A Max-Correlation White Noise Test for Weakly Dependent Time Series (zip file)

Matlab code for Hill, J. B. and K. Motegi (2017, updated 2018). A Max-Correlation White Noise Test for Weakly Dependent Time Series, technical report. The main code generate latex tables of rejection frequencies automatically. The code includes the bootstrap max-correation test with automatic lag selection.


Tail Index Estimation with Robust Nonparametric Inference

Gauss code for Hill, J.B. (2010). On Tail Index Estimation for Dependent, Heterogeneous Data, Econometric Theory 26, 1398-1436.


Least Tail-Trimmed Squares

Gauss code for Hill, J.B. (2012). Least Tail-Trimmed Squares for Infinite Variance Autoregresions, Journal of Time Series Analysis 34, 168-186.


Multi-Step Ahead Rolling Window Causality Tests

Gauss code for Hill, J.B. (2007). Efficient Tests of Long-Run Causation in Trivariate VAR Processes with a Rolling Window Study of the Money-Income Relationship, Journal of Applied Econometrics 22, 747-765.


Rolling Window Bivariate Causality Tests

This program is a simplified version of the above program, designed for a bivariate process W = [X,Y]’ where X and Y may have any dimension.