8時(shí)間序列回歸模型——r實(shí)現(xiàn)(編輯修改稿)
2024-08-31 23:28 本頁(yè)面
【文章內(nèi)容簡(jiǎn)介】 AO = seq(y) == 10))Coefficients: ar1 intercept AO . sigma^2 estimated as : log likelihood = , aic = detectAO(m2)[1] No AO detected detectIO(m2)[1] No IO detected 比較有無(wú)異常值的兩模型再次進(jìn)行異常值探測(cè)時(shí)，沒(méi)有發(fā)現(xiàn)異常值，驗(yàn)證最初序列異常出現(xiàn)在10的猜測(cè)對(duì)比模型1和2的擬合效果 tsdiag(m2) tsdiag(m1)雖然模型二的殘差通過(guò)引入異常值后正太性是顯性的，但是其acf和P值結(jié)果顯示引入MA（1）是必要的。 重新擬合適當(dāng)模型 m3=arima(y,order=c(1,0,1),xreg=(AO=seq(y)==10)) detectAO(m3)[1] No AO detected detectIO(m3)[1] No IO detected tsdiag(m3) m3Call:arima(x = y, order = c(1, 0, 1), xreg = (AO = seq(y) == 10))Coefficients: ar1 ma1 intercept AO . sigma^2 estimated as : log likelihood = , aic = 模型的擬合效果是顯著提高。Acf和P 值檢驗(yàn)也一步通過(guò)。 plot(y,type=39。b39。) arrows(40,7,11,length=,angle=30) 另一個(gè)現(xiàn)實(shí)例子數(shù)據(jù)包中的co2 =arima(co2,order=c(0,1,1),seasonal=list(order=c(0,1,1),period=12)) Call:arima(x = co2, order = c(0, 1, 1), seasonal = list(order = c(0, 1, 1), period = 12))Coefficients: ma1 sma1 . sigma^2 estimated as : log likelihood = , aic = detectAO()[1] No AO detected detectIO() [,1]ind lambda1 擬合含有新息異常的模型 =arimax(co2,order=c(0,1,1),seasonal=list(order=c(0,1,1),period=12),io=c(57)) Call:arimax(x = co2, order = c(0, 1, 1), seasonal = list(order = c(0, 1, 1), period = 12), io = c(57))Coefficients: ma1 sma1 IO57 . sigma^2 estimated as : log likelihood = , aic = 模型顯示AIC相比之前模型一更小了。而且IO效應(yīng)的P 值=3 偽相關(guān)在時(shí)間序列中引入?yún)f(xié)變量，如非洲牧草產(chǎn)量通常與某些氣候指標(biāo)密切相關(guān)，在這種發(fā)問(wèn)下在通過(guò)在時(shí)間序列模型中納入相關(guān)的協(xié)變量，將有助于更好的了解基礎(chǔ)過(guò)程以及得到更為準(zhǔn)確的預(yù)測(cè)。 模擬數(shù)據(jù)(12345)X=rnorm(105)Y=zlag(X,2)+.5*rnorm(
高考資料相關(guān)推薦
鄂ICP備17016276號(hào)-1