[R-sig-Geo] predict.spautolm

[Bjarke Christensen]

Roger Bivand wrote:
>On Thu, 24 Sep 2009, Bjarke Christensen wrote:
>> Roger Bivand wrote:
>>> If you want simulations around
>>> those point estimates, you can introduce spatial autocorrelation with
the
>>> lambda term, but lambda will not impact the predictions unless the
model
>>> was misspecified, I believe.
>>
>> I'm not quite sure I understand why. If lambda does not impact the
>> predictions, would its estimate not converge to zero?
>
>Not the estimate of lambda, but the expectation of the spatially
>autocorrelated errors will (I think) be zero - it is their covariance that

>isn't \sigma^2 I.

I follow your thinking. My rationale was that while the expectation of the
errors is zero globally, it might be non-zero locally because of the
spatial autocorrelation. My current application is for imputing missing
observations (which is also why I wanted to do out-of-sample validation
first). I will check out the references you gave. Thanks for helping.

Bjarke Christensen