Objectives:

(1)   Learn how to use a dataset that is in “raw” form

(2)   learn how to use a dataset that already is in STATA form

(3)   practice summarizing datasets

(4)   learn some new STATA commands

 

STATA commands that you will find helpful today and in the future:

(For many of these commands, you can type as many variables as you want. Feel free to experiment; nothing bad will happen if you make a mistake.)

 

describe

graph varname1 varname2

chist varname1

summarize varname1 varname2, detail

help command

infile varname1 varname2 using “filename.raw”

use filename.dta

open filename.dta

list

clear

 

Activity 1:  Captopril

In order to test the effectiveness of the drug captopril as a blood-pressure treatment, 15 patients were given the same dose of the drug.  Their blood pressure was measured before and after taking the drug.  Use this data from http://www.stat.ucla.edu/~rgould/datasets/bloodpressure.raw

 

To download this existing “raw” file of data, type

infile before after using “http://www.stat.ucla.edu/~rgould/datasets/bloodpressure.raw”

 

There are two variables in this dataset.  The first variable represents the systolic blood pressure before the drug (varname = before), the second variable is the systolic blood pressure after the drug (varname = after).

 

A.  Type

summarize

for a summary of these two variables.  Describe the summary. 

See what happens when you type

summarize before, detail

 

B.  Make histograms of the before and after blood pressures. 

Type

chist varname1

Compare the shapes of the two histograms.  Can you conclude anything about the effectiveness of Captopril? Take into account the study design and provide any evidence, numerical or graphical that you think support your point.

 

Activity 2:  Old Faithful

 

Old Faithful is a geyser in Yellowstone National Forest that is a popular tourist attraction.  This geyser earned its name from the regularity of its eruptions.  This regularity, of course, also makes it ideal for a tourist attraction.  If a geyser erupts infrequently, and with no discernible pattern, then how are tourists to know when to visit?

 

Use data from http://www.stat.ucla.edu/~rgould/datasets/oldfath.dta

Note that this is a STATA object (it has the “.dta” ending). 

 

To use this file in STATA, type

use “http://www.stat.ucla.edu/~rgould/datasets/oldfath.dta”

 

C.  Type

describe

How many variables are in this dataset?  What are the variable names?  How many observations in the dataset?

 

D.  Type

list

What does this command do?

 

E.  The data record the length of time between eruptions (length) and the length of the last eruption (duration).  Tourists usually want to know how long they will have to wait until an eruption.  Based on this data, what would you tell them?  Are there any unusual features in the distribution of the times between eruptions?