Main Content

Specification Testing

Identify the parametric form of a model

Econometrics Toolbox™ has a variety of functions that describe the statistical properties of a series or multiple series. The functionality ranges form providing visual diagnostics, such as the autocorr function, which plots a correlogram of a series, through conducting statistical hypothesis tests, such as the archtest function, which tests a series for heteroscedasticity. These diagnostics help you identify a parametric form for the series.

The Econometric Modeler app uses many of these function to enable you to characterize your series interactively. However, for full flexibility in your workflow, call the functions at the command line.

Apps

Econometric ModelerAnalyze and model econometric time series

Functions

expand all

adftestAugmented Dickey-Fuller test
kpsstestKPSS test for stationarity
lmctestLeybourne-McCabe stationarity test
pptestPhillips-Perron test for one unit root
vratiotestVariance ratio test for random walk
i10testPaired integration and stationarity tests
autocorrSample autocorrelation
parcorrSample partial autocorrelation
crosscorrSample cross-correlation
corrplotPlot variable correlations
lbqtestLjung-Box Q-test for residual autocorrelation
collintestBelsley collinearity diagnostics
gctestBlock-wise Granger causality and block exogeneity tests
archtestEngle test for residual heteroscedasticity
chowtestChow test for structural change
cusumtestCusum test for structural change
recregRecursive linear regression
collintestBelsley collinearity diagnostics
egcitestEngle-Granger cointegration test
jcitestJohansen cointegration test
jcontest Johansen constraint test

Topics

Stationarity

Correlation

Heteroscedasticity

Structural Change

Collinearity

Cointegration