Name: key UnrviD: EXAM II - STAT 226 F FALL 2009 For B Show all your work AND WRITE COMPLETE ANSWERS. PLEASE WRITE AS CLEARLY AND NEATLY AS POSSIBLE. FEEL FREE TO ASK FOR MORE PAPER IF YOU NEED MORE SPAcE. GOOD LUCK 1. ‘TRUE or FALSE: Identify which of the following are valid statements, (2) T@For a 95% confidence interval for j, we are 95% confident that the interval contains the sample mean, (b) TEA larger p-value is stronger evidence against the null hypothesis. (0) DEE everything else is held constant, increasing the sample size will increase the margin of error of a confidence interval. (@ CDF If we take a large enough sample size, any difference between the sample mean % and the ‘mall hypothesis value of j, io, can be made to be statistically significant, whether or not the difference is actually practically significant. (© ©F For populations “farther from normality,” a larger sample size n is necessary for the ) sampling distribution of Z to be normally distributed. (8) T@)Ater a 95% confidence interval for the population mean 1 is constructed, the interval has ‘a 95% chance of containing (s) @ F 95% confidence means that if repeated samples are taken and corresponding confidence intervals are constructed, in the long run, 95% of the intervals will contain (i) T@A parameter is used to estimate a statistic. () TH Toking larger samples always reduces the bias of a statistic in estimating a population parameter. (3) T@)An observational study is a study for which researchers simply observe subjects for different treatments. The treatments are randomly assigned by the researchers. 2. Consider the following cases. i, The population is non-normal. The saniple size n is small. fi, The population is non-normal. The sample size n is large. iii, The population is normally distributed. The sample size n is small. iv. The population is normally distributed. The sample size n is large. (a) Write ALD cases in which the sampling distribution of # is normal. Ut, (it Lv (b) Write ALL cases in which the Central Limit Theorem is used to conclude that the sampling distribution of # is normal. [L———Exam II star 226 FoRM B PAGE 2 3. Choose the situation in which a Type-I Error occurs. (a) We fail to reject Ho when Ho is false fe reject Hy when Hg is false. (€). We fail to reject: Ho when Ho is true. WW reject Ho when Ho is true 4. The Crown Bottling Company has just installed a new bottling process that will fill 16-o7 bottles of the popular Crown Classic Cola soft drink. Both overfiling and underfilling bottles are undesirable: Underflling leads to customer complaints and overfilling costs the company considerable money. In order to verify that the filler is set up correctly, the company wishes to see whether the mean bottle fill, 4, is close to the target fill of 16 ounces. To this end, a random sample of 49 filled bottles is selected from the output of a test filler run, which yields a sample mean of 16.03 oz. It is known that the standard deviation of the fll distribution is 0.1 os. Test whether the mean bottle fil is the desired 16 ounces at the a = 0.02 significance level (a) State the null and alternative hypotheses, Repro Heel (b) Compute the value of the test statistic. = lee 3 eS MTR (©) Sketch a standard normal curve and shade the area under the curve that corresponds to your p-value, Calculate this p-value 2(.0144) =,035% (a) State your decision and briefly explain how you came to it in terms of the relevant quantities. prvslucrsa, Gal bh ted Hy (€) Write your conclusion within the context of the problem. Thure is no statistically igsbiant” evidence ot He &=,.00 (uel to conctoole that nears battle RI ciffea From (bre.Exam IT sar 226 FORM B PAGE 3 5. ‘The thickness (in millimeters) of the coating applied to disk drives is a characteristic that determines the usefulness of the product. When no unusual circumstances are present, the thickness has a normal distribution with a mean of 3 mm and a standard deviation of 0.05 mm. Suppose that: the process will be monitored by selecting a random sample of 16 drives from each shift’s production and determining Z, the mean coating thickness for the sample. (a) Find the mean jis and standard deviation os of the sampling distribution of Z. (b) Is the sampling distribution of # normal? (Circle one Ys or No. (0) Is the Central Limit Theorem used to determine the answer to (b)? (Circle one) Yes or(NO) (d) Find the probability, if possible, that a single disk drive has a coating with thickness greater than 3,03 mm. If it is not possible, simply write not possible. P(x>408)= Ple> *982)= Gero.) = 1-425} =, 2743 (e) Find the probability, if possible, that a random sample of 16 drives has mean coating thickness greater than 3.03 mm. If it is not possible, simply write not possible. PlK3.03) = Pz > B22) = Plera.d)=\— 47 = DOKL (8) When no unusual circumstances are present, we expect Z to be within 3cy of 3 mm, the desired value. An # value farther from 3 than Ses is interpreted as an indication of a problem that needs attention. Compute the two numbers represented by 3 + 303. (2.615 , 3.0375) (@) Referring to part 5f, what is the probability that a sample mean will be outside the range between the two numbers defined by 3+ cg, just by chance (i.e. when there are no unusual circumstances)? 3 o(x>30a7s) = (2? a) 2flera}e.00l3 0 (K< 3B .AWIS) = P (2-3) = 0013Exam II star 226 Form B PAGE 4 (h) Suppose that a machine used to apply the coating is out of adjustment, resulting in a new mean coating thickness of : = 3.05 mm (we will assume the standard deviation remains the same). What is the probability that a problem will be detected when the next snp is taken? (Hint: ‘This will occur if # > 3 +302 or & < 3—8cg under the new distribution of #.) P(K 73.0346) = Play SDFESAIOS) - Yar -)= |, 158F=9413 (Ks 29018) = %<-B=0. [a \ 6. A management consulting firm has installed a new computer-based, electronic billing system in a Hamilton, Ohio, trucking company. ‘The mean payment time using the trucking company’s old billing system was approximately equal to 39 days. In order to assess whether the mean payment, time, 4, using the new billing system is substantially less than 39 days, the consulting firm will use ‘a random sample of 45 payment times. ‘The mean of the sample of-65 payment times is 18.11 days and the standard deviation is 3.96 days. The sample size is large enough to assume that this is the population standard deviation. (a) Construct a 97% confidence interval for the mean payment time using the new billing system, BNE 244 SE ALE LIB * 2 (635, wan) (b) Assuming the relevant quantities are under your control, list two ways to reduce the width of the above interval. )) Oeerecse C 3) Decreare o 2) Tac (©) Give an interpretation for the confidence interval in part 6a within the context of the problem. We are TH conden” heck He maar porywaert Fin vsing the now billing systeun lies in-fle interval of (104, (118) (q) Ithe firm wanted to estimate the new mean payment time with a 97% confidence interval with a width of 1 day, how large of a sample would it have to collect? AA x loa (aay (22: w)sm95.4 7) 2% us as (©) Suppose we test the hypotheses Hy : = 39 vs. Hy : 1 < 99 at the a = 0.08 significance level to determine whether the mean payment decreased. Can the interval in part 6a be used to conduct this test? (Circle one) Y8s or(No.) maa,Exam II star 226 Form B PAGE 5 7. Financial guru Suze Orman preaches a common investing rule-of-thumb: “Take 100 minus your age, ‘and that percentage of your investments should be in stocks.” This adage communicates that younger | investors should invest more heavily in risky stocks, retirees should mostly stay away from stocks, and investors should reduce the percentage of stocks in their portfolio as they age. While stocks have larger variability than other investments, it is commonly accepted that stocks also have a higher | ‘mean return than other investments. Use the Law of Large Numbers to explain why this rule of ‘thumb suggests that young investors should put most of their money in stocks. See Gorm A soluhonr,