Identifying trends nature in time series using autocorrelation functions and stationarity tests

 

International Journal of Economics and Econometrics, vol. 14, n°1 (2024) pp.1-22

M. Boutahar and M. Royer Carenzi

 

 

 

Appendix

 

 

 

Supplementary

 

 

R Code :

 

Autocorrelation function with global test and Sidack correction

 

Function_ acfG.R

 

Example of acfG use

 

 

Unit root test with OPP test

 

Function_ opp.test.R

 

Example of opp.test use

 

 

Trend diagnosis between (detT,1) (detT,2) (stoT,1) and (stoT,2) models

 

Function_ trend.diag.tests.R

 

Example of trend.diag.tests use

 

 

Trend diagnosis between (detT,d) and (stoT,d) models

 

Function_ trend.diag.high.R 

 

Example of trend.diag.high use

 

 

 

Data and associated scripts :

 

Auxiliary functions for data stydy

 

Function season.R

 

Function tsdiag.Arma.R

 

 

Money Stock in USa

 

MoneyStock.csv

 

Script_MoneyStock.R

 

 

 

 

CO2 atmospheric

 

CO2_Atmosph.csv

 

Script_CO2_Atmosph.R

 

Information criteria for all processes SARMA(p,q)(P,Q)[12] with p,q<3

NA means that R function Arima() from package forecast did not converge

 

ModSelection_SARMA_det2.csv

 

ModSelection_SARMA_sto1.csv