STATA Programming Language - Computer Project 1 | ECON 422, Study Guides, Projects, Research of Introduction to Econometrics

Material Type: Project; Professor: Cropper; Class: ECONOMETRICS I; Subject: Economics; University: University of Maryland; Term: Fall 2008;

Typology: Study Guides, Projects, Research

Pre 2010

Uploaded on 07/29/2009

koofers-user-psj
koofers-user-psj 🇺🇸

3

(1)

10 documents

1 / 4

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
ECON 422
Quantitative Methods in Economics I
Prof. Maureen Cropper
Department of Economics
University of Maryland
Fall 2008
Computer Project 1
This project is designed to familiarize you with the STATA programming language. You are
asked to read a raw data file into STATA data set, construct a series of new variables, and then
produce some descriptive statistics about the data.
Most federal statistics about the labor market are collected as part of the Current Population
Survey (CPS). The CPS is a monthly survey administered by the Bureau of Labor Statistics to
about 60,000 households and 160,000 people. Sampled households participate in the survey for
the same 4 months in a two-year period (January-April in both 1986 and 1987 for example). In
each month of the survey, 1/4 of the families exit the survey and they are replaced by a new
group. The group that exits is called the "out-going rotation" group. Given the structure of the
survey, the CPS provides information about households as well as individuals. Some questions
are asked of all survey participants such as basic demographic information (e.g. age, race, sex,
education levels, marital status) and labor market participation (whether the individual is
working, looking for work, or out of the labor force). The "out-going rotation" group is
questioned about their jobs including usual weekly earnings, union status, and usual hours
worked per week.
A raw data file that includes 8 variables for 500 male workers, aged 21 to 64, from the
September 1985 CPS is located in the course web page. These observations are all taken from
the "out-going rotation" group.
The file contains the following variables (in order):
Variable Definition
AGE Age in years.
RACE Indicator value for race: =1 if respondent is hispanic, =2 if
respondent is black, =3 if respondent is white, nonhispanic.
EDUC Years of education (12 years means the person is a high school
graduate, 16 means the person is a college graduate, etc).
REGION Indicator variable for region of country: =1 if live in northeast, =2
if live in midwest, =3 if live in south, =4 if live in west.
URBAN Indicator variable for type of city: =1 is live in one of 19 largest
metropolitan areas. =2 if live in other metropolitan area, =3 if live
in other area.
pf3
pf4

Partial preview of the text

Download STATA Programming Language - Computer Project 1 | ECON 422 and more Study Guides, Projects, Research Introduction to Econometrics in PDF only on Docsity!

ECON 422

Quantitative Methods in Economics I

Prof. Maureen Cropper Department of Economics University of Maryland Fall 2008 Computer Project 1 This project is designed to familiarize you with the STATA programming language. You are asked to read a raw data file into STATA data set, construct a series of new variables, and then produce some descriptive statistics about the data. Most federal statistics about the labor market are collected as part of the Current Population Survey (CPS). The CPS is a monthly survey administered by the Bureau of Labor Statistics to about 60,000 households and 160,000 people. Sampled households participate in the survey for the same 4 months in a two-year period (January-April in both 1986 and 1987 for example). In each month of the survey, 1/4 of the families exit the survey and they are replaced by a new group. The group that exits is called the "out-going rotation" group. Given the structure of the survey, the CPS provides information about households as well as individuals. Some questions are asked of all survey participants such as basic demographic information (e.g. age, race, sex, education levels, marital status) and labor market participation (whether the individual is working, looking for work, or out of the labor force). The "out-going rotation" group is questioned about their jobs including usual weekly earnings, union status, and usual hours worked per week. A raw data file that includes 8 variables for 500 male workers, aged 21 to 64, from the September 1985 CPS is located in the course web page. These observations are all taken from the "out-going rotation" group. The file contains the following variables (in order): Variable Definition AGE Age in years. RACE Indicator value for race: =1 if respondent is hispanic, =2 if respondent is black, =3 if respondent is white, nonhispanic. EDUC Years of education (12 years means the person is a high school graduate, 16 means the person is a college graduate, etc). REGION Indicator variable for region of country: =1 if live in northeast, = if live in midwest, =3 if live in south, =4 if live in west. URBAN Indicator variable for type of city: =1 is live in one of 19 largest metropolitan areas. =2 if live in other metropolitan area, =3 if live in other area.

UNION Indicator that equals 1 if respondent is a union member, = otherwise. HOURS Usual hours worked per week. WEARN Usual weekly earnings. To insure confidentiality, earnings are "top-coded" in the CPS to equal $999 if weekly earnings exceed $1000.

a) Using command summarize, calculate the mean, minimum and maximum

hourly wage in the sample (8 points).

b) Using command summarize with option detail, calculate the median

wage in the sample (7 points). The syntax for this command is:

summarize [ varlist ], detail;

c) Construct the appropriate variable, and using command tabulate, calculate

the percent of workers working at or below the Federal minimum wage of $3.35/ hour (5 points).

4. Using command ttest, test the hypothesis that weekly earnings for workers with at

least a high school degree are the same as for workers without a high school degree. Using the results from the test, construct a 95 percent confidence interval for the difference in means between high school graduates and dropouts (20 points). The syntax

for ttest is:

ttest varname , by( groupvar );

5. Using command correlate, calculate the correlation coefficient between log

weekly wages and education (5 points). With an option covariance, you can

calculate the covariance between these two variables. What is it? (5 points) The syntax

for command correlate is:

correlate [ varlist ], covariance;

  1. Regress log weekly wages on education. What is the percentage change in earnings corresponding to a 1 year change in education (10 points)? The syntax for OLS regression is:

regress depvar [ varlist ];

You will also receive 10 points for handing in your STATA output.