Using 6 columns of time series data, conduct pairwise analysis on all possible iterations (in R)
up vote
0
down vote
favorite
I have a dataframe mydf containing 6 columns of time series data.
I want to calculate the correlation of all this data, which can easily be done through cor(mydf). However, I want to multiply each of the correlations by the square root of the relevant long-run variances (I adopt an arbitrary autocorrelation lag of 5) of each pairwise column.
To demonstrate, val = cor(mydf[,1], mydf[,2])
cov_temp1 = acf(mydf[,1], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
cov_temp2 = acf(mydf[,2], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
s.e. = sqrt((cov_temp1[1]+2*sum(cov_temp1[-1]))/nrow(mydf) * (cov_temp2[1]+2*sum(cov_temp2[-1]))/nrow(mydf))
Then, the pairwise statistic for column 1 and 2 is val*s.e.. Assuming I have 6 columns of data, which I do, I want to construct the same statistic for all iterations of pairwise columns and then sum them up. I am not entirely sure how to proceed?
r
asked Nov 13 at 9:41
TheManR
154
add a comment |
up vote
0
down vote
favorite
I have a dataframe mydf containing 6 columns of time series data.
I want to calculate the correlation of all this data, which can easily be done through cor(mydf). However, I want to multiply each of the correlations by the square root of the relevant long-run variances (I adopt an arbitrary autocorrelation lag of 5) of each pairwise column.
To demonstrate, val = cor(mydf[,1], mydf[,2])
cov_temp1 = acf(mydf[,1], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
cov_temp2 = acf(mydf[,2], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
s.e. = sqrt((cov_temp1[1]+2*sum(cov_temp1[-1]))/nrow(mydf) * (cov_temp2[1]+2*sum(cov_temp2[-1]))/nrow(mydf))
Then, the pairwise statistic for column 1 and 2 is val*s.e.. Assuming I have 6 columns of data, which I do, I want to construct the same statistic for all iterations of pairwise columns and then sum them up. I am not entirely sure how to proceed?
r
asked Nov 13 at 9:41
TheManR
154
add a comment |
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I have a dataframe mydf containing 6 columns of time series data.
I want to calculate the correlation of all this data, which can easily be done through cor(mydf). However, I want to multiply each of the correlations by the square root of the relevant long-run variances (I adopt an arbitrary autocorrelation lag of 5) of each pairwise column.
To demonstrate, val = cor(mydf[,1], mydf[,2])
cov_temp1 = acf(mydf[,1], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
cov_temp2 = acf(mydf[,2], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
s.e. = sqrt((cov_temp1[1]+2*sum(cov_temp1[-1]))/nrow(mydf) * (cov_temp2[1]+2*sum(cov_temp2[-1]))/nrow(mydf))
Then, the pairwise statistic for column 1 and 2 is val*s.e.. Assuming I have 6 columns of data, which I do, I want to construct the same statistic for all iterations of pairwise columns and then sum them up. I am not entirely sure how to proceed?
r
asked Nov 13 at 9:41
TheManR
154
I have a dataframe mydf containing 6 columns of time series data.
I want to calculate the correlation of all this data, which can easily be done through cor(mydf). However, I want to multiply each of the correlations by the square root of the relevant long-run variances (I adopt an arbitrary autocorrelation lag of 5) of each pairwise column.
To demonstrate, val = cor(mydf[,1], mydf[,2])
cov_temp1 = acf(mydf[,1], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
cov_temp2 = acf(mydf[,2], type = "covariance", lag.max = 5, plot = FALSE, na.action = na.pass)$acf
s.e. = sqrt((cov_temp1[1]+2*sum(cov_temp1[-1]))/nrow(mydf) * (cov_temp2[1]+2*sum(cov_temp2[-1]))/nrow(mydf))
Then, the pairwise statistic for column 1 and 2 is val*s.e.. Assuming I have 6 columns of data, which I do, I want to construct the same statistic for all iterations of pairwise columns and then sum them up. I am not entirely sure how to proceed?
r
r
asked Nov 13 at 9:41
TheManR
154
asked Nov 13 at 9:41
TheManR
154
asked Nov 13 at 9:41
TheManR
154
asked Nov 13 at 9:41
TheManR
154
asked Nov 13 at 9:41
TheManR
154
154
add a comment |
add a comment |
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53278021%2fusing-6-columns-of-time-series-data-conduct-pairwise-analysis-on-all-possible-i%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
