.- help for ^durbinh^ (SSC distribution 11 August 2002) .-Calculate the Durbin-Watson h statistic after @regress@ or @newey@ --------------------------------------------------------------

^durbinh^ [, force]

^durbinh^ is for use after ^regress^ or ^newey^; see help @regress@ or @newey@.

^durbinh^ is for use with time-series data. You must ^tsset^ your data before using ^durbinh^; see help @tsset@.

Description -----------

^durbinh^ computes the Durbin (1970) 'h' statistic to test for first-order seri > al correlation in the disturbances after @regress@ when the regressor list contain > s one or more lagged values of the dependent variable. In this case, the Durbin- Watson statistic (@dwstat@) is inappropriate, as it is biased toward 2.0 (non- rejection). Likewise, the Box-Pierce portmanteau test (@wntestq@) is not appropriate in the presence of stochastic regressors. The Durbin "h" test regresses the OLS residuals on their own lags and the original regressor list. The coefficient on the lagged residual series, in ratio to its estimated standard error, is distributed 't' under the null of zero autocorrelation in the error process. This test (a special case of the Breusch-Godfrey LM test @bgtest@) is asymptotically equivalent to the original test proposed by Durbin, as discussed in Greene (2000, Ch. 13). Unlike the original test, this test is computable for all data.

The command displays the estimated coefficient, 't-statistic', and P-value, and places values in the return array. @return list@ for details.

Options ------- The ^force^ option specifies that the test is to be allowed after @regress ..., robust@ and @newey@; by default it is not allowed. In these cases the test statistic is exactly the same as if standard OLS were performed using @regress@. This is true because the test is based on the residuals from the regression and they are the same for @regress@, @regress ..., robust@, and @newey@. There is no way the test can utilize any of the information used to make the standard errors robust after estimation with @newey@ or @regress ..., robust@. It is best to view the test as a test of the OLS disturbances whether estimation is by @regress@, @regress ..., robust@, or @newey@.

Examples --------

. ^use http://fmwww.bc.edu/ec-p/data/macro/wgmacro.dta^ . ^regress consumption L.consumption L(1/4).income^ . ^durbinh^ . ^g Lincome = L.income^ . ^g Lconsump = L.consumption^ . ^newey consumption Lconsump Lincome, lag(4)^ . ^durbinh, force^

References ----------

Durbin, J. "Testing for serial correlation in least squares regression when some of the regressors are lagged dependent variables." Econometrica, 38, 1970, 410-421. Greene, W. Econmetric Analysis. 4th ed., 2000. New York: Prentice-Hall.

Authors -------

Christopher F Baum, Boston College, USA baum@@bc.edu

Vince Wiggins, Stata Corporation vwiggins@@stata.com Also see --------

Manual: ^[R] regress^, ^[R] regression diagnostics^ On-line: help for @regdiag@, @regress@, @time@, @tsset@; @dwtest@, @newey@, @bgtest@ (if installed)