Estimators and tests: summary

Table 13-2 shows the estimators available under the Model menu in gretl's main window. The corresponding script command (if there is one available) is shown in parentheses. For details consult the command's entry in Chapter 13.

Table 13-2. Estimators

EstimatorComment
Ordinary Least Squares (ols)The workhorse estimator
Weighted Least Squares (wls)Heteroskedasticity, exclusion of selected observations
HCCM (hccm)Heteroskedasticity corrected covariance matrix
Heteroskedasticity corrected (hsk)Weighted Least Squares based on predicted error variance
Cochrane–Orcutt (corc)First-order autocorrelation
Hildreth–Lu (hilu)First-order autocorrelation
Prais–Winsten (pwe)First-order autocorrelation
Autoregressive Estimation (ar)Higher-order autocorrelation (generalized Cochrane–Orcutt)
ARMAX (arma)Time-series model with ARMA error
GARCH (garch)Generalized Autoregressive Conditional Heteroskedasticity
Vector Autoregression (var)Systems of time-series equations
Cointegration test (coint)Long-run relationships between series
Two-Stage Least Squares (tsls)Simultaneous equations
Nonlinear Least Squares (nls)Nonlinear models
Logit (logit)Binary dependent variable (logistic distribution)
Probit (probit)Binary dependent variable (normal distribution)
Tobit (tobit)Truncated dependent variable
Logistic (logistic)OLS, with logistic transformation of dependent variable
Least Absolute Deviation (lad)Alternative to Least Squares
Rank Correlation (spearman)Correlation with ordinal data
Pooled OLS (pooled)OLS estimation for pooled cross-section, time series data
Multiple precision OLS (mpols)OLS estimation using multiple precision arithmetic

Table 13-3 shows the tests that are available under the Tests menu in a model window, after estimation.

Table 13-3. Tests for models

TestCorresponding command
Omit variables (F-test if OLS)omit
Add variables (F-test if OLS)add
Sum of coefficients (t-test if OLS)coeffsum
Nonlinearity (squares)lmtest --squares
Nonlinearity (logs)lmtest --logs
Nonlinearity (Ramsey's RESET)reset
Heteroskedasticity (White's test)lmtest --white
Influential observationsleverage
Autocorrelation up to the data frequencylmtest --autocorr
Chow (structural break)chow
CUSUM (parameter stability)cusum
ARCH (conditional heteroskedasticity)arch
Normality of residualtestuhat
Panel diagnosticshausman

Table 13-4 shows the correspondence between the long-form option flags used in the command reference above and the short versions.

Table 13-4. Long- and short-form options

CommandOptionEffectShort form
arma--x-12-arimaestimate with X-12-ARIMA-x
 --verboseprint iteration details-v
coint2--verboseprint details of VARs-v
eqnprint, tabprint--completecomplete TeX document-o
fcasterr--plotshow graph-o
gnuplot--with-linesplot with lines-o
 --with-impulsesplot with impulses-m
 --suppress-fitteddon't show fitted line-s
 --dummyfactor separation-z
import--box1import BOX1 data-o
leverage--savesave values to dataset-s
lmtest--logsnon-linearity (logs)-l
 --squaresnon-linearity (squares)-s
 --whiteWhite's test (heteroskedasticity)-w
 --autocorrserial correlation-m
meantest--unequal-varsassume unequal variances-o
leverage--savesave values to dataset-s
ols--robustrobust standard errors-r
 --vcvprint covariance matrix-o
 --quietdon't print results-q
outfile--writeopen file for writing-w
 --appendappend to existing file-a
 --closeclose file-c
panel--time-seriesstacked time series-s
 --cross-sectionstacked cross-sections-c
pca--savesave useful eigenvectors-s
 --save-allsave all eigenvectors-a
pergm--bartlettuse Bartlett lag window-o
plot--one-scaledon't scale variables-o
print--byobsvariables in columns-o
 --tenuse 10 significant figures-t
smpl--dummyrestrict using dummy var-o
 --no-missingonly complete observations-m
 --restrictuse boolean criterion-r
spearman--verboseprint original, ranked data-o
square--crossgenerate cross-products-o
store--csvcomma-separated values-c
 --traditionaltraditional ESL format-t
 --gnu-octaveGNU Octave format-m
 --gnu-RGNU R format-r
 --gzippedgzip compression-z
var--quietdon't print all results-q
Model commands--vcvprint covariance matrix-o