Practice Exam B

Description: The data `Evals` are gathered from end of semester student evaluations for a large sample of professors from a university. In addition, six students rate the professors’ physical appearance. The result is a data frame where each row contains a different professor and each column has information on the professor. Please load in the data by copy/pasting the relevant code below:

R: 

evals<-read.csv(“https://raw.githubusercontent.com/nazzstat/AppliedData/master/PracticeData/Evals.csv”, stringsAsFactors = FALSE)

SAS:

LIBNAME myFolder “P:\QAC\QAC201\PracticeData”;

data new; set myFolder.Evals; run;

Stata:

use “https://github.com/nazzstat/AppliedData/blob/master/PracticeData/Evals.dta?raw=true”, clear

VariableDescription
ScoreAverage professor evaluation score (1) very unsatisfactory – (5) excellent
RankRank of professor, (1) teaching, (2) tenure track, (3) tenured
EthnicityMinority (1), Not Minority (0)
GenderFemale (0), Male (1)
AgeAge of professor
bty_r1 Beauty rating of professor from 1st semester female: (1) lowest – (10) highest.
bty_r2 Beauty rating of professor from 3rd semester female: (1) lowest – (10) highest.
bty_r3 Beauty rating of professor from 7th semester female: (1) lowest – (10) highest.
bty_r4 Beauty rating of professor from 1st semester male: (1) lowest – (10) highest.
bty_r5 Beauty rating of professor from 3rd semester male: (1) lowest – (10) highest.
bty_r6 Beauty rating of professor from 7th semester male: (1) lowest – (10) highest.

Instructions:

  1. Call in the data set.
  2. Make an appropriate plot that describes the distribution of the scores. Answer Questions #1 and #2 on moodle.
  3. Make a frequency table with cumulative percents of bty_r1. Answer Questions #3 and #4.
  4. Make a frequency table with cumulative percents of bty_r4. Answer Questions #5 and #6.
  5. Create a new variable bty_total that sums up the beauty scores for each professor.
  6. Evaluate the relationship between bty_total and score using the pearson correlation test. Answer Questions #7 and #8.
  7. Find the mean evaluation score based on gender. Answer Question #9.
  8. Determine whether there is a significant relationship between score and gender. Answer Question #10.
  9. Create a new categorical variable junior from the quantitative variable age by dummy coding professors under 38 years old with a 1 (junior faculty), and professors at least 38 years old with a 0 (not junior faculty).
  10. Determine what percent of faculty is considered junior and not junior based on your new variable. Answer Question #11.
  11. Determine whether there is a significant relationship between gender and rank. Answer Questions #12 and #13.
  12. Run two multiple regression analyses, first examining the association between bty_total (explanatory variable) and score (response variable) (MODEL1) and then examining the association between bty_total (explanatory variable) and score (response variable), controlling for gender. Answer Questions #14 and #15.
  13. Submit your program.

Check your answers by submitting them on moodle under Practice B for Exam 4.