# refVAR: Refining a VAR Model In MTS: All-Purpose Toolkit for Analyzing Multivariate Time Series (MTS) and Estimating Multivariate Volatility Models

## Description

Refine a fitted VAR model by removing simultaneously insignificant parameters

## Usage

 `1` ```refVAR(model, fixed = NULL, thres = 1) ```

## Arguments

 `model` An output object of the command VAR or the refVAR command `fixed` A logical matrix for VAR polynomial structure `thres` Threshold used to set parameter to zero. Default is 1.

## Details

Refine a VAR fitting by setting all estimates with t-ratio less than the threshold (in modulus) to zero.

## Value

The same as those of the command VAR

Ruey S. Tsay

## References

Tsay (2014, Chapter 2)

VAR

## Examples

 ```1 2 3 4 5 6``` ```data("mts-examples",package="MTS") gdp=log(qgdp[,3:5]) zt=diffM(gdp) m1=VAR(zt,3) m2=refVAR(m1,thres=1.0) names(m2) ```

### Example output

```Constant term:
Estimates:  0.001611113 0.000919218 0.002644757
Std.Error:  0.0007328135 0.0007872168 0.0008584164
AR coefficient matrix
AR( 1 )-matrix
[,1]  [,2]   [,3]
[1,] 0.430 0.116 0.0518
[2,] 0.326 0.322 0.4882
[3,] 0.487 0.175 0.2407
standard error
[,1]   [,2]   [,3]
[1,] 0.0906 0.0965 0.0889
[2,] 0.0973 0.1037 0.0955
[3,] 0.1061 0.1130 0.1042
AR( 2 )-matrix
[,1]    [,2]    [,3]
[1,]  0.000512  0.1342 -0.0409
[2,] -0.184259 -0.1919  0.0239
[3,] -0.233267 -0.0949  0.1713
standard error
[,1]  [,2]   [,3]
[1,] 0.102 0.099 0.0955
[2,] 0.110 0.106 0.1026
[3,] 0.119 0.116 0.1119
AR( 3 )-matrix
[,1]    [,2]    [,3]
[1,] 0.1011 -0.2691  0.1680
[2,] 0.0467  0.0835 -0.0856
[3,] 0.0205 -0.0972 -0.0306
standard error
[,1]   [,2]   [,3]
[1,] 0.0932 0.0853 0.0893
[2,] 0.1001 0.0916 0.0959
[3,] 0.1092 0.0999 0.1046

Residuals cov-mtx:
[,1]         [,2]         [,3]
[1,] 2.469619e-05 4.101370e-06 8.052621e-06
[2,] 4.101370e-06 2.849915e-05 1.320285e-05
[3,] 8.052621e-06 1.320285e-05 3.388747e-05

det(SSE) =  1.799982e-14
AIC =  -31.21641
BIC =  -30.6055
HQ  =  -30.96823
Constant term:
Estimates:  0.00167979 0.001023964 0.002644002
Std.Error:  0.0006939314 0.0007374557 0.0008350321
AR coefficient matrix
AR( 1 )-matrix
[,1]  [,2]  [,3]
[1,] 0.444 0.127 0.000
[2,] 0.340 0.327 0.471
[3,] 0.479 0.150 0.231
standard error
[,1]   [,2]   [,3]
[1,] 0.0827 0.0745 0.0000
[2,] 0.0943 0.0938 0.0917
[3,] 0.1041 0.1083 0.1004
AR( 2 )-matrix
[,1]   [,2]  [,3]
[1,]  0.000  0.124 0.000
[2,] -0.153 -0.175 0.000
[3,] -0.217  0.000 0.139
standard error
[,1]   [,2]  [,3]
[1,] 0.0000 0.0927 0.000
[2,] 0.0946 0.0804 0.000
[3,] 0.1067 0.0000 0.102
AR( 3 )-matrix
[,1]   [,2]  [,3]
[1,] 0.0855 -0.274 0.174
[2,] 0.0000  0.000 0.000
[3,] 0.0000 -0.145 0.000
standard error
[,1]   [,2]   [,3]
[1,] 0.0808 0.0825 0.0879
[2,] 0.0000 0.0000 0.0000
[3,] 0.0000 0.0825 0.0000

Residuals cov-mtx:
[,1]         [,2]         [,3]
[1,] 2.481393e-05 4.095313e-06 8.031321e-06
[2,] 4.095313e-06 2.885024e-05 1.338902e-05
[3,] 8.031321e-06 1.338902e-05 3.419020e-05

det(SSE) =  1.847448e-14
AIC =  -31.35039
BIC =  -30.96574
HQ  =  -31.19412
[1] "data"      "order"     "cnst"      "coef"      "aic"       "bic"
[7] "hq"        "residuals" "secoef"    "Sigma"     "Phi"       "Ph0"
```

MTS documentation built on May 29, 2017, 5:15 p.m.