Type: | Package |
Title: | Testing Zero Correlation |
Version: | 0.3.0 |
Description: | Computes the test statistics for examining the significance of autocorrelation in univariate time series, cross-correlation in bivariate time series, Pearson correlations in multivariate series and test statistics for i.i.d. property of univariate series given in Dalla, Giraitis and Phillips (2022), https://www.cambridge.org/core/journals/econometric-theory/article/abs/robust-tests-for-white-noise-and-crosscorrelation/4D77C12C52433F4C6735E584C779403A, https://elischolar.library.yale.edu/cowles-discussion-paper-series/57/. |
License: | GPL-3 |
Encoding: | UTF-8 |
Imports: | stats, ggplot2, scales, reshape2, forcats, knitr, methods, xts, zoo |
Suggests: | testthat, rmarkdown |
VignetteBuilder: | knitr |
RoxygenNote: | 7.3.2 |
NeedsCompilation: | no |
Packaged: | 2025-06-12 17:18:45 UTC; drvio |
Author: | Violetta Dalla [aut, cre], Liudas Giraitis [aut], Peter C. B. Phillips [aut] |
Maintainer: | Violetta Dalla <vidalla@econ.uoa.gr> |
Repository: | CRAN |
Date/Publication: | 2025-06-12 17:30:02 UTC |
Testing zero autocorrelation
Description
The function ac.test computes the test statistics for examining the null hypothesis of zero autocorrelation for univariate time series given in Dalla, Giraitis and Phillips (2022).
Usage
ac.test(x, max.lag, m0 = 1, alpha = 0.05, lambda = 2.576,
plot = TRUE, var.name = NULL, scale.font = 1)
Arguments
x |
A numeric vector or a univariate numeric time series (ts, xts, zoo) object or a data frame variable. |
max.lag |
Maximum lag at which to calculate the test statistics. |
m0 |
Minimum lag at which to calculate the cumulative test statistics. Default is 1. |
alpha |
Significance level for hypothesis testing used in the plots. Default is 0.05. |
lambda |
Threshold in |
plot |
Logical. If TRUE, 1) the sample autocorrelations with their confidence bands are plotted and 2) the cumulative test statistics with their critical values are plotted. Default is TRUE. Can be a logical vector for each of the plots 1)-2). |
var.name |
NULL or a character string specifying the variable name. If NULL and x has name, the name of x is used. If NULL and x has no name, the string "x" is used. Default is NULL. |
scale.font |
A positive number indicating the scaling of the font size in the plots. Default is 1. |
Details
The standard t
and robust \widetilde{t}
statistics are for testing the null hypothesis H_0:\rho_k=0
at lags k=1,...,max.lag
,
and the standard LB
and robust \widetilde{Q}
statistics are for testing the null hypothesis H_0:\rho_{m_0}=...=\rho_m=0
at lags m=m_0,...,max.lag
,
where \rho_k
denotes the autocorrelation of x_t
at lag k
.
Value
An object of class "ac.test", which is a list with the following components:
lag |
The lags of the sample autocorrelations. |
ac |
The sample autocorrelations. |
scb |
The lower and upper limit of the confidence bands based on the standard test statistics. |
rcb |
The lower and upper limit of the confidence bands based on the robust test statistics. |
t |
The |
pvt |
The p-values for the |
ttilde |
The |
pvttilde |
The p-values for the |
lagc |
The lags of the cumulative test statistics. |
lb |
The |
pvlb |
The p-values for the |
qtilde |
The |
pvqtilde |
The p-values for the |
alpha |
Significance level for hypothesis testing used in the plots. |
varname |
The variable name used in the plots/table. |
Note
Missing values are not allowed.
Author(s)
Violetta Dalla, Liudas Giraitis and Peter C. B. Phillips
References
Dalla, V., Giraitis, L. and Phillips, P. C. B. (2022). "Robust Tests for White Noise and Cross-Correlation". Econometric Theory, 38(5), 913-941, doi:10.1017/S0266466620000341. Cowles Foundation, Discussion Paper No. 2194RS, https://elischolar.library.yale.edu/cowles-discussion-paper-series/57/.
Giraitis, L., Li, Y. and Phillips, P. C. B. (2024). "Robust Inference on Correlation under General Heterogeneity". Journal of Econometrics, 244(1), 105691, doi:10.1016/j.jeconom.2024.105691.
Examples
x <- rnorm(100)
ac.test(x, max.lag = 10)
Testing zero cross-correlation
Description
The function cc.test computes the test statistics for examining the null hypothesis of zero cross-correlation for bivariate time series given in Dalla, Giraitis and Phillips (2022).
Usage
cc.test(x, y, max.lag, m0 = 0, alpha = 0.05, lambda = 2.576,
plot = TRUE, var.names = NULL, scale.font = 1)
Arguments
x |
A numeric vector or a univariate numeric time series (ts, xts, zoo) object or a data frame variable. |
y |
A numeric vector or a univariate numeric time series (ts, xts, zoo) object or a data frame variable. |
max.lag |
Maximum lag at which to calculate the test statistics. |
m0 |
Minimum lag at which to calculate the cumulative test statistics. Default is 0. |
alpha |
Significance level for hypothesis testing used in the plots. Default is 0.05. |
lambda |
Threshold in |
plot |
Logical. If TRUE, 1) the sample cross-correlations with their confidence bands are plotted and 2) the cumulative test statistics with their critical values are plotted. Default is TRUE. Can be a logical vector for each of the plots 1)-2). |
var.names |
NULL or a character string specifying the variable names. If NULL and x,y have names, the names of x,y are used. If NULL and x,y have no names, the string c("x","y") is used. Default is NULL. |
scale.font |
A positive number indicating the scaling of the font size in the plots. Default is 1. |
Details
The standard t
and robust \widetilde{t}
statistics are for testing the null hypothesis H_0:\rho_k=0
at lags k=-max.lag,...,-1,0,1,max.lag
,
and the standard HB
and robust \widetilde{Q}
statistics are for testing the null hypothesis H_0:\rho_{m_0}=...=\rho_m=0
at lags m=-max.lag,...,-1,0,1,max.lag
,
where \rho_k
denotes the cross-correlation of x_t
and y_{t-k}
at lag k
.
Value
An object of class "cc.test", which is a list with the following components:
lag |
The lags of the sample cross-correlations. |
cc |
The sample cross-correlations. |
scb |
The lower and upper limit of the confidence bands based on the standard test statistics. |
rcb |
The lower and upper limit of the confidence bands based on the robust test statistics. |
t |
The |
pvt |
The p-values for the |
ttilde |
The |
pvtttilde |
The p-values for the |
lagc |
The lags of the cumulative test statistics. |
hb |
The |
pvhb |
The p-values for the |
qtilde |
The |
pvqtilde |
The p-values for the |
alpha |
Significance level for hypothesis testing used in the plots. |
varnames |
The variable names used in the plots/table. |
Note
Missing values are not allowed.
Author(s)
Violetta Dalla, Liudas Giraitis and Peter C. B. Phillips
References
Dalla, V., Giraitis, L. and Phillips, P. C. B. (2022). "Robust Tests for White Noise and Cross-Correlation". Econometric Theory, 38(5), 913-941, doi:10.1017/S0266466620000341. Cowles Foundation, Discussion Paper No. 2194RS, https://elischolar.library.yale.edu/cowles-discussion-paper-series/57/.
Giraitis, L., Li, Y. and Phillips, P. C. B. (2024). "Robust Inference on Correlation under General Heterogeneity". Journal of Econometrics, 244(1), 105691, doi:10.1016/j.jeconom.2024.105691.
Examples
x <- rnorm(100)
y <- rnorm(100)
cc.test(x, y, max.lag = 10)
Testing iid property
Description
The function iid.test computes the test statistics for examining the null hypothesis of i.i.d. property for univariate series given in Dalla, Giraitis and Phillips (2022).
Usage
iid.test(x, max.lag, m0 = 1, alpha = 0.05,
plot = TRUE, var.name = NULL, scale.font = 1)
Arguments
x |
A numeric vector or a univariate numeric time series (ts, xts, zoo) object or a data frame variable. |
max.lag |
Maximum lag at which to calculate the test statistics. |
m0 |
Minimum lag at which to calculate the cumulative test statistics. Default is 1. |
alpha |
Significance level for hypothesis testing used in the plots. Default is 0.05. |
plot |
Logical. If TRUE, 1) the test statistics (J) and their critical values are plotted and 2) the cumulative test statistics (C) with their critical values are plotted. Default is TRUE. Can be a logical vector for each of the plots 1)-2). |
var.name |
NULL or a character string specifying the variable name. If NULL and x has name, the name of x is used. If NULL and x has no name, the string "x" is used. Default is NULL. |
scale.font |
A positive number indicating the scaling of the font size in the plots. Default is 1. |
Details
The J_{x,|x|}
and J_{x,x^2}
statistics are for testing the null hypothesis of i.i.d. at lag k
, k=1,...,max.lag
,
and the C_{x,|x|}
and C_{x,x^2}
statistics are for testing the null hypothesis of i.i.d. at lags m_0,...,m
, m=m_0,...,max.lag
.
Value
An object of class "iid.test", which is a list with the following components:
lag |
The lags of the test statistics. |
jab |
The |
pvjab |
The p-values for the |
jsq |
The |
pvjsq |
The p-values for the |
lagc |
The lags of the cumulative test statistics. |
cab |
The |
pvcab |
The p-values for the |
csq |
The |
pvcsq |
The p-values for the |
alpha |
Significance level for hypothesis testing used in the plots. |
varname |
The variable name used in the plots/table. |
Note
Missing values are not allowed.
Author(s)
Violetta Dalla, Liudas Giraitis and Peter C. B. Phillips
References
Dalla, V., Giraitis, L. and Phillips, P. C. B. (2022). "Robust Tests for White Noise and Cross-Correlation". Econometric Theory, 38(5), 913-941, doi:10.1017/S0266466620000341. Cowles Foundation, Discussion Paper No. 2194RS, https://elischolar.library.yale.edu/cowles-discussion-paper-series/57/.
Examples
x <- rnorm(100)
iid.test(x, max.lag = 10)
Testing zero Pearson correlation
Description
The function rcorr.test computes the test statistics for examining the null hypothesis of zero Pearson correlation for multivariate series in Dalla, Giraitis and Phillips (2022).
Usage
rcorr.test(x, plot = TRUE, var.names = NULL, scale.font = 1)
Arguments
x |
A numeric matrix or a multivariate numeric time series object (ts, xts, zoo) or a data frame. |
plot |
Logical. If TRUE the sample Pearson correlations and the p-values for significance are plotted. Default is TRUE. |
var.names |
NULL or a character string specifying the variable names. If NULL and x has names, the names of x are used. If NULL and x has no names, the string c("x[1]","x[2]",...) is used. Default is NULL. |
scale.font |
A positive number indicating the scaling of the font size in the plots. Default is 1. |
Details
The p-value of the robust \widetilde{t}
statistic is for testing the null hypothesis H_0:\rho_{i,j}=0
,
where \rho_{i,j}
denotes the correlation of x_{i}
and x_{j}
.
Value
An object of class "rcorr.test", which is a list with the following components:
pc |
The sample Pearson correlations. |
pv |
The p-values for the |
varnames |
The variable names used in the plot/table. |
Note
Missing values are not allowed.
Author(s)
Violetta Dalla, Liudas Giraitis and Peter C. B. Phillips
References
Dalla, V., Giraitis, L. and Phillips, P. C. B. (2022). "Robust Tests for White Noise and Cross-Correlation". Econometric Theory, 38(5), 913-941, doi:10.1017/S0266466620000341. Cowles Foundation, Discussion Paper No. 2194RS, https://elischolar.library.yale.edu/cowles-discussion-paper-series/57/.
Giraitis, L., Li, Y. and Phillips, P. C. B. (2024). "Robust Inference on Correlation under General Heterogeneity". Journal of Econometrics, 244(1), 105691, doi:10.1016/j.jeconom.2024.105691.
Examples
x <- matrix(rnorm(400), 100)
rcorr.test(x)