Testing autocorrelation and partial autocorrelation: Asymptotic methods versus resampling techniques

Abstract

Autocorrelation and partial autocorrelation, which provide a mathematical tool to understand repeating patterns in time series data, are often used to facilitate the identification of model orders of time series models (e.g., moving average and autoregressive models). Asymptotic methods for testing autocorrelation and partial autocorrelation such as the 1/T approximation method and the Bartlett's formula method may fail in finite samples and are vulnerable to non-normality. Resampling techniques such as the moving block bootstrap and the surrogate data method are competitive alternatives. In this study, we use a Monte Carlo simulation study and a real data example to compare asymptotic methods with the aforementioned resampling techniques. For each resampling technique, we consider both the percentile method and the bias-corrected and accelerated method for interval construction. Simulation results show that the surrogate data method with percentile intervals yields better performance than the other methods. An R package pautocorr is used to carry out tests evaluated in this study.

Seasonal Changes of Serum Gonadotropins and Testosterone in Men Revealed by a Large Data Set of Real-World Observations Over Nine Years

“…Testosterone, LH and FSH distribution was evaluated considering the date of examination by autocorrelation analyses. Autocorrelation functions were first calculated as lag 1, which is the correlation between adjacent observations in a time series (15,16). Autocorrelation function represents the statistical approach to measure the linear relationship between an observation at specific time and the observations at previous times.…”

Analisis Efisiensi Penggunaan Faktor-Faktor Produksi Usahatani Cabai Rawit Di Desa Girikulon Kecamatan Secang Kabupaten Magelang

“…Jika nilai VIF < 10 dan sebaliknya maka tidak terjadi multikolinieritas (Setyadharma, 2010). Uji Autokorelasi bertujuan untuk menguji apakah terdapat korelasi antara kesalahan pengganggu pada periode t dengan periode t-1 atau sebelumnya didalam model regresi (Chen, 2016;Ke & Zhang, 2018) Hal tersebut dapat dilihat melalui nilai residual (prediction error) dari uji Durbin-Watson (Durbin & Watson, 1950;Vinod, 1973) Apabila uji DW menunjukkan angka -2< dw <2 maka tidak terjadi autokorelasi (Gujarati et al, 2010). Uji heteroskedastisitas bertujuan untuk mengetahui apakah dalam suatu model regresi terdapat perbedaan atau persamaan varians dari residual satu pengamatan ke pengamatan yang lain (Carapeto & Holt, 2003;Shen, Cui, & Wang, 2014).…”

Trends on Modern Family Planning Methods in Abuja, Nigeria (2010 - 2021)

“…Autocorrelation and Partial autocorrelation are the time series techniques to measure the linear relationship between lagged values of the time series. The higher the deviation of these coefficients from zero, indicates more dependency of the series at a specific time with its lag values (18,19).…”