midterm1_key - ph 141 summer 2010 midterm 1 NAME k F)1 Show...

Info icon This preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Image of page 1

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

View Full Document Right Arrow Icon
Image of page 2
Image of page 3

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

View Full Document Right Arrow Icon
Image of page 4
Image of page 5

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

View Full Document Right Arrow Icon
Image of page 6
Image of page 7

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

View Full Document Right Arrow Icon
Image of page 8
Image of page 9

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

View Full Document Right Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ph 141 summer 2010 midterm 1 NAME k F- )1 Show all work on these sheets. Total 100 points. Working time is 2 hours. Part 1. 20 points Afier a person with dementia has died, the diagnosis of Alzheimer's disease can be made definitively from an autopsy, but it is extremely difficult to diagnose Alzheimer's disease for an elderly person with dementia. Suppose that researchers are assessing a new test to assist clinicians in their assessment of elderly patients with dementia. When the test was done for a sample of patients for whom the autopsy diagnosis was available, the test gave the following results: test + test — Alzheimer's disease 800 _ 100 900 other dementia ‘ 150 1350 1500 1. ( 4 points) Use these data to find the following probabilities probability the test is positive given the person really has Alzheimer's disease 900 900 = .‘3‘? probability the test is negative given the person really has another dementia I350 : filo '50“ Suppose the prevalence of Alzheimer's among this population of elderly persons with dementia is thought to be .40 Using this prevalence and the information given above, set up a tree diagram on the next page to help you answer the following questions: (16 points) What is the probability of Alzheimer's disease given the test is positive? N 9* T P A C: E What is the probability of Alzheimer's disease given the test is negative? .Ho 0 “0 AV" °THER '%'*/\“ .VVO "TEST-i- 159; - TEST 1' TEST- PL1E$1 e) —. P (am. Ann TEST +) ;. P‘Mnm AM“ ‘EST 0-) — Puma.) Pug“ u an.) 4- p LIN-tan) p “I“ * I ovum) : .40 x .99 + .b0 u do : ’35" * .0430 3 .HH. 80 PS TgsT -) ._ ‘- .th :. .‘SfiH PLRL‘L ANb TEST +) D‘Ak1\ TEST +\ M“ PL‘TEST-o) 7' .Ho 1531 — A 35L. ‘ ‘_“”——' = .95; 'H" .Hna 'PCAL‘LI 1551— .) -: PU‘L‘L Ann TE51 .) PLTES‘r-3 7' M _. .OHI-l ’ 1 .015 .ssq .SQH Part 2. 20 points A club has 10 members 1. (5 points) How many ways can they appoint a committee of 6 members to plan an event? ‘ 3 ('0) = —'°—" : '“WS‘WU _ toxxszA'I ‘9 1155’. India: (a! ‘ “43:2 1 “’11! = 1:0 For the next 3 questions, suppose that the club consists of 5 men and 5 women. 2. (6 points) How many ways can they appoint a committee of 6 members so that there are 3 men and 3 women? MWLT‘PL|QRT\ON RuLE '. NuMB‘EK oF ways ‘ Nuneea 0F wnws *9 Pick MEN 7° pick wo MEN 5 t s! (g) " ( 3) 5' t 3 113', 1'. 3! Si“ * sxu 0 : ’1. 7,. l ’( M) NO 3. ( 4 points) If a committee of 6 members is appointed at random, what is the probability that it consists of an equal number of men and women? '00 _ '0 ’LIO 1| : AFN. ‘T IS HWPEKGEoMETam Bur ensma To be 3" RgfisonKs ) am: Tue kuSwEnsTo QMESTDONS I Am: '1. 4. (5 points ) What is the probability that a randomly appointed committee of 6 has no women? 0 THERE (we WU; 5 Man To LHooSE men MosT BE AT LEAST I \NOMRLJZ Part 3. 25 points Is there an association between a mother's smoking during pregnancy and premature birth? The following data were obtained from a cross-sectional study of 1, 300 mothers: premature birth full-term birth smoked throughout pregnancy 45 355 | 400 I did not smoke at all | during pregnancy 35 865 | 900 80 1220 I 1300 1. (4 points) Complete the following table of expected cell counts under the assumption that there is no association between smoking during pregnancy and premature birth. Give the details of all the calculations you need to make and explain your reasoning: premature birth full-term birth 0k smoked throughout ro’ F H41) 1 . pregnancy ‘1 L 375.4 400 E “K 121: did not smoke at all “L‘- "°° ”15 during pregnancy 55-“ 844.6 900 [31 sugmnume 1f ‘tou 80 1220 1300 ‘ 6x9~A\N P(PREMA1\;.P.E) '3 $9 = aOLIS . Rmsoumtyl 1300 ‘ EM mom SMoueRS : .0515! Hoo - “M, E19 Loom NoN—SMM<ERS ’- -°"'5" (‘00 7' 55'“ 09‘ (3° ‘ 1”" o a 30 I q 00 (300 2. (4 points) Do these data satisfy the conditions required to use the )8 distribution to find the P value? Explain why or Why not — do not actually calculate any test statistic or P value! fies ! ML 619 can. Loums 7; 5 ’THE Con‘nou For: \(1 Fort a 111 Tami 3. (4 points) What is the relative risk of premature birth? N PREMATUKENSMokER) L‘s/“W .II’AS - PtPKEMA-TuRE ‘ Nun SMDKERB 35/5100 .038? RR: 4. (4 points) The investigators carried out a )6 test and obtained )6 = 25.98 What are thedegrees offreedom? K NULMBER °F hws' 0 1‘ ("“MBER 0‘: (”mums ' I) L 1 — n ‘ * t 1 - i) I 3‘ I ' | What is the P value? (It is a good idea to report the P value as an inequality.) 1ABI-E F, ta” mow P’\ Y} W ‘1_ta\|NbED) = -°°°5 P 1,0005 5. (5 points) Do the investigators have evidence that there is an association between a mother's smoking during pregnancy and premature birth? Use the P value to justify your answer. Write a summary sentence that explains your conclusion in words. n: “haze Rearw is No nssoatATIoM \N "THE POPLLLA‘HON, l“E335 fun» 3 \N 10,000 SH HPLES C’NE "Y,“ > |1J1 So, Assumwe No fissouA'noN) ouK SAMPLE ham WeUth BE VEM RRRE. we coNCLubE THAT name [5 AN Assoowrrwu BETWEEN SMowMG THRoucHouu Pkécktauc‘t PW! l’nEMATung man-t. 6. (4 points) Do these data prove that a mother's smoking during pregnancy causes premature birth? Explain your reasoning. (This question requires thinking, not calculation.) 1m; ts OSSERVA'HOHRL brunt) So 1HE answer; is NO- womeu wuq SMOKE THkonHwT PREGNANOY “9“ “”1““ FROM WNW“ WHO be fit“ SMOKE A1 ALL burUNG eneeNAuq. (uneven >131) ALCOHOL °°NSKHPTIOH)..-) PERHaPs LAB E‘LPEPAMEHTS um“ SHELL MHMMALS, \N WINCH RBMMM RsstlsNMENT TO SMOkE exvosuac IS e-rchL, tout-b ”.0me SOME CqusAL EVlhEMLE . Part 4. 15 points You are asked to assist an investigator who is working with a simple random sample of 400 men age 40 to 49. You have calculated the body mass index (BMI) for these men and created a box plot. The investigators have asked you to explain the plot and make some suggestions for summarizing the data. minimum 1 6.9 25th percentile 22.9 median 25.1 75th percentile 27.9 maximum 57.6 Body Mass index 41) 5 0 6 0 3‘0 20 Using the summary and the boxplot, answer the following questions. 1. (12 points) Explain clearly how stata determined which points were to be plotted as outliers in the boxplot. Give specific numerical details, not just a general outline. IQR‘ 1” - 11.“ Wes-Q.) 5 1.51ch = “1.5 “975K FENCE .3 Q3 4' LSIQR 7' 1".q+‘1‘5 ‘. 35'“ BM! VALuES 7 35A! W|LL BE PLO‘T‘TEB As no LAN.) ukuts (Tums A115 m LERST a!) N°1E rHé Mom ts SM, LowER Fence. : (1‘ - LEIQK = qua-$5 : lS-H km \sALuEs ‘ ISH \mu. BE none» as mom-re» cmLLEs we Mm IS ”9.5!, So 1HERERRE N0 ouruens AT THE Low Eu» N: THE mnmuunon. Tue Lauren wmgkgg EHDS AT Iefl 2. (3 points) Based on what you have learned in class, do you think the assumption that the distribution of bmi for this population is approximately a normal curve? Why or why not? ‘WE MEMAN ‘5 “Emir Hethwa‘; Bewweeu 0‘ an» Q3) SiucE M-Q‘: '15.! - 11.7 = 1.7. M» 023- M'— 2cm - 15il= 1.8 Tu: UPPER WMSKER. \S A Bn’ mum-.1 THAN THE L°WER WMSKER nus lS No‘r so 151RABLE! Ho waven, we Saw 1HAT THE. UPPER FENCE Fon- ~n-u; NORMA!- cums um; A 1. scoRE 3F 1.10, so Tu‘m pgomucm A, Hm” aunt] is ABM»? .0035 WE Hem; T00 Mam; Mammals FOR 1HE BIST‘MBvTIoN To BE Rouenw NOflMRL cum; ! [8m °F 5'14, lS est-mama \F THE ”“0“ WE“ ‘9 FE“ Ta“) nus ooaQeSPoubs To A “Just” OF HIS vouuns PM A to Pct-r mn- Pek 3°" W“ WW,” 2‘00 PouMDS) 13m: qoq QOME‘UMis \NVESTKsATORS L‘MiT 3669:. OF ANALV‘S‘S «o excuse New EMKEM‘: \mwns — “we“ Maria). ‘53“‘-] Part 5. 20 points Suppose that you are in charge of warranties for a manufacturer of batteries for an implanted medical device. From long-term quality studies, you know that the distribution of lifetimes for your batteries is very close to the normal curve, with a mean of 60 months (5 years) and a standard deviation of 8 months. 1. (6 points) What proportion of your batteries last longer than 75 months? 5h; fis—eO, = lg, / ‘4‘: 6' Q g ‘ L815 || so 15 0k To use :31 0R I539 on INTERPOLATE Aaom \- .qlo‘le : .0309 I815 2. (6 points) What is the 90th percentile of the distribution of battery lifetimes? .‘iooo ‘ \ 1.19 - 8 1 was” a X' (a0 FOR 1= [.18 (pol-Lassa 3 x mun 10 rue LEF1 (.o+ norm = X 10")“ MW”: IS - 2 q 1 7 3. (8 points) Suppose your research department wants to improve the quality and consistency of the manufacturing process. They have been able to modify the process so that the mean is now 67.5 months. (The consistency will be measured by the standard deviation, the spread of the battery lives around the new mean.) If they want 99% of the batteries to last at least 75 months, what standard deviation do they have to achieve? nus ts No1- Pm A'rteMeT To Tuck ‘wu - vr was \NSTfluc‘foR eaaoaf 1; THE Mean is 51.5) mat-r- 5F iHE Garrett‘s: mm. LAST LESS Tm‘” v1.5 Mourns THE caKREcT 9: Fall .qcioo [s RBaUT 1.33 0-: 3.1 MoNTHS womb (“we 9‘1")» 0F TREH L685 mm: '15 MONTHS, Bur TMA1'S Not A user-Lu. Qucs‘nou ...
View Full Document

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern