stata prirucnik

8/13/2019 Stata prirucnik

1/75

UVOD U STATA SOFTWARE21/09/2013


2/75

SOFTWARE OPTIONS

(NO SUCH THING AS THE BEST)

MS Excel

SPSS

STATA

EViews

R

SAS (+ SAP, Oracle, Business Objects, etc.)

MATLab Shazam

Compare statistical packages online

Install student/trial versions2


3/75

OBJECTIVES

As per prof. Verbi

Introduction to the Stata software:

Capabilities

User interface

Menus vs commands

Statistics features

Regression features

3


4/75

USEFUL INTRO INFO

o STATA Help for all STATA commands

o the STATA Users Guide andReference Manual

o STATA Journal - a quarterly publication containing articles about statistics,

data analysis, teaching methods, and effective use of STATA's language.

o STATA Tutorial for Stock and WatsonIntroduction to Econometrics,

Pearson, 2003

o University of Toronto, Department of Economics, Elena Capatina

o www.ats.ucla.edu/stat/stata/webbooks/reg/default.htm

o www.iies.su.se/~masa/stata.htm

o www.princeton.edu/~erp/stata/main.html4


5/75

HOW TO GET DATA

World Bank databases

Penn World Tables

COMPUSTAT

OECD National Accounts Database

Greene, Wooldridge, Hsiao, Gujarati, Kennedy, etc.

Websites of professors

Google Scholar

5


6/75

STATAWINDOWS

The command window

The viewer/results window

The review of commands window

The variable window

6


7/75

7


8/75

8

Drop-down menu

Review

window

Variableswindow

Command window

Results window


9/75

9


10/75

10


11/75

11


12/75

12


13/75

13

copy + later paste


14/75

14


15/75

DATA EDITOR VS. DATA BROWSER

Data editor shows you your data and you can edit it

Data browser shows you your data but you cannot edit it

Check this frequently, especially after commands you are

unsure about

15


16/75

16

data browser

data editor


17/75

17


18/75

18


19/75

TYPE OF COMMANDS

1. Administrative commands that tell STATA where to

save results, how to manage computer memory, and

2. Commands that tell STATA to read and manage

datasets

3. Commands that tell STATA to modify existing

variables or to create new variables

4. Commands that tell STATA to carry out the

statistical analysis19


20/75

WORKING WITH STATA

Once you have started STATA, you will see a large window containing several

smaller windows. At this point you can load the dataset and begin thestatistical analysis.

STATA can be operated interactively or in batch mode.

When you use STATA interactively, you type each STATA command in theSTATA command window and hit theReturn/Enter key on your keyboard.

STATA executes the command and the results are displayed in the STATAResults window.

Then you enter the next command, STATA executes it, and so forth, until theanalysis is complete.

Even the simplest statistical analysis will involve several STATA commands.20


21/75

WORKING WITH STATA

When STATA is used in batch mode, all of the commands for the analysisare listed in a file, and STATA is told to read the file and execute all of thecommands.

These files are called do files by STATA and are saved using a .dosuffix.When STATA executes .do file, all of the empirical resultsfor some work/paper/research study are produced.

21


22/75

WORKING WITH STATA

Using STATA in batch mode has three important advantages over usingSTATA interactively.

1. .do files provide an audit trail for your work. The file provides an exact

record of each STATA command that allows you to be more efficient inyour research.

2. .do files allows others to learn from your work, replicate your work andfind other ways to improve their/your research.

3. Everyone makes errors when using STATA. When a command containsan error, it will not be executed by STATA, or if it is, it will produce the

wrong result. Following an error, it often necessary to start the analysisfrom the beginning.

22


23/75

WORKING WITH STATA

If you are using STATA interactively, you must retype all of thecommands.

If you are using a do file, then you only need to correct thecommand containing the error and rerun the file.

For these reasons, you are strongly encouraged to use .do files.

23


24/75

WORKING WITH STATA

1. From the command window

2. Using a .do file

A text file that can be edited using any text editor (the

STATA do-file editor, notepad, word, etc), but you need

to save it as filename.do for STATA to read it

file do for STATA to execute all commands

24


25/75

25

Lets run our first STATA .do file


26/75

EXAMPLE: STATA1.DO

clear

log using caschool.log

use caschool.dta

describe

generate income = avginc*1000

summarize income

log close

exit

26


27/75

THELOG USINGCOMMAND

The log file is an output file

Creates and saves a log with all the actions performed by

STATA and all the results How do I view this log file?

From the drop-down menu: file log view and then

search for your filename, keeping in mind it has extension .log

27


28/75

LOADING YOUR DATA

3 ways to enter your data:

1. If your data is in STATA format, for example,

filename.dta, then enter: usefilename.dta

2. If your data is a comma delimited file, then enter: insheet

usingfilename.txt

3. Or simply copy paste your data from your .xls file.

Warning: This is the most troublesome and error-proneway of loading your data.

For other formats, can useStatTransfer software to convert

to STATA format28


29/75

USEFUL COMMANDS:

describewill list all the variables, their labels, types,

and tell you the number of observations

Two types of variables:

1. Numerical

2. String (usually appear in red in the data browser)

You can convert a string variable to numerical using the

destring. For example, destring var1, replace or destringvar1, force replace

** NO UNDO OPTION **29


30/75

MORE COMMANDS:

generate or gen creates a new variable

e.g. generate income = avginc*1000

e.g. generate log_inc = log(income)

e.g. gen inc_sq = (income)^2

30


31/75

MORE COMMANDS:

summarize or summ tells STATA to compute

summary statistics (mean, standard deviations,

etc.) for all variables

This is useful to identify outliers and get an idea of

your data!

e.g. summarize

e.g. summ income inc_sq

31


32/75

ENDING THE DO FILE

log close closes the file stata1.log that contains the

output.

The command exit tells STATA that the programhas ended.

32


33/75

33

Lets run our second STATA .do file


34/75


35/75

COMMENTS IN .DO FILE:

Star(*) STATA ignores the text that comes after *

These lines can be used to describe what the commandsare doing

Allows you to write comments (usually administrativecommands)

35


36/75

SOME USEFUL COMMANDS

# delimit;

Tells STATA that each STATA command ends with a semicolon.

Useful for long commands

Do not forget the ; and write this even after the comment lines

that start with *.

set more off

Ensures STATA executes all commands.

If code is too long, the output window might be filled, and STATA

will display --more-- at the bottom and not execute all commands

set memory 600m

Increases memory available for STATA to do work36


37/75

OTHER COMMANDS

tabulate shows the frequency and percent of each value of acertain variable in the dataset

e.g. tabulate county

generate ... if

e.g. generate teachers_new= teachers if teachers10

37


38/75


39/75

MORE COMMANDS

by performs whatever command is given for each categoryof variable

e.g. by county: summarize income by county, sort: summarize income

sort simply sorts data in ascending order (for descendingorder find gsort)

e.g. sort income e.g. sort county income

39


40/75

DELETING VARIABLES AND OBSERVATIONS

drop

use this command to delete variables or observations

e.g. drop avginc deletes average income variable

e.g. drop if teachers=7

40


41/75

BASIC STATISTICAL RELATIONSHIPS

Correlation:

correlate

Remember: Correlation coefficients which are close to -1 or +1indicate a strong linear correlation. Values close to o indicate a

weak linear correlation; 0 indicates no linear correlation at all. e.g. correlate income teachers

e.g. correlate income teachers computer

Regression:

reg performs OLS regression predicting value of dependent

variable from one or more independent variables

e.g. reg income teachers

e.g. reg income teachers computer41


42/75

GRAPHS: SCATTER PLOTS

e.g. graph twoway scatter income computer e.g. graph twoway scatter income computer || lfitci income computer

42

STATA graph editor


43/75

SAVING YOUR DATA

Saving data in Stata format:

(the usual way) file save as ... or

savefile name.dta

(on my PC the file is saved to C:\data)

Export your data in another format:

file export (choose file format)

43


44/75

SOME DATA CLEANING COMMANDS

reshape transforms (converts) data from long to wideformat or from wide to long format

Before using reshape, you need to determine whether thedata are in long or wide form.

Also determine the logical observation (i) and the

subobservation (j) by which to organize the data.

44


45/75


46/75

RESHAPE COMMANDS

Lets practice: use http://www.ats.ucla.edu/stat/stata/modules/kidshtwt, clear

Then save example2.dta

Ask yourself:

Q: What is the stem of the variable going fromwide to long?A: The stem is ht andwt

Q: What variable uniquely identifies an observation when it is in thewide form?A: famid andbirth together uniquely identify thewide observations.

Q: What do we want to call the variable which contains the suffix of ht (andwt)?A: Lets call the suffix age.

From wide to long:

reshape long stem-of-wide-vars, i(wide-id-var) j(var-for-suffix)

Example: browse list famid birth ht1 ht2 wt1 wt2 reshape long ht wt, i(famid birth) j(age) list famid birth ht wt

46


47/75

EGEN COMMAND

Extended generate (egen) is more powerful thanordinary gen

Examples:

egen age_mean = mean(age), by(year)

egen stdage = std(age)

47


48/75

LAGGED VARIABLES

[_n-1] tells STATA this is the previous observation

[_n-2] is 2 observations before

Examples:

First sort your data!

gen GDP_lagged= GDP[_n-1]

gen GDP_2= GDP[_n-2]

Other uses:Filling in missing data

by ID: replace education=1 if education[_n-1]==1 &education[_n+1]==1 & ID[_n-1]==ID[_n+1];

48


49/75

COLLAPSE COMMAND

Lets practice: use http://www.ats.ucla.edu/stat/Stata/modules/collapse.htm

Then save example3.dta

Example:

create one record per family (famid) with the average of age (avgage) andaverage weight (avgwt) within each family, and the number of kids (numkids)per family

collapse (mean) avgage=age avgwt=wt (count) numkids=birth, by(famid)

49


50/75

NEW DATA AFTER COLLAPSE

50

famid avgage avgwt numkids

1 6 40 32 5,333333 50 3

3 4 40 3


51/75

PRESERVING DATA

preserve tells STATA to keep your data in memory,so if your next commands modify it, you can comeback to your original data

restore gives you back your original data

Example: use data1.dta

preserve collapse (mean) age, by (family)

save data2.dta

restore

51


52/75

SIMPLE REGRESSION

Example:

use http://www.ats.ucla.edu/stat/stata/notes/hsb2

browse

regress science math female socst read

52


53/75

53

OUTPUT


54/75

54

OUTPUT

ANOVA table Model fit

Parameter estimates


55/75

ANOVA TABLE

Source: Looking at the breakdown of variance in the outcome variable,

these are the categories we examine:Model, Residual, and Total.

Total variance is partitioned into the variance which can be explained

by the independent variables (Model) and the variance which is not

explained by the independent variables (Residual, sometimes calledError).

SS: These are the Sum of Squares associated with the three sources of

variance: Total, Model and Residual.

df: These are the degrees of freedom associated with the sources of

variance.55


56/75

DF

The total variance has N-1 degrees of freedom. The model degrees of freedom

corresponds to the number of coefficients estimated minus 1. Including the

intercept, there are 5 coefficients, so the model has 5-1=4 degrees of freedom. The

Residual degrees of freedom is the DF total minus the DF model, 199-4=195.

DF is the number of free or linearly independent observations used in the

calculation of the statistic. DF of a statistic is the number of quantities that enter

into calculation of the statistic minus the number of constraints connecting these

quantities. as the number of independent pieces of information available to

estimate another piece of information.

This is the number of degrees of freedom is the number of independent

observations in a sample of data that are available to estimate a parameter of the

population from which that sample is drawn.

MS: These are the Mean Squares: the Sum of Squares divided by their respective DF. 56


57/75

57

OUTPUT


Parameter estimates


58/75

MODEL FIT

Number of obs: This is the number of observations used inthe regression analysis.

F(4, 195): This is the F-statistic. It is the Mean Square Model(2385.93019) divided by the Mean Square Residual

(51.0963039), yielding F=46.69. The numbers in parenthesesare the Model and Residual degrees of freedom from theprevious ANOVA table.

Prob > F: This is the p-value associated with the F-statistic. It is used in testing the null hypothesis that all of the

model coefficients are 0.

R-squared: This is the proportion of variance in thedependent variable (science) which can be explained by theindependent variables (math, female, socst and read).

58


59/75

MODEL FIT

R-squared is an overall measure of the strength of associationand does not reflect the extent to which any particular indep.variable is associated with the dependent variable.

Adj R-squared: This is an adjustmentof the R-squared that

penalizes the addition of extraneous predictors to the model. Adjusted R-squared is computed using the following formula:

1 - ((1 R2)((N - 1)/( N - k - 1)) where k is the number ofpredictors.

Root MSE: Root MSE is the standard deviation of the errorterm, and is the square root of the Mean Square Residual (orError).

59


60/75

60

OUTPUT


Parameter estimates


61/75

PARAMETER ESTIMATES

science: This column shows the dependent variable atthe top (science) with the predictor variables below it(math, female, socst, read and_cons).

The last variable (_cons) represents the constant or

intercept.Coef.: These are the values for the regression equation

for predicting the dependent variable from theindependent variable.

The regression equation can have the following form

Y(hat) =0+1X1 +2X2 +3X3 +4X461


62/75

PARAMETER ESTIMATES

The column estimates provide values for 0, 1, 2, 3 and 4.

science(predicted) = 12.32529 + .3893102 math + -2.009765 female+.0498443 socst+.3352998 read

math: The coefficient is .3893102. So for every unit increase in math, a.389 point increase in science is predicted, holding all other variablesconstant.

Be careful! Since female is coded 0/1 (0=male, 1=female), we interpretthe coefficient: the predicted science score would be 2 points lower for afemale than for a male, for a randomly chosen student.

62


63/75

PARAMETER ESTIMATES

socst: The coefficient for socst is .0498443. So for every unit increase in socst,we expect an approximately .05 point increase in the science score, holding allother variables constant.

read: The coefficient for read is .3352998. So for every unit increase in read, weexpect a .34 point increase in the science score.

t and P>|t|: These columns provide the t-value and 2-tailed p-value used intesting the null hypothesis that the coefficient (parameter) is 0.

Remember: In significance testing, the p-value is the probability of obtaining atest statistic at least as extreme as the one that was actually observed, assumingthat the null hypothesis is true. One often "rejects the null hypothesis" when the p-

value is less than the significance level (alhpa) which is often 0.01 or 0.05. Whenthe null hypothesis is rejected, the result is said to be statistically significant.

[95% Conf. Interval]: This shows a 95% confidence interval for the coefficient.

Remember: The coefficient will not be statistically significant if the confidenceinterval includes 0.

63


64/75

PREDICTED VALUES

After the regression, type predict yhat This command creates a new variable yhatwith the predicted values

for the dependant variable (science).

Next ...

Regression diagnostics is beyond the scope of our short intro course,but ...

Some issues:

heteroskedasticity (when disturbances do not all have the same variance),

autocorrelation (when disturbances are correlated with one another),

multicolinearity (two or more independent variables are approximatelylinearly related in the sample data)

64


65/75

DIAGNOSTICS

Lets check homoscedasticity of residuals

predict r, residuals

One of the main assumptions for the ordinary leastsquares regression is the homogeneity of variance ofthe residuals.

If the model is well-fitted, there should be no patternto the residuals plotted against the fitted values. If thevariance of the residuals is non-constant, then theresidual variance is said to be heteroscedastic.

65


66/75

DIAGNOSTICS

There are graphical and non-graphical methods fordetecting heteroscedasticity.

A commonly used graphical method is to plot theresiduals versus fitted (predicted) values. We do

this by issuing the rvfplot command.yline(0)puts a reference line at y=0.

rvfplot, yline(0)

66

DIAGNOSTICS


67/75

DIAGNOSTICS

estat imtest (White test)

estat hettest (Breusch-Pagan test)67


68/75

DIAGNOSTICS

White and Breusch-Pagan tests test the null hypothesisthat the variance of the residuals is homogenous.

If the p-value is very small, we would have to reject thehypothesis and accept the alternative hypothesis that the

variance is not homogenous. In this case, the evidence is against the null hypothesis

that the variance is homogeneous.

These tests are very sensitive to model assumptions, such

as the assumption of normality. So, it is a commonpractice to combine the tests with diagnostic plots to makea judgment on the severity of the heteroscedasticity and todecide if any correction is needed for heteroscedasticity

68


69/75

69


70/75

LINEAR REGRESSION WITH PANEL DATA

Declaring the data to be a panel:

Example, where data consists of many firms, eachobserved over 5 years

iis Firm ;

tis Year ;

xt are the prefix for the commands in this class

xtreg should be used for regressions with panel

data

70


71/75

FIXED EFFECTS:

yit = a + xitb + vi + eiti.e. xtreg lnc lny, fe

Equivalent to including a dummy variable for eachcase (i.e. firm). But not really!

71


72/75

RANDOM EFFECTS (RE)

If you think some omitted variables may beconstant over time but vary between cases, andothers may be fixed between cases but vary overtime, then you can include both types by using

random effects. Stata's RE estimator is a weighted average of fixed

and between effects

i.e. xtreg lnc lny, re

72

C OOS G B F


73/75

CHOOSING BETWEEN FIXED ANDRANDOM EFFECTS

running a Hausman test: estimate the FE model, save the coefficients, estimate

the RE model, and then do the comparison.

Example: xtreg dependentvar var1 var2 var3 ... , fe

estimates store fixed

xtreg dependentvar var1 var2 var3 ... , re

estimates store random

hausman fixed random

If significant p-value, use FE

Source:http://dss.princeton.edu/online_help/analysis/panel.htm

73


74/75

TIME SERIES DATA

tsset declare data to be time-series data

Examples:

tsset time, yearly (For an annual time series, timetakes on values such as 1990, 1991, ...)

tsset company year, yearly (For yearly panel data,variable company being the panel ID variable and yearbeing a four-digit calendar year)

74


75/75

QUESTIONS

Ensar Sehic, PhD, Assistant Professor

Academic Unit for Quantitative Economics

University of Sarajevo, School of Economics and Business

Trg Oslobodjenja 1, office #69, 71000 Sarajevo, B&H

Tel: +387 33 253 767

Mob: +387 62 225 123

Email: [email protected]: ensar.sehic

stata prirucnik

Documents