.988 3.9 13 a x1 x2 b (.6 to 7.2) xi 111.6 9.3 n1 12 s1 s2 8.42 7.42 50 40 ( xi x1 ) 71.12 2.54 n1 12 xi 42 4.2 n2 10 ( xi x2 ) 18.4 1.43 n2 10.1 x1 x2 = 9.3 4.2 = 5.1 tons Memphis is the higher volume airport and handled an average of 5.1 tons per day more than Louisville. Memphis handles more than twice the volume of Louisville 10 7 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 c s12 s22 2.542 1.432 n1 n2 12 10 df 17.8 2 2 2.542 1.432 s12 s22 11 12 10 n1 n1 n2 n2 Use df = 17, t.025 = 2.110 ( x1 x2 ) t.025 5.1 2.110 14 a s12 s22 n1 n2 2.542 1.432 12 10 5.1 1.82 (3.28 to 6.92) H0: 1 2 �0 Ha: 1 2 b t x1 x2 (56,100 59, 400) 2.41 s12 s22 n1 n2 (6000) (7000) 40 50 c �s12 s22 � �60002 70002 � � � � � n1 n2 � 40 50 � � � df 2 2 = 87.55 �6000 � �7000 � �s12 � �s22 � � � � � � � � � n1 �n1 � n2 �n2 � 40 � 40 � 50 � 50 � Rounding down, we will use a t distribution with 87 degrees of freedom. From the t table we see that t = 2.41 corresponds to a pvalue between .005 and .01 Exact pvalue corresponding to t = 2.41 is .009 d pvalue .05, reject H0. We conclude that the salaries of staff nurses are lower in Tampa than in Dallas 1 for 2001 season 15 2 for 1992 season H0: 1 0 Ha: 1 b x1 x2 = 60 51 = 9 days 10 8 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations 9/51(100) = 17.6% increase in number of days c t x1 x2 2 s s n1 n2 (60 51) 182 152 45 38 2.48 2 s12 s22 182 152 n1 n2 45 38 df 81 2 2 182 152 s12 s22 44 45 37 38 n1 n1 n2 n2 Using t table, pvalue is between .005 and .01 Exact pvalue corresponding to t = 2.48 is .0076 pvalue .01, reject H0. There is a greater mean number of days on the disabled list in 2001. d 16 a Management should be concerned. Players on the disabled list have increased 32% and time on the list has increased by 17.6%. Both the increase in inquiries to players and the cost of lost playing time need to be addressed 1 = population mean verbal score parents college grads 2 = population mean verbal score parents high school grads H0: 1 0 Ha: 1 b x1 xi 8400 525 n 16 x2 xi 5844 487 n 12 x1 x2 = 525 487 = 38 points higher if parents are college grads c s1 ( xi x1 ) 52962 3530.8 59.42 n1 16 s2 ( xi x2 ) 29456 2677.82 51.75 n2 12 t x1 x2 D0 2 s s n1 n2 (525 487) 59.42 51.752 16 12 1.80 10 9 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 2 s12 s22 59.422 51.752 n1 n2 16 12 df 25.3 2 2 59.422 51.752 s12 s22 15 16 11 12 n1 n1 n2 n2 Use df = 25 Using t table, pvalue is between .025 and .05 Exact pvalue corresponding to t = 1.80 is .0420 d 17 a pvalue .05, reject H0. Conclude higher population mean verbal scores for students whose parents are college grads H0: 1 0 Ha: 1 b t x1 x2 D0 2 s s n1 n2 (6.82 6.25) 64 752 16 10 1.99 c s12 s22 642 752 n1 n2 16 10 df 16.9 2 2 642 752 s12 s22 15 16 10 n1 n1 n2 n2 Use df = 16 Using t table, pvalue is between .025 and .05 Exact pvalue corresponding to t = 1.99 is .0320 d 18 a pvalue .05, reject H0. The consultant with more experience has a higher population mean rating H0: 1 2 120 Ha: 1 120 b t x1 x2 D0 2 s s n1 n2 (1058 983) 120 902 1052 35 48 2.10 10 10 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 (di d )2 26 2.08 n 7 c sd d d = 2 e With 6 degrees of freedom t.025 = 2.447 2.447 2.082 / 2 1.93 21 (.07 to 3.93) Difference = rating after rating before H0: d 0 Ha: d > 0 d = .625 and sd = 1.30 t d d 625 1.36 sd / n 1.30 / df = n 1 = 7 Using t table, pvalue is between .10 and .20 Exact pvalue corresponding to t = 1.36 is .1080 Do not reject H0; we cannot conclude that seeing the commercial improves the mean potential to purchase 22 Let di = current qtr. per share earnings – previous quarter per share earnings d �di / n 2064 sd �(di d ) 2654 n 1 With df = 24, t.025 = 2.064 d t.025 sd n �.2654 � 2064 2.064 � � � 25 � Confidence interval: $.21 $.11 ($.10 to $.32) Earnings have increased. The point estimate of the increase in earnings per 10 12 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations share is $.21 with a margin of error of $.11 23 a 1 = population mean grocery expenditures 2 = population mean diningout expenditures H0: d 0 Ha: d 0 b t d d 850 4.91 sd / n 1123 / 42 df = n 1 = 41 pvalue 0 Conclude that there is a difference between the annual population mean expenditures for groceries and for diningout c Groceries has the higher mean annual expenditure by an estimated $850 d t.025 sd n 850 2.020 1123 42 850 350 (500 to 1200) 24 H0: d≤ 0 Ha: d> 0 Differences 177, 21, 186, 131, 22, 212, 5, 14 d �d i / n 454 / 56.75 sd t �(di d ) 121.5445 n 1 d 0 56.75 1.32 sd 121.5445 n df = n 1 = 7 Using t table, pvalue is greater than .10 10 13 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 Exact pvalue corresponding to t = 1.32 is .1142 Since pvalue > .10, do not reject H0. We cannot conclude that airfares from Dayton are higher than those from Louisville at a α = .05 level of significance 25. a H0: d= 0 Ha: d 0 Use difference data: 3, 2, 4, 3, 1, 2, 1, 2, 0, 0, 1, 4, 3, 1, 1 d di 18 1.2 n 15 (d i d ) 54.4 1.97 n 15 sd t d d sd / n 1.2 1.97 / 15 2.36 df = n 1 = 14 Using t table, area is between .01 and .025. Twotail pvalue is between .02 and .05. Exact pvalue corresponding to t = 2.36 is .0333 pvalue .05, reject H0. Conclude that there is a difference between the population mean weekly usage for the two media b xTV xR xi 282 18.8 hours per week for cable television n 15 xi 300 20 hours per week for radio n 15 Radio has greater usage 26 a H0: d= 0 Ha: d 0 Differences: 2, 1, 5, 1, 1, 0, 4, 7, 6, 1, 0, 2, 3, 7, 2, 3, 1, 2, 1, 4 d �di / n 21/ 20 1.05 10 14 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations sd t �(d i d ) 3.3162 n 1 d d sd / n 1.05 3.3162 / 20 1.42 df = n – 1 = 19 Using t table, area in tail is between .05 and .10 Twotail pvalue must be between .10 and .20 Exact pvalue corresponding to t = 1.42 is .1718 Cannot reject H0. There is no significant difference between the mean scores for the first and fourth rounds b d = 1.05; First round scores were lower than fourth round scores c α = .05 df = 19 Margin of error = t.025 sd n t = 1.729 = 1.729 3.3162 20 1.28 Yes, just check to see if the 90% confidence interval includes a difference of zero. If it does, the difference is not statistically significant 90% Confidence interval: 1.05 ± 1.28 (2.33, .23) 27 a The interval does include 0, so the difference is not statistically significant Difference = Price deluxe Price Standard H0: d = 10 Ha: d 10 d = 8.86 and sd = 2.61 t d d 8.86 10 116 sd / n 2.61 / df = n 1 = 6 Using t table, area is between .10 and .20 Twotail pvalue is between .20 and .40 Exact pvalue corresponding to t = 1.16 is .2901 Do not reject H0; we cannot reject the hypothesis that a $10 price differential exists 10 15 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 b 95% Confidence interval d �t.025 sd / n 8.86 �2.447(2.61) / 8.86 �2.41 or (6.45 to 11.27) 28 a b c p1 p2 = .48 .36 = .12 p1 (1 p1 ) p2 (1 p2 ) n1 n2 p1 p2 z.05 12 1.645 48(1 48) 36(1 36) 400 300 12 .0614 (.0586 to .1814) 12 1.96 48(1 48) 36(1 36) 400 300 12 .0731 29 a p z (.0469 to .1931) n1 p1 n2 p2 200(.22) 300(.16) .1840 n1 n2 200 300 p1 p2 1 p 1 p n1 n2 22 16 1840 1840 200 300 1.70 p value = 1.0000 .9554 = .0446 b 30. pvalue .05; reject H0 p1 = 220/400 = .55 p2 = 192/400 = .48 p1 p2 z.025 p1 (1 p1 ) p2 (1 p2 ) n1 n2 55 48 1.96 55(1 55) 48(1 48) 400 400 10 16 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations 07 .0691 (.0009 to .1391) 7% more executives are predicting an increase in fulltime jobs. The confidence interval shows the difference may be from 0% to 14% 31 a Professional Golfers: p1 = 688/1075 = .64 Amateur Golfers: p2 = 696/1200 = .58 Professional golfers have the better putting accuracy b. p1 p 64 58 06 Professional golfers make 6% more 6foot putts than the very best amateur golfers c p1 p2 z.025 p1 (1 p1 ) p2 (1 p2 ) n1 n2 64 58 �1.96 64(1 64) 58(1 58) 1075 1200 06 .04 (.02 to .10) The confidence interval shows that professional golfers make from 2% to 10% more 6foot putts than the best amateur golfers. 32. a. H : pw �pm b H a : pw pm pw = 300/811 = .3699 37% of women would ask directions c pm = 255/750 = .3400 34% of men would ask directions d p z n1 pw n2 pm 300 255 3555 n1 n2 811 750 p1 p2 3699 3400 1.23 � �1 � �1 p p � � 3555 3555 � � �811 750 � �n1 n2 � Upper tail p-value is the area to the right of the test statistic Using normal table with z = 1.23: p-value = - 8907 = 1093 pvalue > α ; do not reject H We cannot conclude that women are more likely to ask directions 10 17 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 33 Let p1 = the population proportion of delayed departures at Chicago O’Hare p2 = the population proportion of delayed departures at Atlanta HartsfieldJackson a H0: p1 p2 = 0 Ha: p1 p2 ≠ 0 b p1 = 252/900 = .28 c p2 = 312/1200 = .26 d p z n1 p1 n2 p2 252 312 2686 n1 n2 900 1200 p1 p2 28 26 1.02 � �1 � �1 p p � � 2686 2686 � � �900 1200 � �n1 n2 � pvalue = 2(1 .8461) = .3078 Do Not Reject H0. We cannot conclude that there is a difference between the proportion of delayed departures at the two airports. 34 a p1 = 192/300 = .64 b p2 = 117/260 = .45 c p1 p2 = .64 .45 = .19 19 �z.025 p1 (1 p1 ) p2 (1 p2 ) n1 n2 19 �1.96 64(1 64) 45(1 45) 300 260 19 .0813 35 a (.1087 to .2713) H0: p1 p2 = 0 Ha: p1 p2 0 p1 = 63/150 = .42 p2 = 60/200 = .30 10 18 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations p n1 p1 n2 p2 63 60 .3514 n1 n2 150 200 p1 p2 z 1 p 1 p n1 n2 42 30 3514 3514 150 200 2.33 pvalue = 2(1.0000 .9901) = .0198 pvalue .05, reject H0. There is a difference between the recall rates for the two commercials b p1 p2 z.025 p1 (1 p1 ) p2 (1 p2 ) n1 n2 42 30 1.96 42(1 42) 30(1 30) 150 200 12 .1014 (.0186 to .2214) Commercial A has the better recall rate 36 a p1 = proportion of under 30 liking the ad a lot p2 = proportion of 30 to 49 liking the ad a lot H0: p1 p2 = 0 Ha: p1 p2 0 b p1 = 49/100 = .49 p2 = 54/150 = .36 p1 p2 = .49 .36 = .13 c p z n1 p1 n2 p2 100(.49) 150(.36) .412 n1 n2 100 150 p1 p2 1 p 1 p n1 n2 49 36 412 412 100 150 2.05 pvalue = 2(1.0000 .9798) = .0404 pvalue .05, reject H0. There is a difference between the response to the ad by the younger under 30 and the older 30 to 49 age groups 10 19 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 d 37 a There is a statistically significant difference between the population proportions for the two age groups. The stronger appeal is with the younger, under 30, age group. Miller Lite is most likely pleased and encouraged by the results of the poll. "The Miller Lite Girls" ad ranked among the top three Super Bowl ads in advertising effectiveness. In addition, 49% of the younger, under 30, group liked the ad a lot. While a response of 36% for the older age group was not bad, Miller Lite probably liked, and probably expected, the higher rating among the younger audience. Since a younger audience contains the newer beer drinkers, appealing to the younger audience could bring new customers to the Miller Lite product. The older age group may be less likely to change from their established personal favorite beer because of the commercial H0: p1 p2 = 0 Ha: p1 p2 0 b p1 = 141/523 = .2696 (27%) p2 = 81/477 = .1698 (17%) c p n1 p1 n2 p2 141 81 .2220 n1 n2 523 477 p1 p2 z 1 p 1 p n1 n2 2696 1698 222 222 523 477 3.79 pvalue 0 Reject H0. There is a significant difference in the population proportions. A higher flying rate in 2003 is observed d 38 It may be that the general population is more acceptable to flying on vacation in 2003. Also, frequent flyer awards and special discount air fares in 2003 may have made 2003 flying more economical. Note: In 1993, a round trip Newark to San Francisco was $388. In 2003, a special fare for the same trip was $238 H0: 1 2 = 0 Ha: 1 2 0 z ( x1 x2 ) D0 2 n1 n2 (4.1 3.4) (2.2)2 (1.5)2 120 100 2.79 pvalue = 2(1.0000 .9974) = .0052 pvalue .05, reject H0. A difference exists with system B having the lower mean checkout time 10 20 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations 39 a x1 xi 6, 776,900 225,897 Mean resale price in 2006 n1 30 x2 xi 6,839, 735 170,993 Mean resale price in 2009 n2 40 Difference = 225,897 – 170,993 = 54,904 Using sample mean prices, the 2009 resale prices are $54,904 less than in 2006 b s1 ( xi x1 ) 55, 207 n1 s2 ( xi x2 ) 44,958 n2 2 �s12 s22 � �55207 449582 � � � � � n1 n2 � 30 40 � � � df 54.92 2 2 �s12 � �s22 � �55207 � �449582 � � � � � � � � � n1 �n1 � n2 �n2 � 29 � 30 � 39 � 40 � Use df = 54, t.005 = 2.670 ( x1 x2 ) �t.005 s12 s22 n1 n2 54904 �2.670 55207 449582 30 40 54904 32931 (21,973 to 87,835) c We are 99% confident that home prices have declined by between $21,973 and $87,835 To answer this question we need to conduct a one-tailed hypothesis test No value for the level of significance (α) has been given But, most people would agree that a p-value �.01 would justify concluding that prices have declined from 2006 to 2009 H : 1 � H a : 1 2 t x1 x2 2 s s n1 n2 54,904 55, 207 44,9582 30 40 4.45 For t = 4.45 and df =54, we find p-value �0.00 Thus, we are justified in concluding that existing home prices have declined between 2006 and 2009 40 a H0: 1 2 0 10 21 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 Ha: 1 2 > 0 b n1 = 30 x1 = 16.23 s1 = 3.52 t n2 = 30 x2 = 15.70 s2 = 3.31 ( x1 x2 ) D0 2 s s n1 n2 (16.23 15.70) .60 (3.52) (3.31) 30 30 s12 s22 3.522 3.312 n1 n2 30 30 df 57.8 2 2 3.52 3.312 s12 s22 29 30 29 30 n1 n1 n2 n2 Use df = 57 Using t table, pvalue is greater than .20 Exact pvalue corresponding to t = .60 is .2754 pvalue > .05, do not reject H0. Cannot conclude that the mutual funds with a load have a greater mean rate of return 41. a n1 = 10 x1 = 21.2 s1 = 2.70 n2 = 8 x2 = 22.8 s2 = 3.55 x1 x2 = 21.2 22.8 = 1.6 Kitchens are less expensive by $1600 b s12 s22 2.702 3.552 n1 n2 10 df 12.9 2 2 2.70 3.552 s12 s22 10 n1 n1 n2 n2 Use df = 12, t.05 = 1.782 1.6 1.782 1.6 2.7 2.702 3.552 10 (-4.3 to 1.1) 42 a January April 30 di (di d ) 10 22 (di d ) © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations 10.13 28.33 73.97 16.30 45.27 16.88 2.29 16.20 59.83 31.53 19.44 17.73 17.71 43.51 61.82 d b 12.21 25.48 66.10 19.32 43.05 15.46 5.98 12.65 52.36 33.00 20.26 19.34 13.36 36.18 49.44 -2.08 2.85 7.87 -3.02 2.22 1.42 -3.69 3.55 7.47 -1.47 -0.82 -1.61 4.35 7.33 12.38 Sum 36.75 �di 36.75 2.45 n 15 sd -4.53 0.40 5.42 -5.47 -0.23 -1.03 -6.14 1.10 5.02 -3.92 -3.27 -4.06 1.90 4.88 9.93 20.5209 0.1600 29.3764 29.9209 0.0529 1.0609 37.6996 1.2100 25.2004 15.3664 10.6929 16.4836 3.6100 23.8144 98.6049 313.774 The mean price per share declined $2.45 over the four months �(di d ) 313.7742 4.73 n 1 14 df = n - = 14, t.05 = 1.761 d t.05 sd n = 2.45 �1.761 2.45 2.15 c 4.73 15 ($.30 to $4.60) We are 90% confident that the population mean price per share has decreased between $.30 and $4.60 over the four month period �xi 460.94 x $30.73 Sample mean price per share January 1: n 15 Percentage decrease over the months: d 43 a 2.45 (100) 8% 30.73 Mean price per share December 31, 2009 = $30.73(.92)(.92)(.92) = $23.93 This is a decline of $30.73 – 23.93 = $6.80 per share for the year p1 = population proportion for men p2 = population proportion for women H0: p1 p2 = 0 10 23 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 Ha: p1 p2 0 b p1 = 248/800 = .31 p2 = 156/600 = .26 c p n1 p1 n2 p2 800(.31) 600(.26) .2886 n1 n2 800 600 p1 p2 z 1 p 1 p n1 n2 (.31 26) 2886 2886 800 600 2.04 pvalue = 2(1.0000 .9793) = .0414 pvalue .05, reject H0. Conclude the population proportions are not equal. The proportion is higher for men d p1 p2 z.025 p1 (1 p1 ) p2 (1 p2 ) n1 n2 (.31 26) 1.96 31(1 31) 26(1 26) 800 600 05 .0475 Margin of Error = .0475 95% Confidence Interval (.0025 to .0975) 44 a p1 = 76/400 = .19 p2 = 90/900 = .10 p n1 p1 n2 p2 76 90 .1277 n1 n2 400 900 p1 p2 z 1 p 1 p n1 n2 19 10 1277 1277 400 900 4.49 pvalue 0 Reject H0; there is a difference between claim rates b p1 p2 z.025 p1 (1 p1 ) p2 (1 p2 ) n1 n2 10 24 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Statistical Inference About Means and Proportions with Two Populations 19 10 1.96 19(1 19) 10(1 10) 400 900 09 .0432 (.0468 to .1332) Claim rates are higher for single males p1 = 9/142 = .0634 45 p2 = 5/268 = .0187 p n1 p1 n2 p2 95 .0341 n1 n2 142 268 p1 p2 z 1 p 1 p n1 n2 0634 0187 0341 0341 142 268 2.37 pvalue = 2(1.0000 .9911) = .0178 pvalue .02, reject H0. There is a significant difference in drug resistance between the two states. New Jersey has the higher drug resistance rate 46. a March, 2007: p1 = 70/200 = .35 March, 2008: p2 = 70/150 = .47 b p2 p1 47 35 12 s p1 p2 35(1 35) 47(1 47) 0529 200 150 Confidence interval: .12 1.96(.0529) or .12 .1037 (.0163 to .2237) c 47. Since the confidence interval in part (b) does not include 0, I would conclude that occupancy rates are higher in the first week of March, 2008 than in the first week of March, 2007. On the basis of this I would expect occupancy rates to be higher for March, 2008 than for March, 2007 p1 276 Most recent week p2 487 One Week Ago p3 397 One Month Ago a Point estimate = p1 p2 276 487 .211 Margin of error: z.025 p1 (1 p1 ) p2 (1 p2 ) 276(1 276) 487(1 487) 1.96 085 n1 n2 240 240 10 25 © 2010 Cengage Learning All Rights Reserved May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part Chapter 10 95% confidence interval: .211 ± .085 (.296, .126) b H0: p1 – p3 ≥ 0 Ha: p1 – p3