Grading the professor

Many college courses conclude by giving students the opportunity to evaluate the course and the instructor anonymously. However, the use of these student evaluations as an indicator of course quality and teaching effectiveness is often criticized because these measures may reflect the influence of non-teaching related characteristics, such as the physical appearance of the instructor. The article titled, “Beauty in the classroom: instructors’ pulchritude and putative pedagogical productivity” (Hamermesh and Parker, 2005) found that instructors who are viewed to be better looking receive higher instructional ratings. (Daniel S. Hamermesh, Amy Parker, Beauty in the classroom: instructors pulchritude and putative pedagogical productivity, Economics of Education Review, Volume 24, Issue 4, August 2005, Pages 369-376, ISSN 0272-7757, 10.1016/j.econedurev.2004.07.013. http://www.sciencedirect.com/science/article/pii/S0272775704001165.)

In this lab we will analyze the data from this study in order to learn what goes into a positive professor evaluation.

The data

The data were gathered from end of semester student evaluations for a large sample of professors from the University of Texas at Austin. In addition, six students rated the professors’ physical appearance. (This is aslightly modified version of the original data set that was released as part of the replication data for Data Analysis Using Regression and Multilevel/Hierarchical Models (Gelman and Hill, 2007).) The result is a data frame where each row contains a different course and columns represent variables about the courses and professors.

load("more/evals.RData")
variable description
score average professor evaluation score: (1) very unsatisfactory - (5) excellent.
rank rank of professor: teaching, tenure track, tenured.
ethnicity ethnicity of professor: not minority, minority.
gender gender of professor: female, male.
language language of school where professor received education: english or non-english.
age age of professor.
cls_perc_eval percent of students in class who completed evaluation.
cls_did_eval number of students in class who completed evaluation.
cls_students total number of students in class.
cls_level class level: lower, upper.
cls_profs number of professors teaching sections in course in sample: single, multiple.
cls_credits number of credits of class: one credit (lab, PE, etc.), multi credit.
bty_f1lower beauty rating of professor from lower level female: (1) lowest - (10) highest.
bty_f1upper beauty rating of professor from upper level female: (1) lowest - (10) highest.
bty_f2upper beauty rating of professor from second upper level female: (1) lowest - (10) highest.
bty_m1lower beauty rating of professor from lower level male: (1) lowest - (10) highest.
bty_m1upper beauty rating of professor from upper level male: (1) lowest - (10) highest.
bty_m2upper beauty rating of professor from second upper level male: (1) lowest - (10) highest.
bty_avg average beauty rating of professor.
pic_outfit outfit of professor in picture: not formal, formal.
pic_color color of professor’s picture: color, black & white.

Exploring the data

  1. Is this an observational study or an experiment? The original research question posed in the paper is whether beauty leads directly to the differences in course evaluations. Given the study design, is it possible to answer this question as it is phrased? If not, rephrase the question.

    This is an observational study. The current question cannot be answered with an observational study, only with an experiment that controls for confounding variables. A more accurate question is whether there is a relationship between beauty and course evations.

  2. Describe the distribution of score. Is the distribution skewed? What does that tell you about how students rate courses? Is this what you expected to see? Why, or why not?

    The distribution of score is centered at 4.3, and is strongly skewed to the left. This tells me that most students rated professors between a 4 and 5, and lower ratings were less common. I expected to see ratings centered at 3 and distributed more symmetrically. This distribution shows that students included in this study view their teachers rather favorably.

    hist(evals$score)

    summary(evals$score)
    ##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   2.300   3.800   4.300   4.175   4.600   5.000

  3. Excluding score, select two other variables and describe their relationship using an appropriate visualization (scatterplot, side-by-side boxplots, or mosaic plot).

    I decided to visualize the relationship between age and average beauty rating of a teacher. It seems like age and beauty of teachers has a weak, linear, and negative relationship.

    plot(evals$bty_avg ~ evals$age)

Simple linear regression

The fundamental phenomenon suggested by the study is that better looking teachers are evaluated more favorably. Let’s create a scatterplot to see if this appears to be the case:

plot(evals$score ~ evals$bty_avg)

Before we draw conclusions about the trend, compare the number of observations in the data frame with the approximate number of points on the scatterplot. Is anything awry?

It seems like there may be overlap in the points on the scatter plot.

  1. Replot the scatterplot, but this time use the function jitter() on the \(y\)- or the \(x\)-coordinate. (Use ?jitter to learn more.) What was misleading about the initial scatterplot?

    The initial scatterplot was misleading because it did not show duplicate values with the same beauty rating and evalation score.

r plot(evals$score ~ jitter(evals$bty_avg))

  1. Let’s see if the apparent trend in the plot is something more than natural variation. Fit a linear model called m_bty to predict average professor score by average beauty rating and add the line to your plot using abline(m_bty). Write out the equation for the linear model and interpret the slope. Is average beauty score a statistically significant predictor? Does it appear to be a practically significant predictor?

    The equation is \(y=3.88034 + 0.06664x\). The slope means that for every point the beauty evaluation score increases, the teaching evaluation score increases by 0.06664. The Pr(>|t|) is almost 0, which means it is highly unlikely to observe a relationship between bty_avg and score by chance. Although the p-value shows that bty_avg is a statistically significant predictor, it does not seem to be a practically significant predictor. The scatter plot shows a very weak relationship between bty_avg and score with a very low R-squared value of 0.03502.

plot(evals$score ~ jitter(evals$bty_avg))
m_bty <- lm(score ~ bty_avg, data = evals)
abline(m_bty)
summary(m_bty)

  1. Use residual plots to evaluate whether the conditions of least squares regression are reasonable. Provide plots and comments for each one (see the Simple Regression Lab for a reminder of how to make these).

    Linearity: The scatter plot of bty_avg and score residuals appear to be close to the normal line.

qqnorm(m_bty$residuals)
qqline(m_bty$residuals)
*Nearly normal residuals*: The distribution of residuals is skewed to the left and is centered close to zero.
m_bty <- lm(score ~ bty_avg, data = evals)
hist(m_bty$residuals)

*Constant variability*: The scatter plot of residuals (above) shows constant variability for all values of bty_avg.
plot(m_bty$residuals ~ evals$bty_avg)
abline(h = 0, lty = 3)

Multiple linear regression

The data set contains several variables on the beauty score of the professor: individual ratings from each of the six students who were asked to score the physical appearance of the professors and the average of these six scores. Let’s take a look at the relationship between one of these scores and the average beauty score.

plot(evals$bty_avg ~ evals$bty_f1lower)
cor(evals$bty_avg, evals$bty_f1lower)

As expected the relationship is quite strong - after all, the average score is calculated using the individual scores. We can actually take a look at the relationships between all beauty variables (columns 13 through 19) using the following command:

plot(evals[,13:19])

These variables are collinear (correlated), and adding more than one of these variables to the model would not add much value to the model. In this application and with these highly-correlated predictors, it is reasonable to use the average beauty score as the single representative of these variables.

In order to see if beauty is still a significant predictor of professor score after we’ve accounted for the gender of the professor, we can add the gender term into the model.

m_bty_gen <- lm(score ~ bty_avg + gender, data = evals)
summary(m_bty_gen)
  1. P-values and parameter estimates should only be trusted if the conditions for the regression are reasonable. Verify that the conditions for this model are reasonable using diagnostic plots.

Linear Relationship The relationship between the bty_avg and score and between gender and score looks somewhat linear.

plot(evals$score ~ evals$bty_avg)

plot(evals$score ~ evals$gender)

Linearity: The scatter plot of bty_avg + gender and score residuals appear to be close to the normal line.

fit <- lm(score ~ bty_avg + gender, data = evals)
qqnorm(fit$residuals)
qqline(fit$residuals)
*Nearly normal residuals*: The distribution of residuals is skewed to the left and is centered at a mean of 0.
fit <- lm(score ~ bty_avg + gender, data = evals)
hist(fit$residuals)

summary(fit$residuals)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## -1.8305 -0.3625  0.1055  0.0000  0.4213  0.9313
*Constant variability*: The scatter plot of residuals (above) shows constant variability for all values of bty_avg.
plot(fit$residuals ~ evals$bty_avg)
abline(h = 0, lty = 3)

Conditions:
-The residuals of the model are nearly normal (confirmed by residual qq plot)
-The variability of the residuals is nearly constant (confirmed by residual plot)
-The residuals are independent (confirmed by residual plot)
-Each variable is linearly related to the outcome (confirmed by scatter plot)

  1. Is bty_avg still a significant predictor of score? Has the addition of gender to the model changed the parameter estimate for bty_avg?

    “bty_avg” is still a signifiant predicator of score, since the p-value for gendermale is still close to 0. The addition of “gender” to the model changed the intercept and slope of the model but not its significance.

Note that the estimate for gender is now called gendermale. You’ll see this name change whenever you introduce a categorical variable. The reason is that R recodes gender from having the values of female and male to being an indicator variable called gendermale that takes a value of \(0\) for females and a value of \(1\) for males. (Such variables are often referred to as “dummy” variables.)

As a result, for females, the parameter estimate is multiplied by zero, leaving the intercept and slope form familiar from simple regression.

\[ \begin{aligned} \widehat{score} &= \hat{\beta}_0 + \hat{\beta}_1 \times bty\_avg + \hat{\beta}_2 \times (0) \\ &= \hat{\beta}_0 + \hat{\beta}_1 \times bty\_avg\end{aligned} \]

We can plot this line and the line corresponding to males with the following custom function.

multiLines(m_bty_gen)

  1. What is the equation of the line corresponding to males? (Hint: For males, the parameter estimate is multiplied by 1.) For two professors who received the same beauty rating, which gender tends to have the higher course evaluation score?

    For two professors who received the same beauty rating, male professors tend to have the higher course evaluation scores. The equation of the line corresponding to males is: \[ \begin{aligned} \widehat{score} &= \hat{\beta}_0 + \hat{\beta}_1 \times bty\_avg + \hat{\beta}_2 \times (1) \\ &= 3.74734 + 0.17239 \times bty\_avg\end{aligned} \]

The decision to call the indicator variable gendermale instead ofgenderfemale has no deeper meaning. R simply codes the category that comes first alphabetically as a \(0\). (You can change the reference level of a categorical variable, which is the level that is coded as a 0, using therelevel function. Use ?relevel to learn more.)

  1. Create a new model called m_bty_rank with gender removed and rank added in. How does R appear to handle categorical variables that have more than two levels? Note that the rank variable has three levels: teaching, tenure track, tenured.

    R created a slope estimate for two of the three categorical variable levels. In general, it seems like the summary shows one less regression line than there are levels.

m_bty_rank <- lm(score ~ bty_avg + rank, data = evals)
summary(m_bty_rank)
## 
## Call:
## lm(formula = score ~ bty_avg + rank, data = evals)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.8713 -0.3642  0.1489  0.4103  0.9525 
## 
## Coefficients:
##                  Estimate Std. Error t value Pr(>|t|)    
## (Intercept)       3.98155    0.09078  43.860  < 2e-16 ***
## bty_avg           0.06783    0.01655   4.098 4.92e-05 ***
## ranktenure track -0.16070    0.07395  -2.173   0.0303 *  
## ranktenured      -0.12623    0.06266  -2.014   0.0445 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.5328 on 459 degrees of freedom
## Multiple R-squared:  0.04652,    Adjusted R-squared:  0.04029 
## F-statistic: 7.465 on 3 and 459 DF,  p-value: 6.88e-05

The interpretation of the coefficients in multiple regression is slightly different from that of simple regression. The estimate for bty_avg reflects how much higher a group of professors is expected to score if they have a beauty rating that is one point higher while holding all other variables constant. In this case, that translates into considering only professors of the same rank with bty_avg scores that are one point apart.

The search for the best model

We will start with a full model that predicts professor score based on rank, ethnicity, gender, language of the university where they got their degree, age, proportion of students that filled out evaluations, class size, course level, number of professors, number of credits, average beauty rating, outfit, and picture color.

  1. Which variable would you expect to have the highest p-value in this model? Why? Hint: Think about which variable would you expect to not have any association with the professor score.

    I would expect rank to have the highest p-value in this model, because that seems like the variable that would have the least association with professor score.

Let’s run the model…

m_full <- lm(score ~ rank + ethnicity + gender + language + age + cls_perc_eval 
             + cls_students + cls_level + cls_profs + cls_credits + bty_avg 
             + pic_outfit + pic_color, data = evals)
summary(m_full)

  1. Check your suspicions from the previous exercise. Include the model output in your response.

    My suspicious from the previous exercise were correct; for tenured and tenure track variable categories, the p-values of 0.14295 and 0.07278 are not statistically significant.

  2. Interpret the coefficient associated with the ethnicity variable.

    The coefficient associated with the ethnicity variable is 0.1234929 means that the regression line between ethnicity and score increases by 0.1234929 for minority professors.

  3. Drop the variable with the highest p-value and re-fit the model. Did the coefficients and significance of the other explanatory variables change? (One of the things that makes multiple regression interesting is that coefficient estimates depend on the other variables that are included in the model.) If not, what does this say about whether or not the dropped variable was collinear with the other explanatory variables?

    I dropped the cls_profs variable. The coefficients and significance of other explanatory variable changed slightly. If the coefficience and significance didn’t change, this would indicate that cls_profs was not collinear with the other explanatory variables.

m_new <- lm(score ~ rank + ethnicity + gender + language + age + cls_perc_eval 
             + cls_students + cls_level + cls_credits + bty_avg 
             + pic_outfit + pic_color, data = evals)
summary(m_new)

  1. Using backward-selection and p-value as the selection criterion, determine the best model. You do not need to show all steps in your answer, just the output for the final model. Also, write out the linear model for predicting score based on the final model you settle on.

    Backward elimination starts with the model that includes all potential predictor variables. Variables are eliminated one-at-a-time from the model until we cannot improve the adjusted R-squared. The strategy within each elimination step is to eliminate the variable that leads to the largest improvement in adjusted R-squared.

    \(score = 3.771922 + (0.167872 * ethnicitynot minority) + (0.207112 * gendermale) + (-0.206178 * languagenon-english) + (-0.006046 * age) + (0.004656 * cls_perc_eval) + (0.505306 * cls_creditsone credit) + (0.051069 * bty_avg) + (-0.190579 * pic_colorcolor)\)

m_new <- lm(score ~ rank + ethnicity + gender + language + age + cls_perc_eval 
             + cls_students + cls_level + cls_credits + bty_avg 
             + pic_outfit + pic_color, data = evals)
m_new <- lm(score ~ rank + ethnicity + gender + language + age + cls_perc_eval 
             + cls_students + cls_credits + bty_avg 
             + pic_outfit + pic_color, data = evals)
m_new <- lm(score ~ rank + ethnicity + gender + language + age + cls_perc_eval 
             + cls_credits + bty_avg 
             + pic_outfit + pic_color, data = evals)
m_new <- lm(score ~ + ethnicity + gender + language + age + cls_perc_eval 
             + cls_credits + bty_avg 
             + pic_outfit + pic_color, data = evals)
m_new <- lm(score ~ + ethnicity + gender + language + age + cls_perc_eval 
             + cls_credits + bty_avg 
             + pic_color, data = evals)
summary(m_new)

  1. Verify that the conditions for this model are reasonable using diagnostic plots.

    Conditions: -The residuals of the model are nearly normal (confirmed by residual qq plot)

qqnorm(m_new$residuals)
qqline(m_new$residuals)
-The variability of the residuals is nearly constant (confirmed by residual plot)
m_new <- lm(score ~ + ethnicity + gender + language + age + cls_perc_eval 
             + cls_credits + bty_avg 
             + pic_color, data = evals)
plot(m_new$residuals ~ evals$bty_avg)
abline(h = 0, lty = 3)

-The residuals are independent (attractiveness of one professor is independent from another)
-Each variable is linearly related to the outcome (confirmed by the correlation plot)

  1. The original paper describes how these data were gathered by taking a sample of professors from the University of Texas at Austin and including all courses that they have taught. Considering that each row represents a course, could this new information have an impact on any of the conditions of linear regression?

    This new information would impact the independence condition, because the attractiveness of a professor teaching different courses would not be independent if the same professor is teaching these cources.

  2. Based on your final model, describe the characteristics of a professor and course at University of Texas at Austin that would be associated with a high evaluation score.

    The characteristics of a professor and course that would be associated with a high evaluation score are:

    • Professor belongs to an ethnic minority group
    • Professor is female
    • Professor was educated in an english-speaking institution
    • Professor is younger
    • A higher percentage of the course provided evaluations
    • The course is more than one credit
    • The professor picture is not in color

  3. Would you be comfortable generalizing your conclusions to apply to professors generally (at any university)? Why or why not?

    I would not be comfortable generalizing these conclusions to apply to professors at any university because the sample only includes professors from one univerity. One university cannot be representative of all universities.

This is a product of OpenIntro that is released under a Creative Commons Attribution-ShareAlike 3.0 Unported. This lab was written by Mine Çetinkaya-Rundel and Andrew Bray.