thanks. i'll have to check out hamilton again. it has an amazing amount of information but it's been a LONG while<br />since i looked at it. I also spelled your name wrong so I apologize for that.<br /><br /><br /><br /><br /><p>On Jun 22, 2009, <strong>Matthieu Stigler</strong> <matthieu.stigler@gmail.com> wrote: </p><div class="replyBody"><blockquote style="border-left: 2px solid #267fdb; margin: 0pt 0pt 0pt 1.8ex; padding-left: 1ex">Hi<br /><br />Yes dependance of regressor and errors has the effect that your <br />estimator is biased. Hamilton (p 215) discusses the case of AR() with <br />iid errors:<br /><br />"the OLS coefficient gives a biased estimate in case of an autoregression <br />and the standard t and F statistic can only be justified asymptotically. "<br /><br /><br />So as you point right out, normal distribution instead of student should <br />be used for the p-values! (I'm not sure whether student distribution <br />can't be used if you make the assumption that the errors are Gaussian. )<br /><br />Note however that those results are derived for the OLS estimator, which <br />is not the estimator by default in ar().<br /><br />For small sample p-values, bootstrap methods could be used. Introductory <br />discussion can be found in Maddala p 323 (available on google books, <br />type: "the procedure for the generation of the bootstrap samples").<br /><br />Matthieu<br /><br /><a href="mailto:markleeds@verizon.net" target="_blank" class="parsedEmail">markleeds@verizon.net</a> a écrit :<br />> hi matthew: maybe someone can say more including yourself but one <br />> doesn't have independence of error term<br />> and regressor in an AR so I'm not certain that the t-test in the arima <br />> model is valid ? I imagine that hamilton or<br />> some other book must talk about the validity of the assumptions but I <br />> don't have them in my apt at the moment.<br />><br />><br />><br />> On Jun 22, 2009, *Matthieu Stigler* <<a href="mailto:matthieu.stigler@gmail.com" target="_blank" class="parsedEmail">matthieu.stigler@gmail.com</a>> wrote:<br />><br />> Hi<br />><br />> as you can see:<br />><br />> methods(class="ar")<br />><br />> there is no summary() nor confint() function for class ar :-(<br />><br />> But if you check values returnd by ar:<br />><br />> str(ar(lh))<br />><br />><br />> you see there is: asy.var.coef<br />> so with:<br />><br />> sqrt(diag(ar(lh)$asy.var.coef))<br />><br />><br />> You get standard errors and can compute the corresponding p-values.<br />><br />> Mat<br />><br />> FMH a écrit :<br />> > Dear All,<br />> ><br />> > I used an AR(1) model to explain the process of the stationary<br />> residual and have used an 'ar' command in R. From the results, i<br />> tried to extract the standard error and p-value for the estimated<br />> parameter, but unfortunately, i never find any way to extract it<br />> from the output.<br />> ><br />> > What i did was, i assigned the residuals into the 'residual'<br />> object in R and used an 'ar' function as below.<br />> ><br />> ><br />> >> residual <- residuals<br />> >> ar(residual, aic = TRUE, method = "mle", order.max = 1)<br />> >><br />> ><br />> > Could someone help me to extract the stadard error and the<br />> p-value for the estimated parameter, please?<br />> ><br />> > Thank you<br />> ><br />> > Fir<br />> ><br />> ><br />> ><br />> > [[alternative HTML version deleted]]<br />> ><br />> ><br />> ><br />> ------------------------------------------------------------------------<br />> ><br />> > _______________________________________________<br />> > <a href="mailto:R-SIG-Finance@stat.math.ethz.ch" target="_blank" class="parsedEmail">R-SIG-Finance@stat.math.ethz.ch</a><br />> <mailto:<a href="mailto:R-SIG-Finance@stat.math.ethz.ch" target="_blank" class="parsedEmail">R-SIG-Finance@stat.math.ethz.ch</a>> mailing list<br />> > <a href="https://stat.ethz.ch/mailman/listinfo/r-sig-finance" target="_blank" class="parsedLink">https://stat.ethz.ch/mailman/listinfo/r-sig-finance</a><br />> > -- Subscriber-posting only.<br />> > -- If you want to post, subscribe first.<br />><br />> _______________________________________________<br />> <a href="mailto:R-SIG-Finance@stat.math.ethz.ch" target="_blank" class="parsedEmail">R-SIG-Finance@stat.math.ethz.ch</a><br />> <mailto:<a href="mailto:R-SIG-Finance@stat.math.ethz.ch" target="_blank" class="parsedEmail">R-SIG-Finance@stat.math.ethz.ch</a>> mailing list<br />> <a href="https://stat.ethz.ch/mailman/listinfo/r-sig-finance" target="_blank" class="parsedLink">https://stat.ethz.ch/mailman/listinfo/r-sig-finance</a><br />> -- Subscriber-posting only.<br />> -- If you want to post, subscribe first.<br />><br /><br /></blockquote></div>