ADF檢驗(yàn)中滯后長(zhǎng)度的選擇——基于ARIMA

ADF檢驗(yàn)中滯后長(zhǎng)度的選擇——基于ARIMA(0,1,q)過程的模擬證據(jù)

【摘要】在進(jìn)行ADF檢驗(yàn)時(shí)如何確定一個(gè)最優(yōu)的滯后長(zhǎng)度一直是研究者們關(guān)注的問題。最近的研究表明，不同的滯后長(zhǎng)度選擇方法對(duì)ADF檢驗(yàn)的統(tǒng)計(jì)推斷影響很大。本文在已有研究的基礎(chǔ)上，模擬了更為一般的ARIMA(0,1,q)過程，分析了在不同的數(shù)據(jù)生成過程、檢驗(yàn)式以及樣本容量下，各種滯后長(zhǎng)度選擇方法對(duì)ADF檢驗(yàn)功效和實(shí)際檢驗(yàn)水平的影響，最后認(rèn)為修正的信息準(zhǔn)則通常具有較合理的實(shí)際檢驗(yàn)水平，而從一般到特殊法具有更為穩(wěn)健的ADF檢驗(yàn)性質(zhì)。

關(guān)鍵詞 ADF檢驗(yàn) 滯后長(zhǎng)度 信息準(zhǔn)則 修正的信息準(zhǔn)則 從一般到特殊法

Abstract: The optimal lag length in estimating Augmented Dickey-Fuller statistics have been concentrated on for years. Previous research indicated that different leg length selection models affect a lot on the statistical inference of ADF test. Based on all the researches available, this paper simulates a more general ARIMA(0,1,q) process and analyzes the influence of lag length selection criterions to the size and power of the ADF test with different data generating processes, ADF regressions, and sample sizes. Finally, it is proved that the Modified Information Criteria always shows a more proper size and the General to Special Criteria has more robust properties in ADF test.

Keywords: ADF test Lag Length Information Criteria Modified Information Criteria General to Specific