HP-340 Fall 2016 Extra Credit Instructions - PLEASE READ This extra credit assignment is an opportunity for each of you to improve upon your midterm score. The score you get on the extra credit will be scaled and added to your midterm score. In other words, the total number of points for the midterm will remain the same, but the score you achieve will be the score you actually got, plus the scaled extra credit points. The scaling of the extra credit points will be done such that 1) those who received a grade of \"C\" or above will earn up to an additional 5% and 2) those who received a grade of below a \"C\" will gain a bit more. Also, please note the following rules regarding the extra credit assignment: 1. The assignment is take-home and is due one week after the assignment date. 2. Extensions to the deadline for the extra credit will only be provided with adequate documented excuse, e.g., illness, death in the family, etc. 3. You are to work independently. That means you cannot consult with classmates, friends, family, or other students regarding the content of the assignment. You may refer to your notes, textbook, or other printed or online materials. 4. You may turn in your extra credit assignment digitally online or as a hard copy. If you choose the former, please create a single digital file and upload. The format of the digital file is up to you. You are on the honor system, so we will assume you have followed the above guidelines. Any evidence to the contrary will result in no points and, depending on the severity of the infraction, reporting to the office of Student Judicial Affairs and Community Standards for further adjudication. GOOD LUCK! HP340: Fall 2016 Mid-Semester Extra Credit (100 points) Name: __________________________ Directions: Please answer the questions on the provided sheets using the space provided. Show all of your work. If you need more space, please use the back of the pages and indicate the problem to which the work corresponds. You are on the honor system and are to work independently. That means, you cannot consult with your classmates or other students. The following questions are worth 2.5 points each 1. A nominal scale is used for: a) b) c) d) e) 2. All categorical data Discrete data with categories that do not follow a natural sequence Continuous data that follow a natural sequence Discrete data with categories that follow a natural sequence Quantitative data One useful summary of a set of data is provided by the mean and standard deviation. Which of the following is true? a) The mean is the middle value (50th percentile) and the standard deviation is the difference between the 90th and the 10th percentiles b) The mean is the arithmetic average and the standard deviation measures the extent to which observation vary about or are different from the mean c) The mean is the most frequently occurring observation and the standard deviation is the difference between the largest and smallest observations d) None of the above 3. The height, in centimeters, of 2nd year medical students was recorded and the variance of these heights was calculated. The unit of measurement for the calculated variance is: a) b) c) d) e) centimeters Centimeters (Centimeters)2 No units None of the above 4. Consider the following set of cholesterol levels in mg/dl: Set 1: 200, 210, 190, 220, 195 Set 2: 210, 170, 180, 235, 240 The standard deviation of Set 1 is: a) b) c) d) e) 5. The same as that of Set 2 < Set 2 > Set 2 Equal to the mean of Set 2 Cannot be determined from the information provided The following cumulative plot was derived from the pulse of 1,000 students Which of the following is false? a) b) c) d) e) 6. The range of the distribution is 60 to 100 beats/min The mode of the distribution is 100 beats/min The median of the distribution is 77 beats/min 92% of the values are <90 beatsmin 94% of the values are>65 beats/min A certain operation has a fatality rate of 30%. If this operation is performed independently on three different patients, what is the probability that all three operations will be fatal? a) b) c) d) e) 0.09 0.90 0.009 0.027 0.27 7. A person randomly selected from a population of interest has a probability of 0.01 of having disease D. The probability of symptom S, which may require a diagnostic test to evaluate its presence or absence, is 0.7 in a person known to have D. The probability of S in a person known not to have D is 0.02. A patient from this population is found to have symptom S. What is the probability this patient has disease D? a) b) c) d) e) 8. All of the following are characteristics of the family of normal distributions except: a) b) c) d) e) 9. Positively skewed Mean equal to the median Median equal to the mode Mean equal to the mode Symmetric A 99% confidence interval for a mean a) b) c) d) e) 10. 0.01 0.02 0.26 0.53 0.95 Is wider than a 95% confidence interval Is narrower than a 95% confidence interval Includes the mean with 99% probability Excludes the mean with 99% probability Is obtained as the sample average plus two standard deviations An investigator wishes to estimate the mean cholesterol level in a pediatric population. He decides, on the basis of a small sample, to calculate the 95% confidence interval for the population mean. Since the data appear to be normally distributed, the appropriate statistical distribution to use in calculating the confidence interval is: a) b) c) d) e) Normal distribution t-distribution Uniform distribution Binomial distribution z-distribution 11. The following SPSS output summarizes midterm exam scores for a class. a) Provide the missing information for A, B, and C in the output based on the information provided. (5 points) A B C b) Based on the output, determine whether the data are normally distributed or not, describe how you came to your conclusion, then report the appropriate descriptive statistics to summarize the distribution. (5 points) 12. Assume the information provided in the SPSS output for Question 11 represents population-based values. You have now sampled from the population the 12 midterm scores shown below: 86.96, 76.09, 92.39, 75.00, 91.30, 102.17, 86.96, 98.91, 98.91, 55.43, 75.00, 73.91 a) Compute summary statistics for this sample (assume the data are normally distributed) (5 points) b) Compute the 90% confidence interval for the mean (5 points) c) Test the hypothesis that the average midterm score from the sample is less than the 75th percentile from the population using an -level of 0.01 i. State the null and alternative hypotheses (2 points) ii. Calculate the appropriate test statistic (5 points) iii. State your conclusions. (5 points) 13. You draw another sample from the population, perform a one-sample t-test and get the following SPSS output. a) Compute the missing values from the SPSS output. There are a total of 6 values you must determine. (12 points) b) Assuming a two-sided alternative, what are the null and alternative hypotheses for this analysis? (2 points) c) What conclusion do you make based on the results of the analysis? (5 points) d) What if the hypothesis had been stated as a one-sided alternative? Ignoring the direction of the alternative, would this result still be significant? What would be the pvalue? (2 points) 14. The distribution of grades for the midterm was as follows: Grading Scale A 93 - 100+ C 73 - 76 A- 90 - 92 C- 70 - 72 B+ 87 - 89 D+ 67 - 69 B 83 - 86 D 63 - 66 BC+ 80 - 82 77 - 79 DF 60 - 62 <60 points)