analyzes nonstationary or locally stationary multivariate
time series by using the minimum AIC procedure
- CALL TSMLOMAR( arcoef, ev, nar, aic, start, finish, data
- <,maxlag, opt, missing,
The inputs to the TSMLOMAR subroutine are as follows:
- specifies a T ×M data matrix, where T is the number of
observations and M is the number of variables to be analyzed.
- specifies the maximum lag of the vector AR (VAR) process.
This value should be less than [1/2M]
of the length of locally stationary spans.
The default is maxlag=10.
- specifies an options vector.
- specifies the mean deletion option.
The mean of the original data is deleted if opt=-1.
An intercept coefficient is estimated if opt=1.
If opt=0, the original input data is processed
assuming that the mean values of input series are zeroes.
The default is opt=0.
- specifies the number (J) of basic spans.
By default, opt=1.
- specifies the minimum AIC option.
If opt=0, the maximum lag
VAR process is estimated.
If opt=1, a minimum AIC procedure is used.
The default is opt=1.
- specifies the missing value option.
By default, only the first contiguous observations
with no missing values are used (missing=0).
The missing=1 option ignores
observations with missing values.
If you specify the missing=2 option, the
missing values are replaced with the sample mean.
- specifies the print option.
By default, printed output is suppressed (print=0).
The print=1 option prints the AR estimates, minimum
AIC, minimum AIC order, and innovation variance matrix.
The TSMLOMAR subroutine returns the following values:
- refers to an M ×(M* nar) VAR coefficient
vector of the final model if the intercept vector is not included.
If opt=1, the first column of the
arcoef matrix is an intercept estimate vector.
- refers to the error variance matrix.
- is the selected VAR order of the final model.
If opt=0, nar=maxlag.
- refers to the minimum AIC value of the final model.
- refers to the starting position of the input series data,
which corresponds to the first observation of the final model.
- refers to the ending position of the input series data,
which corresponds to the last observation of the final model.
The TSMLOMAR subroutine analyzes nonstationary
(or locally stationary) multivariate time
series by using the minimum AIC procedure.
The data of length T is divided
into J locally stationary subseries.
See "Nonstationary Time Series" in
the "Nonstationary Time Series" section for details.
Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.