cvlm {NTS}

Check linear models with cross validation

Description

The function checks linear models with cross-validation (out-of-sample prediction).

Usage

cvlm(y, x, subsize, iter = 100)

Arguments

y

dependent variable.

x

design matrix (should include constant if it is needed).

subsize

sample size of subsampling.

iter

number of iterations.

Value

The function returns a list with following components.

rmse

root mean squares of forecast errors for all iterations.

mae

mean absolute forecast errors for all iterations.

References

Tsay, R. and Chen, R. (2018). Nonlinear Time Series Analysis. John Wiley & Sons, New Jersey.