Confusing result with AIC and ACF
One week, still no suggestion. Is my question not understandable or answerable? Regards,
RON70 wrote:
Hi, I have a strange problem with following dataset : -0.075851693 -0.046125504 -0.009117161 0.025569817 0.034882743 0.073671497 0.063805297 0.062306796 0.072343820 0.058354121 -0.007635359 0.086790779 0.085487789 0.113577103 0.021293381 0.089423068 0.090485998 0.128847827 0.011859335 0.058794744 0.065909368 0.020887431 0.085387467 0.097375525 0.108981417 0.044289044 0.071428571 0.052430556 0.056307049 0.041957314 If I see the ACF then, it seems that this values are random. However next I fit two regressions and get the AIC values : 1. regression of y (above series) on : y[-1], y[-2], y[-3], y[-4] and x[-1], x[-2], x[-3], x[-4] 2. regression of y on y[-1], y[-2], y[-3] and x[-1], x[-2], x[-3], x[-4] Here y[-p] is the p-th lagged value. and x is some other variable. AIC for those regressions are : -6.673 and -6.636. This means 4-th lag of y has some explanatory power on y. Therefore this result is coming confusing when I compare with ACF figures [which tells y is random] Can ppl here suggest me what inference I should make on y? Regards,
View this message in context: http://www.nabble.com/Confusing-result-with-AIC-and-ACF-tp21563337p21678634.html Sent from the Rmetrics mailing list archive at Nabble.com.