exam2f09_key

exam2f09_key - Fall 2009 STATISTICS 401C Examination 2 (100...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 2
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 4
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Fall 2009 STATISTICS 401C Examination 2 (100 points) Name NOTE: Please show all work to obtain full credit. 1. Trace metals in drinking water affect the flavor and an unusually high concentration can pose a health hazard. Ten pairs of data were taken measuring zinc concentration in bottom water and surface water from various locations of a stream. Do the data suggest that the true average concentration of zinc in the bottom water exceeds that of surface water? The data are given below aggregated: Location Bottom Surface Difference cl 1 .430 .415 .015 2 .266 .238 .028 3 .567 .390 .177 4 .531 .610 -.079 5 .707 .605 .102 6 .716 .663 .053 7 .651 .632 .019 8 .589 .523 .066 9 .469 .411 .058 10 .723 .612 .111 Ed = .55 2ch = .072194 Let W = abattom — usurface be the mean difference in zinc concentration of the two populations and assume that the differences dz- have an approximately Normal distribution. (a) (10) Compute a t—statistic to test the research hypothesis that the mean zinc concentration in the bottom water exceeds that of surface water. State the null and alternative hypothesis in terms of ,ud. Compute an approximate p—value and make the decision using oz = 0.05. go m. Illa/«45>o Ho: M A; ‘__ 472/434 “Mgr/(0 __ mot/{A 7 (b) (10) Construct a 90% confidence interval for ad. Use this interval to test the hypothesis in part (a), explaining how you arrived at your conclusion. What is the (Jr—level of this test? 9 m ~——~ . A 10” C'L ' d If ewes '76% ‘0'” v be: :1: T) (momajarwva) 99mg 0 a m Ith w at». xtth We veg/“eat” )‘flL WM/wféfl's mug" 01:05 2. Many people purchase sport utility vehicles (SUV’s) because they think they are sturdier and hence'saier than regular cars. However, data have indicated that the costs of repairs for SUVs are higher than for midsize cars when both vehicles are in an accident. To verify this observation, a random sample of 9 new SUVs and 8 midsize cars are tested for front impact resistance. The amounts of damage (in hundreds of dollars) to the vehicles when crashed at 20 mph head—on into a stationary barrier are recorded below: Vehicle Damage (in $100’s) g SUV 14.25 24.47 18.15 15.17 27.48 16.42 29.56 12.33 21.54 9 19.93 37.6349 Midsize 11.95 15.42 13.27 9.87 18.12 10.36 12.65 21.25 8 14.11 15.4741 Let #1 and 11.2 represent mean cost of repair for the two types of vehicles, respectively. ‘ (a) (10) Just by looking at the sample statistics, can you tell if the assumption of equal population variances is plausible or not? Explain. Perform a statistical test using a =' .05 to verify this assumption. State the null and alternative hypotheses and the rejection region clearly. 2 - a r. _l.. . new “ Et“* .5: “‘ '07—3’3772 rings/7 g. 4,620 ’17 Kg, F <1?" mrF7%% (b) (10) State and test the appropriate hypotheses to determine if the mean repair cost for SUVS was higher. Use o4 = .05 to make your decision. Mot/Ac’fla <0 m. «liar/«.790 A“ : Qua) Afar-(wro/sfz H37~éavj+7W<§o4¢7fl£g7wg k ’VLI-i- 91,—2— l5" 2:; AP -—= 5122543 A], {Ea-.157, .2537 “QQ. ‘6 7 6,05, ,5 Ate. 6-71.75? ‘ ' ' *7 %m.r fa 2-5 m ML RR. and its/.113 4190(205' (c) (10) Construct a 90% confidence interval for m — ,ug. Test the research hypothesis that the repair cost for SUVs is larger by $1000 on tl_ie_average, using this confidence interval. 702’ CI Hy #702: %,—?,ifi%)yp'/‘plm it“). gas/452»! . (Wag-x442) .2: #753 22537 5.82. :l: 4.45 (£37 / 0.27) 4431/41“/AJ<IO m. ,fll— 2>lO ! r V <s>maa 10 73 (m %s ?7’I’/?~/-um€,) we ‘éw/ 42’ 74m 3. A research engineer at an electric utility is investigating the use of a Windmill to generate electricity. He has collected data on the Wind velocity and the corresponding DC output from his Windmill: Wind Velocity (mph) DC Output (m) (y) 5.0 1.6 6.0 1.8 3.4 1.1 2.7 0.5 10.0 2.2 9.6 2.3 8.2 2.2 3.0 0.7 5.5 1.6 7.0 1.9 8.8 2.1 9.1 2.3 2.7 0.7 4.1 1.2 Some summary statistics are: n: 14 23331 =85.1 Zyi 222.2 Zr? = 611.85 2y? = 40.52 Exiyi = 156.43 (a) (8) Fit a linear regression y = ,80 + fll a; + e of DC output on the Wind velocity using the above data. State your least squares grediction equation. 82.51 :2. 22% r. /h :2 AME”: "€95.1f/l’1 :: 44154357 337 a :W-v Ex?" :- IS’éJ/Ds -~ @§.I)sz.,z)/H_ zil~$€fl§7l A?" ____ so? km: atrial/(#54357 = 0.2171, A ~ A " z - (1% a: U —' , a? :2 _Q2273.I)(£7‘%L : &.2&7¢él Preaér‘cfim 9 .2 0.20%; .+ 0.227921% (b) (7) According to your fitted model, What is the average increase in DC output associated with a 5 mph increase in wind speed? Must show work. AWfé Warfare 4’”, LDC am‘lawe“ 4}» I 451mg.th 407‘ s ~.= 5-2272] WM MW [IA/W498 L'h/ 35C Emwu AMMW 2M Mhag S/aeec/ : 0427.21 )(5 (c) (8) Fill in the analysis of variance table for the regression below. What is the estimate of the error variance 0?? Compute the F—statistic and use the F table to test H o : ,61 = 0 vs. Ha : £31 aé 0. Use a: = .05 and show work. Source d.f. SS MS F Regression ( "fjfiflQ— Lfvgé’le? I 34/, 5 Error UL 0, #3251}, 0. 03é2& Total 13 15,3 ,7 I 2‘12“ (1%)L/m: %-§2~Q2.2)1//Lf .2 $13171 s :2 334213 2 9:34 New ’- ("2/ 'WSYOL/r’r51357/ :2 Lame F =2 4.75 R. R. 13.7 “MS '06)()I2. 4 Q56: LL, 09 0(2-05 L A 0.9— : A 2 M85: 47.03ng (d) (7) Compute the estimated standard error of ,31 (must give this first). Use it to compute a 95% confidence interval for ,81. Use this interval to test H0 : ,51 S 0 vs. Ha : ,61 > 0 (i.e., that the slope is positive). AF r; u—gé‘éz“ :: :1 0.0/‘fé 1+ ' ~95 KIWI-ream *0 2— I x t A 6150/0 <11" «Gr {5: 1 (*1 it fialQle ' l3 = @272 i ; IMXO'OIW’ 2': 0435/ 0.277 §1hc¢ 0 (15 M” [WC/arid .454; Men's M +9224”, Hi: 62/6— 04: e025. (e) (8) Estimate the mean DC output E(y) for periods when the wind speed is 8 mph. Construct a 95% confidence interval for this mean. 95 ,g 2. 8 ‘3 .— grga4él+ 9.2271/X9 : 2.022. ’5 *— ?SZ CI «95+ 5(3) e6, X129 A 1:13 X/Se'f’t ’5 VOZQ)I2. ‘ I weave)“ 2.022 1 2.176? x "WOEX 72; '* 9%«3635‘7 W '138' ([,;}g47) [1.19) (f) (6) Use above interval to say if the data support the conjecture that the mean DC output greater than 2 is achievable when the wind speed is 8 mph? (Use the interval to perform a test of appropriate hypotheses to answer this question. #0? fl”) <2 L“- 4‘3‘3 N3.) 7 2 ghu 2 L’s Nu m M atlas;ch ) 7J1?» 7’7) £4: Ci/é (X z: ‘02?» W 5 (g) (6) This question concerns the 3 plots attached (see next page). Identify the plot (or plots) you would use to answer each of the questions about model assumptions stated below. Give your answer to each question justifying your answer using the plot or plot(s). An yes/ no answer alone will not earn any points. Questions Plot(s) Do the errors(e’s) have a A normal distribution? Your answer Is the variance (0?) B C constant for all X’s? / Tdnspwmt 0% Me {fin 44L ‘j—éfltefl/‘ZZM "5 Crustal/kl” ’QT JL‘W Wm ML 76~W>cck7 514413124? {WWW Wu; 1’5 Crustal/6" nemsg ad’s, Is the straight line model b adequate? ) ...
View Full Document

Page1 / 6

exam2f09_key - Fall 2009 STATISTICS 401C Examination 2 (100...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online