[Gretl-users] Re: Durbin Watson p-value
On Mon, 9 Nov 2020, ANA JESUS LOPEZ MENENDEZ wrote:
Good morning
We are not quite sure about the interpretation of the Durbin
Watson p-value.
According to the user`s guide “an approximate P-value for the null
of no serial correlation (rho= 0) against the alternative of rho>
0 may be available via the accessor $dwpval”.
However when using this Gretl option it apparently provides the
left-tail probability, for example
Durbin-Watson = 1,38 p = 0,003
Durbin-Watson = 2,33919 p = 0,785174
Assuming this, the Durbin Watson two-tailed test (rho= 0 against
rho different from zero) should consider the p value:
2p in case DW is lower than 2
2(1-p) for DW higher than 2
Gretl is providing what it claims to provide, namely the P-value for
a one tailed test (rho = 0 versus rho greater than zero). DW < 2
suggests rho > 0 so the small P-value you quote for DW = 1.38 looks
plausible, and the large P-value for DW = 2.34 is likewise
plausible.
But if you want a two tailed test then your proposal is right.
Allin Cottrell