STATISTICS 2023 NAME IN PRINT__________________________________ FINAL EXAM SIGNATURE IN INK_______________________________ SPRING 2009 CWID IN INK_____________________________________ FILL IN THE BLANK. Write the word or phrase from the list on the right that belongs in the blank. The words or phrases in this list may be used more than once or not at all. (Each blank 3 points each) 1. Confidence intervals are often constructed by adding and subtracting the ___________________________________ from the point estimate for the parameter. 2 A population _________________________________ is estimated with sample statistic that is used as point estimator. 3. A point estimate is not equal to the value of the parameter estimated so the _______________________________________ that is associated with the point estimator must always be considered. 4. A conclusion about a population based on observed data from a random sample is called a ______________________________________________ . 5. The statement assumed true and tested for validity in a hypothesis Standard error Test statistic Null hypothesis Alternative hypothesis Parameter Sample statistic Confidence interval Point estimate Bound of error Population Sample statistics Statistical inference Alpha value P-value Rejection region Critical value test is the _____________________________________________________ . 6. In a hypothesis test, the probability of observing data at least as extreme as the data observed is the ________________________________________________ of the test. 7. The statement that can be supported by data in a hypothesis test is the _____________________________________________________ . 8. When the null hypothesis is rejected based on certain data then the probability of error when the rejection decision is made is called the __________________________________ of the test. 9. A single number, which is a measure of relative standing, that is calculated from the data on which the validity of the null hypothesis is evaluated is called the ________________________________________ . 10. The _____________________________________ divides the distribution of the test statistic under a true null hypothesis into likely and unlikely values of the test statistic. STATISTICS 2023 FINAL EXAM SPRING 2009 STATE THE ANSWER. Write the answer on the line. PAGE TWO (3 points each) ___________________11. What is the P(Z< -.85) + P(Z>.52)? ___________________12. The number of stock trades in a random sample of 8 days is 346, 645, 435, 745, 867, 456, 851, and 879. What is the numerical value of the point estimate for the population mean number of stock trades per day based on this sample? ___________________13. The number of stock trades in a random sample of 8 days is 346, 645, 435, 745, 867, 456, 851, and 879. What is the numerical value of the point estimate for the population standard deviation of the number of stock trades per day based on this sample? Round your answer to two digits past the decimal. ___________________14. If a hypothesis test based on a large sample has a test statistic value of 0.75 and the researcher is trying to prove that the population mean is not equal to some stated value, what is the p-value of the hypothesis test? __________________ 15. If the p-value in a two tailed hypothesis test based on a z-test statistic is equal to 0.2542, what is the magnitude of the test statistic? ___________________16. In a right-tail hypothesis test based on a small sample of 14 observations the value of the test statistic must exceed what number for the researcher to reject the null hypothesis with only a 0.025 alpha value? ___________________17. If a researcher who is comparing the means of two populations is attempting to prove that the mean of population two is more than 70 units larger than the mean of population one what is the appropriate alternative hypothesis? ___________________18. Based on a sample of 18 observations the mean daily decline of a certain stock is 21.25 units; based on a sample of 16 observations the mean daily decline of a second stock is 14.45 units. What the is the numerical value of the point estimate for the difference between the mean daily change for these two stocks based on these two samples? ___________________19. If two samples of the same size produced variance estimates of 543 and 235, what is the numerical value of the pooled variance estimate based on these two samples? ___________________ 20. If a 95% confidence interval to estimate the difference between two population means is (-34.56, -56.22) then the hypothesis of equal population means would be rejected at the 5% alpha significance level? Answer: yes, no, maybe, or can’t tell. STATISTICS 2023 FINAL EXAM SPRING 2009 PAGE THREE STATE THE ANSWER. Write the answer on the line. (3 points each) Two types of accounting software were being compared in terms of the mean number of account audits that each type could complete in a set time period. For each type of software the number of account audits performed in a set time period was recorded for each of 100 time periods. The sample statistics for the numbers of account audits per time period for each type of accounting software are as follows. Software One n1=100 mean=7086 variance=1764 Software Two n2=100 mean=8763 variance=2704 ___________________21. What is the estimated standard error of the point estimate for the mean number of audits per time period for the first type of accounting software? ___________________22. What is the numerical value of the point estimate for the difference between the mean number of audits per time period for the two types of accounting software? ___________________23. What is the estimated standard error of the point estimate for the difference between the mean number of audits per time period for the two types of accounting software, if the population variances are not assumed equal? ___________________24. If the estimated standard error of the point estimate for the difference between the mean number of audits per time period for the two types of accounting software is 7 units what is the bound of error for a 95% confidence interval to estimate the difference between the mean number of audits per time period for the two types? ___________________25. A pooled variance estimate would probably not be used in this case due to not assuming equal variances, but if it were calculated what would be the numerical value of the pooled variance estimate based on these two samples? ___________________26. The observed test statistic in this case would have to exceed what magnitude for the data to indicate at the 1% significance level that the two types of accounting software do not result in equal mean number of audits in a set time period? STATISTICS 2023 FINAL EXAM SPRING 2009 PAGE FOUR LINEAR REGRESSION QUESTIONS. Write the answer on the line. (3 point each) The number of classes missed by students is used to predict their final grade. The bivariate data recorded below are number of classes missed (X) and class grade (Y). Five students were randomly sampled and the number of classes missed and their final grade in the class were recorded. Use this data to answer the following questions. X Y 1 99.5 2 80.5 3 62.2 5 50.1 8 39.8 __________________27. What is the numerical value of the corrected sum of squares for the y-variable based on the above data? __________________28. What is the least squares estimate of the slope in the linear regression equation to estimate the class grade from the number of classes missed? Round your answer to three digit past the decimal. __________________29. What is the least squares estimate of the y-intercept in the linear regression equation to estimate the class grade from the number of classes missed? Round your answer to one digit past the decimal. ________________________________30. Write the estimated regression equation to estimate the class grade from the number of classes missed. Use the estimates of the slope and y-intercept that you calculated in problems 28 and 29 above. __________________31. What is the numerical value of the estimated linear correlation between the two variables? Round your answer to three digits past the decimal. ANOTHER LINEAR REGRESSION QUESTION. The estimated linear regression equation below uses X=electricity cost to estimate Y=total manufacturing cost of a certain product. Use it to answer the remainder of the questions on this page. ^ y = 1,504 + 19.2x __________________32. When the electricity cost is $485 what is the least squares estimate for the total manufacturing cost of the product? __________________33. If the estimated standard error for the estimate of the slope is 6.4 what is the value of the test statistic to test whether the slope is equal to zero?