Fall 2012 Stat6800 Final Exam

Web Address of This Page

http://www.stat.wmich.edu/wang/680/2012FinalExam

Problem Description

A test prep company, Acme 4 Sure Pass, Unlimted, set up example tests for two types of tests, Test A and Test B. To evaluate how well the targeted potential customers will excel in these prep tests, the company had 200 evaluators in each of the six regions (a total of 1200 evaluators) tried on the tests. Each evaluator was asked to worked on both tests with 10 similar repetitions (20 points each) on each test. However, each evaluator may end up not finished some repetitions. A data set in plain text testEval.txt, accessible by SAS FILENAME URL statement, contain the outcomes from this study. It is a combined raw score book from 6 regions identified by column 1 (regions A through F). Column 2 contains evaluators' IDs (1 through 200 in each region). The next 10 columns are the respective outcomes from the 10 repetitions of Test A. The last 10 columns are the outcomes from the 10 repetitions of Test B. Your WIN will set a random seed so that the raw score data of a randomly selected region (from regions A to E) will be assigned to you to produce a summary report. The summary report for region F was carried out and presented in finalExamEgOutput.txt for your reference.

A SAS data set named raw will first be created for the region you are working on. This data set has columns named Evaluator, A1, A2, A3, A4, A5, A6, A7, A8, A9, A10, B1, B2, B3, B4, B5, B6, B7, B8, B9, and B10. This data set is then split into two data sets, testA and testB. Data set testA contains columns Evaluator, A1 through A10, and an additional column named a_ok which gives the number of repetitions of test A each evaluator had actually completed. Moreover, only observations in which 6 or more repetitions were completed will be kept in testA. Data set testB is similar except that it contains Evaluator, B1 through B10 and b_ok.

Each of these two new data sets will be updated with two additional variables added: variable xbar gives the mean score of the 10 repetitions, variable Category is then created based on the values of variable xbar:

  value of xbar      Category
  -------------      -------------
  [19,20]            Very High
  [17,19)            Somewhat High
  [15.5,17)          Moderate
  [0,15.5)           Low
  
Finally, these two data sets (only variables Evaluator, xbar and Category in each data set will be kept) are concatenated and interleaved to form the final data set named combined. An additional variable named test is created to indicate test types.

The final summary report will be produced using PROC REPORT on the combined data set.

You are provided a SAS Codes (FinalExam.sas) in which many coding errors occur. These errors could be You are to correct all errors. The SAS log generated from running your SAS codes is expected to be error free.

Program Submission

You are to submit SAS codes only through email and get a confirmation of receipt from the instructor before you leave. My email address is
jung-chao.wang@wmich.edu