02-02-2012 02:48 PM
Correcting for heteroskedasticity using the HETERO statement after the MODEL statement. My problem is I cannot figure a way to test for autorcorrelation in this model. Without the HETERO statement /dw will give the durbin-watson. My understanding is that the GARCH model is the only way to correct for both.
02-02-2012 04:48 PM
Hello - not sure if this helps, but this statement from documention might be useful: "For heteroscedastic regression models without GARCH effects, the errors are assumed to be uncorrelated — the heteroscedasticity models specified by the HETERO statement cannot be combined with an autoregressive model for the errors. Thus, when a HETERO statement is used, the NLAG= option cannot be specified unless the GARCH= option is also specified." (http://support.sas.com/documentation/cdl/en/etsug/63939/HTML/default/viewer.htm#etsug_autoreg_sect01...)