Published by
Professor Gd

**MBAAF 636 Fall 2020: Homework #1, Due Thursday, October 8 1**

**Problem 1 (50 points)**

As a computer industry analyst you are interested in tracing financial health of computer industry

between 2010 and 2014 and in particular tracing the impact of the financial crisis and recession

on the industry’s health. To answer these questions you have access to selected balance sheet and

income statement data items from the Compustat.

To accomplish your task you will need to know how to use Stata to import a dataset, review data,

perform simple data manipulation tasks, display summary statistics, and export the final dataset.

You must create and run a do-file and show your results in a log files. The instructions below

contain hints as to which commands may be appropriate for each task. Be sure to consult Stata’s

help function as necessary.

Each of the parts below is worth 5 points. You must use one or more Stata commands to

implement each of the parts below.

Open Stata and start a do-file. Be sure to begin a log (in text file format) and set your

own working directory.

Import the dataset that contains a subset of annual balance sheet and income statement

items [“AnnualFinancials_2010_2014_Fiscal.csv”], browse its contents, and use a

command to describe the variables

How many observations of revenue (revt) and cash and short term investments (che) and

capital expenditure (capx) variables have negative values? How many observations of

revenue variable are negative when variable che is missing? Set negative values of

revenue (revt) and cash and short term investments (che) and capital expenditure (capx)

variables equal to missing.

For each firm and fiscal year generate three variables: cash_to_assets which is a ratio of

cash and short term investments to total assets asset_turn which asset turnover ratio

(revenue/total assets) and the capex_intensity which is a ratio of capital expenditures to

revenue. For each new variable show detailed summary statistics

List fiscal year, company name, sic code and three ratios generated above for Microsoft

Inc. for all years in the data. What can you say about changes in Microsoft’s financial

position or performance over time? Briefly comment.

Generate a dummy variable that takes on value of one if a firm belongs to Electronics and

Computer industries category (SIC codes 3570, 3571, 3572, 3575, 3576, 3577, 3578 or

3579) and zero otherwise.

(Note: for sic code description browse to: http://www.sec.gov/info/edgar/siccodes.htm)

(a) Calculate mean asset turnover ratio for Electronics and Computer category in 2010

and 2014 only? (b) Now calculate the median asset turnover ratio for each industry (sic

code) within Electronics and Computer category in 2010 and in 2014 only. Do you find

MBAAF 636 Fall 2020: Homework #1, Due Thursday, October 8 2

that differences in asset turnover ratios between industries in 2010 remain similar in 2014? Briefly comment.

Display a table that identifies 2014 firm-level asset turnover ratios for each industry (sic

code) in Electronics and Computers category. Which industry contains a firm with the

highest and lowest asset turnover ratio?

Be sure to save a copy of the dataset in your directory in Stata and Excel files. When

saving data to an Excel file make sure that variable names will appear in the first row and

data is outputted to Excel worksheet named “Compustat”.

To finish, close the log file and save the do-file. Hand in print-outs of both.

**Problem 2: (15 points)**

Answer the following problem using Stata commands subject to the following restriction: your

sample should include only CEOs who are older than 40 and who have attended both college and

a graduate school. Use do file and report all your results in a log file. Each of the three parts is

worth 5 points.

The data set in CEOSAL2.dta contains information on chief executive officers for U.S.

corporations. The variable salary is annual compensation, in thousands of dollars, and ceoten is

prior number of years as company CEO.

(i) Find the average salary and the average CEO tenure in the sample.

(ii) How many CEOs are in their first year as CEO (that is, ceoten=0)? What is the

longest tenure as a CEO?

(iii) Estimate the simple regression model

log(??????) = ? + ?ଵ?????? + ?

and report your coefficients, standard errors and R-squared. What is the

(approximate) predicted percentage increase in salary given one more year as a CEO?

**Problem 3: (15 points)**

Using data from 1988 for houses sold in Andover, Massachusetts, from Kiel and McClain

(1995), the following equation relates housing price (price) to the distance from a recently

built garbage incinerator (dist):

Note that this is not a computer exercise. Each of the three parts below is worth 5 points.

MBAAF 636 Fall 2020: Homework #1, Due Thursday, October 8

3

(i) Interpret the coefficient on log(dist). Is the sign of this estimate what you expect it to be?

(ii) Do you think simple regression provides an unbiased estimator of the ceteris paribus

elasticity of price with respect to dist? (Think about the city’s decision on where to

put the incinerator.)

(iii) What other factors about a house affect its price? Might these be correlated with distance

from the incinerator?

Problem 4: (10 points)

Suppose you estimate a simple linear regression of Y on X, and another simple linear regression

of X on Y.

(a) Write down the condition that must hold for the estimated slope coefficient for a

regression of Y on X and the estimated slope coefficient for a regression of X on Y to be

reciprocals of one another? Hint: Look carefully at the formula for OLS slope estimator.

(5 pts)

(b) Suppose you find that the estimated slope coefficient for a regression of Y on X is greater

than the estimated slope coefficient for the regression of X on Y. Would that fact help

you to make a decision as to whether X or Y should be your explanatory variable?

Answer “Yes” or “No” and briefly explain. (5 pts)

Problem 5: (10 points)

Suppose the following is the true population model of the effect of Return on Assets (ROA) on

CEO salary: Annual CEO Salary = β0 + β1Annual ROA + u. Further, suppose that the sample

average CEO Salary is $525,000 and the sample average Annual ROA is 10% (assume that in

your data Annual ROA is reported in percent form, not in decimal form). Finally, suppose your

estimate of β0 is 230,000.

(a) What must your OLS estimate of β1be? Show your calculations. (5 pts)

(b) If Richard Smith, the CEO of XYZ Inc. has earned an annual salary of $800,000 this year

and XYZ Inc’s ROA is 12% this year what is the value of u for Richard Smith? (5 pts)

Extra Credit (5 points)

Using WRDS class account download Stata file that contains data the same variables and the

same fiscal years as “AnnualFinancials_2010_2014_Fiscal.dta” file. Use Compustat North

America Fundamentals Annual for your query. You must save your query as

“HW1_extracredit_YourFirst&LastName” on WRDS website. Once you download the Stata file

describe all variables and summarize all variables in the dataset. Submit your Stata log file.

WRDS website: https://wrds-web.wharton.upenn.edu/wrds/

Login: mbaaf636

Password: QuantData2020