Empirical Exercises1

2026/1/27 6:24:12

By Yanan Zhang, 14210690101

8. The dataset \course characteristics, and professor characteristics for 463 courses at the UT Austin. Please read the detailed description given in \

Description.pdf\professor's beauty.

(a) Draw a scatterplot of average course evaluations (Course_eval) on the professor's beauty. Any relationship between two variables?

(b) Run a regression of Course_eval on Beauty. Interpret the estimated parameters?

(c) Suppose Prof. Wooldridge has an average value of Beauty, while Prof. Zhu's value of Beauty is one standard deviation below the average. Predict Prof. Wooldridge's and Prof. Zhu's course evaluation.

(d) Does Beauty explain a large fraction of the variation in evaluation across courses? Explain. Coding as follows:

x=xlsread('TeachingRatings','E2:E464'); y=xlsread('TeachingRatings','F2:F464'); x_mean=mean(x); y_mean=mean(y); x_std=std(x); y_std=std(y); scatter(x,y);

p=polyfit(x,y,1); x1=[ones(463,1),x];

[b,bint,r,rint,stats]=regress(y,x1);

1=3.9983,?? 0=0.1330, course_eval So ??=0.1330+3.9983????????????.

The regression result indicates that beauty has a positive influence on course_eval and when beauty increase 1 unit, course_eval is expected to increase 3.9983 units. c)

Prof. Wooldridge: beauty=6.2635e^(-8), course_eval=0.1414 Prof. Zhu: beauty=6.2635e^(-8)-0.7886,course_eval=-3.0117

because of R2=0.0357, the goodness of fit is low.Beauty can’texplain course evaluation well.

9. Use the dataset \answer the following questions:

(a) What is the average gift in the sample of 4268 people? What is the percentage of people gave no gifts?

(b) What is the average mailings per year? What are the minimum and maximum values?

(d) Interpret the slope coefficient. If each mailing costs one guilder, is the charity expected to make a net gain on each mailing? Does this mean the charity makes a net gain on every mailing? Explain.

(e) What is the smallest predicted charitable contribution in the sample? Using this simple regression analysis, can you ever predict zero for gift? a)

The smallest predicted charitable contribution in the sample is zero. Using this simple regression analysis, I can’t predict zero for gift for both??1 ?????? ??0>0. gift=xlsread('CHARITY','B2:B4269'); mean_gift=mean(gift) mean_gift =7.4445

gift=xlsread('CHARITY','B2:B4269'); count=0; length=4268; fori=1:length if(gift(i)==0) count=count+1; end end count

ratio=1-count/numel(gift) ratio=0.4 b)

mailsyear=xlsread('CHARITY','F2:F4269'); mailsyear_mean=mean(mailsyear); mailsyear_max=max(mailsyear); mailsyear_min=min(mailsyear);

so the average mailings per year equals to 2.0496. The minimum value is 0.25 and the maximum is 3.5. c)

y=xlsread('CHARITY','B2:B4269'); x=xlsread('CHARITY','F2:F4269'); x_mean=mean(x); y_mean=mean(y); x_std=std(x); y_std=std(y);

scatter(x,y); p=polyfit(x,y,1); x1=[ones(4268,1),x];

[b,bint,r,rint,stats]=regress(y,x1);

=2.6495+2.0141??????????????????. ????????

R2=0.0138

Sample size=4238 d)

The charity is expected to make a net gain on each mailing because ??1>0. However, this doesn’t mean the charity makes a net gain on every mailing because ??1?????????????????? just represents the expectation of gift. e)

The smallest predicted charitable contribution in the sample is 0. Using this simple regression analysis, you can’t predict zero for gift.

10. Something real. Collect the financial information from the annual reports of selected public firms. Clearly state your data source and be prepared for peer validation.

(a) Pick all listed companies whose headquarters are in the province that your personal identification card is designated to.

(b) Collect the annual reports in the year that you entered into your undergraduate college.

(c) Tabulate the cross sectional descriptive statistics of the following financial variables: _ Total Assets _ Total Liability