Introduction to STATA

About STATA
Basic Operations
Regression Analysis
Panel Data Analysis

About

STATA is modern and general command driven package for

statistical analyses, data management and graphics.

STATA provides commands to analyze panel data (crosssectional time-series, longitudinal, repeated-measures, and
correlated data), cross-sectional data, time-series data,
survival-time data, cohort study,

STATA is user friendly.

STATA has an extraordinary set of reference books.

STATA has internet capabilities (installing new features,

updating)

Getting ready

Download statadata.zip from Econ 511 website

Unzip file statadata.zip to U:\stata

Basic Operations

Entering Data

Exploring Data

Modifying Data

Managing Data

Analyzing Data

Entering Data

Insheet: Read ASCII (text) data created by a spreadsheet (.csv files only)

Infile: Read unformatted ASCII (text) data (space delimited files)

Input: Enter data from keyboard

Describe: Describe contents of data in memory or on disk

Compress: Compress data in memory

Save: Store the dataset currently in memory on disk in Stata data format

Count: Show the number of observations

List: List values of variables

Clear: Clear the entire dataset and everything else

Memory: Display a report on memory usage

Set memory: Set the size of memory

Example

cd u:\stata

dir

insheet using hs0.csv (If file has variable name on the first line)

Save hs

insheet gender id race ses schtyp prgtype read write math science
socst using hs0_noname.csv, clear(If file doesnt have variable name on the
first line)

Count

Describe

Compress

Clear

use hs, clear (only for files in Stata files, can be use over internet)

Memory

set memory 5m (maximum: 256MB)

Exploring data

Describe: Describe a dataset

List List the contents of a dataset

Codebook: Detailed contents of a dataset

Log: Create a log file

Summarize: Descriptive statistics

Tabstat: Table of descriptive statistics

Table: Create a table of statistics

Stem: Stem-and-leaf plot

Graph: High resolution graphs

Kdensity: Kernal density plot

Sort: Sort observations in a dataset

Histogram: Histogram for continuous and categorical variables

Tabulate: One- and two-way frequency tables

Correlate: Correlations

Pwcorr: Pairwise correlations

Type: Display an ASCII file

Example

use hs0, clear

Describe
List
list gender-read
Codebook
log using unit1, text replace (open a existing log file called unit1
which will save all of the commands and the output in a text file and
delete the contents and places the current log into the file
summarize
summarize read math science write
display 9.48^2 (note: variance is the sd (9.48) squared)
summarize write
detail sum write if read>=60
sum write if prgtype=="academic
sum write in 1/40
tabulate prgtype, summarize(read)
stem write
graph box write
log close (close the log file)
type unit1.log (see what is in the log file)

Modifying Data

label data:Apply a label to a data set

Order:Order the variables in a data set

label variable: Apply a label to a variable

label define: Define a set of a labels for the levels of a categorical

variable

label values: Apply value labels to a variable

List: Lists the observations

Rename: Rename a variable

Recode: Recode the values of a variable

Notes: Apply notes to the data file

Generate: Creates a new variable

Replace: Replaces one value with another value

Egen: Extended generate - has special functions that can be used when
creating a new variable

Example

Use hs0
Order id gender
label variable schtyp "The type of school the student
attended."
label define scl 1 public 2 private
label values schtyp scl
codebook schtyp
list schtyp in 1/10
list schtyp in 1/10, nolabel
encode prgtype, gen(prog) (create a new numeric version of the
string variable prgtype)
label variable prog "The type of program in which the student
was enrolled."
codebook prog
list prog in 1/10
list prog in 1/10, nolabel

Example (cont)

rename gender female (easier to work with since we dont have to deal with 0s and 1s)

label variable female "The gender of the student."

label define fm 1 female 0 male

label values female fm

codebook female

list female in 1/10, nolabel

Gen total = read +write + math

replace total = read + write + socst

label variable total "The total of the read, write and socst."

list race if race == 5

recode race 5 = .

list race if race == .

generate total = read + write + math

sum total

Codebook total

notes race: values of race coded as 5 were recoded to be missing

egen zread = std(read) (using special function std(.))

save hs1

Managing Data

Pwd: Show current directory (pwd=print working

directory)

dir or ls: Show files in current directory

cd Change directory

keep if: Keep observations if condition is met

Keep: Keep variables (dropping others)

Drop: Drop variables (keeping others)

append using: Append a data file to current file

Merge: Merge a data file with current file

Example
We take the hs1 data file and make a separate folder called honors and store
a copy of our data which just has the students with reading scores of 60 or
higher

use hs1, clear

Pwd

Dir

Ls

cd honors

keep if read >= 60

Describe

summarize read

save hsgoodread, replace

use hsgoodread, clear

drop ses

save hsdropped, replace

describe

list in 1/20

Analyzing Data

Ttest: t-test
Regress: Regression
Predict: Predicts after model estimation
Kdensity: Kernel density estimates and graphs
Pnorm: Graphs a standardized normal plot
Qnorm: Graphs a quantile plot
Rvfplot: Graphs a residual versus fitted plot
Rvpplot: Graphs a residual versus individual predictor plot
Xi: Creates dummy variables during model estimation
Test: Test linear hypotheses after model estimation
Oneway: One-way analysis of variance
Anova: Analysis of variance
Logistic: Logistic regression
Logit: Logistic regression

Example

use hs1, clear

ttest write = 50 (This is the one-sample t-test, testing whether the sample of
writing scores was drawn from a population with a mean of 50 )

ttest write = read (This is the paired t-test, testing whether or not the mean of
write equals the mean of read)

ttest write, by(female) (This is the two-sample independent t-test with pooled
(equal) variances)

ttest write, by(female) unequal (This is the two-sample independent t-test

with separate (unequal) variances)

oneway write prog

anova write prog (Both of these commands perform a one-way analysis of

variance (ANOVA)

anova write prog female prog*female (the anova command is used to

perform a two-way analysis of variance (ANOVA).)

anova write prog female prog*female read, cont(read) (the anova

command performs an analysis of covariance (ANCOVA))

Example (cont)

regress write read female (Plain vanilla OLS regression)

regress write read female, robust (we run the regression with robust
standard errors. This is very useful when there is heterogeneity of
variance. This option does not affect the estimates of the regression
coefficients.)

predict p (The predict command calculates predictions, residuals,

influence statistics, and the like after an estimation command. The default
shown here is to calculate the predicted scores)

predict r, resid (When using the resid option the predict command
calculates the residual)

pnorm r ( produces a normal probability plot and it is another method of

testing whether the residuals from the regression are normally
distributed)

Rvfplot (generates a plot of the residual versus the fitted values; it is

used after regress or anova)

rvpplot read (produces a plot of the residual versus a specified predictor

and it is also used after regress or anova.

Example (cont)

xi: regress write read i.prog (The xi prefix is used to dummy code categorical
variables such as prog. The predictor prog has three levels and requires two
dummy-coded variables)
test _Iprog_2 _Iprog_3 (The test command is used to test the collective effect of
the two dummy-coded variables; in other words, it tests the main effect of prog)
xi: regress write i.prog*read (create dummy variables for prog and for the
interaction of prog and read)
test _IproXread_2 _IproXread_3 (tests the overall interaction)
test _Iprog_2 _Iprog_3 (tests the main effect of prog)
gen honcomp = write >= 60 (create a dichotomous variable called honcomp
(honors composition) to use as our dependent variable)
tab honcomp
The logistic command defaults to producing the output in odds ratios but can
display the coefficients if the coef option is used. The exact same results can be
obtained by using the logit command, which produces coefficients as the default
but will display the odds ratio if the or option is used:
logit honcomp read female
logit honcomp read female, or

Logistic Regression
Classical Regression vs Logistic Regression

All of the previous regression examples have used continuous dependent variables.

Logistic regression is used when the dependent variable is binary or dichotomous.

Different Assumptions

The population means of the dependent variables at each level of the independent
variable are not on a straight line, i.e., no linearity.

The variance of the errors are not constant, i.e., no homogeneity of variance.

The errors are not normally distributed, i.e., no normaility.

Logistic Regression Assumptions:

The model is correctly specified, i.e.,

1.
the true conditional probabilities are a logistic function of the indpendent
variables,
2.
no important variables are omitted,
3.
no extraneous variables are included, and
4.
the independent variables are measured without error.

The cases are independent.

The independent variables are not linear combinations of each other.

Perfect multicolinearity makes estimation impossible, while strong
multicolinearity makes estimates imprecise.

Logistic Regression - 2
Logit:

Use admission into a graduate program in which 70% of the males and 30% of the
females are admitted
Let P equal the probability of being admitted.

Let Q = 1 - P equal the probability of not being admitted.

Let the odds of a male admitted be odds(M) = P/Q = P/1-P = .7/.3 = 2.3333

Let the odds of a female admitted be odds(F) = P/Q = P/1-P = .3/.7 = .42857

Let the odds ration, OR = odds(M)/odds(F) = 2.3333/.42857 = 5.44

The odds if being admitted to the program are about 5.44 times greater for males then
for females.

Let logit(P) = log(odds) = ln(P/Q) = ln (P/1 - P)

This results in the logistic regression equation logit(P) = a + bX.

In effect, this represents a transformation of the dependent variable such that the
resulting logistic regression equation better meets the assumptions of linearity,
normality and homogeneity of variance
Interpreting logit coefficients:

Logistic slope coefficients can be interpreted as the effect of a unit of change in the X
variable on the predicted logits with the other variables in the model held constant. That
is, how a one unit change in X effects the log of the odds when the other variables in the
model held constant.
Interpreting Odds Ratios:

Odds ratios in logistic regression can be interpreted as the effect of a one unit of change
in X in the predicted odds ratio with the other variables in the model held constant

Logistic Regression 3

Sample data set:

input apt gender admit
811
710
511
310
310
511
711
811
511
511
400
701
301
200
400
200
300
401
300
200
end

Logistic Regression 4
Example 1: Categorical Independent Variable

logit admit gender

logistic admit gender

Example 2: Continuous Independent Variable

logit admit apt

logistic admit apt

Example 3: Categorical & Continuous Independent Variables

logit admit gender apt

logistic admit gender apt

Example 4: Honors Composition using HSB Dataset

Use hsb2, clear

generate honors = (write>=60) (create dichotomous response variable)

tabulate ses, generate(ses) (create dummy coding for ses)

logit honors female ses1 ses2 read math

test ses1 ses2

logistic honors female ses1 ses2 read math

lfit (goodness-of-fit test)

lstat

Do file

Do-files are created with the do-file editor or any other text editor. Any
command which can be executed from the command line can be placed in a dofile
To open a do file editor: Window Do-file Editor or Ctrl + 8
set more off
use hsb2, clear
generate lang = read + write
label variable lang "language score"
tabulate lang
tabulate lang female
tabulate lang prog
tabulate lang schtyp
summarize lang, detail
table female, contents(n lang mean lang sd lang)
table prog, contents(n lang mean lang sd lang)
table ses, contents(n lang mean lang sd lang)
correlate lang math science socst
regress lang math science female
set more on

Do file cont.
Look at the commands in a do-file that contains:

. type hsbbatch.do
To run the do-file.

do hsbbatch

From do file, choose Tools - Do

Panel Data
Creat the do file as followed

set matsize 160

use http://www.ats.ucla.edu/stat/stata/stat130/depress, clear

sort group

by group: summarize pre dep1 dep2 dep3 dep4 dep5 dep6

corr pre dep1 dep2 dep3 dep4 dep5 dep6

graph dep1 dep2 dep3 dep4 dep5 dep6, matrix half

ttest pre, by(group) /* check to see if the groups differ on the pretest depression score

*/

hotel dep1 dep2 dep3 dep4 dep5 dep6, by(group)/*There isn't much of a difference
between groups on the pretest so let's try a Hotelling's T2

Using Hotelling's T2 we find a significant difference between the two groups. The T2 did not
make use of any of the information concerning the pretest but that's okay for the moment
especially since we know that the pretest differences were not significant.*/

reshape long dep, i(subj) j(visit)

regress dep pre group visit

glm dep pre group visit, fam(gaus) link(iden)

xtgee dep pre group visit, fam(gaus) link(iden) i(subj) t(visit) corr(ind) /*The three
previous analyses provide identical incorrect results.

The common thread among them is that they all assume that the observations within the
subjects are independent. This seems, on the face of it, to be highly unlikely. Scores on the
depression scale are not likely to be independent from one visit to the next.

Of the three, only xtgee makes the assumption concerning the correlations explicit.*/

xtcorr /* The xtcorr command shows structure of the correlation matrix*/

/* xt commands are used with cross-sectional time-series data */

xtsum dep

Panel data 2

/*We can analyze these data using compound symmetry for the correlational structure.
This approach can be tried using exchangable for the correlation matrix in xtgee */
xtgee dep pre group visit, fam(gaus) link(iden) i(subj) t(visit) corr(exc)
xtcorr
/*Note in particular the change in the standard errors between this analysis and the
previous one.
Now let's try a different correlation structure, auto regressive with lag one.*/
xtgee dep pre group visit, fam(gaus) link(iden) i(subj) t(visit) corr(ar1)
/*back up and reconsider the group by visit interaction.
We will try a model with the interaction using the ar1 correlations. */
generate gxv = group*visit
xtgee dep pre group visit gxv, fam(gaus) link(iden) i(subj) t(visit) corr(ar1)
/* The group by visit interaction still is not significant even though this may be a better
approach for testing it.
So far we have been treating visit as a continuous variable.
Is it possible that our analysis might change if we were to treat visit as a categorical
variable, the way that the anova did?
Let's try one last analysis using xi to create dummy variables on-the-fly. */
xi: xtgee dep pre group i.visit, fam(gaus) link(iden) i(subj) corr(ar1)

Searching for help

The help command can be used from the command line or from the Help
window. To use help the command must be spelled correctly and the full
name of the command must be used. help contents will list all
commands that can be accessed using help
help if
help anova
help regress
The search command searches for information in Stata manuals, FAQs,
and Stata Technical Bulletins (STBs). The search options include: manual
which restricts searches to the Stata Manual; author when searching for
an author by name; stb which restricts searhes to STBs; faq which
restricts searches to FAQs.The search command can be used from either
the command line or the Help window.
search if
search regression
search ttest, manual
Each copy of Stata comes with a built-in tutorital. Typing tutorial brings
up information about the tutorials. tutorial regress will bring up the
tutorial on regression.
tutorial
tutorial regress

End of Session