Ron Michael

2008-Mar-20 18:32 UTC

### [R] Interpretation of Variance decomposition in VAR model

Hi all, This question is not really R related, rather on Statistics subject itself. Even I did not do those using R. however still I want to post it here, because my hope is I could get help from great statisticians who are the very active member of this group. My problem is to interpret Variance decomposition of VAR model in layman's language. Using EViews I got following : Variance Decomposition of LN_FU: Period S.E. LN_SPOT LN_FU 1 0.024422 93.66959 6.330413 2 0.034838 94.36506 5.634938 3 0.042280 94.60712 5.392882 4 0.048540 94.30725 5.692747 5 0.054060 93.99039 6.009611 6 0.059042 93.67545 6.324554 7 0.063621 93.33405 6.665951 8 0.067885 92.99347 7.006529 9 0.071893 92.65966 7.340337 10 0.075687 92.33266 7.667341 Variance Decomposition of LN_SPOT: Period S.E. LN_SPOT LN_FU 1 0.023745 100.0000 0.000000 2 0.033741 99.51122 0.488785 3 0.041018 99.25339 0.746605 4 0.047204 98.98354 1.016462 5 0.052660 98.62401 1.375990 6 0.057600 98.24985 1.750151 7 0.062155 97.86303 2.136970 8 0.066400 97.46197 2.538034 9 0.070394 97.05655 2.943451 10 0.074176 96.65102 3.348978 Cholesky Ordering: LN_SPOT LN_FU Myquestion is How to interpret those result in layman language? If I sayfollowing : "93.66959% of tomorrow's volatility in LN_FU is explainedby LN_SPOT's today volatility and remaining 6.330413% is explained byit's today's Volatility", is this statement correct? Then what will bethe interpretation of remaining numbers like : 94.36506,5.634938,......etc? And also What could be the interpretation of the SE in layman's term? I already gone through Eviews help file however, did not get anything. If u people here help me on this regard, I will be very very grateful. Regards, Send instant messages to your online friends http://uk.messenger.yahoo.com [[alternative HTML version deleted]]

Ron Michael

2008-Mar-20 18:34 UTC

### [R] Interpretation of Variance decomposition in VAR model

Hi all, This question is not really R related, rather on Statistics subject itself. Even I did not do those using R. however still I want to post it here, because my hope is I could get help from great statisticians who are the very active member of this group. My problem is to interpret Variance decomposition of VAR model in layman's language. Using EViews I got following : Variance Decomposition of LN_FU: Period S.E. LN_SPOT LN_FU 1 0.024422 93.66959 6.330413 2 0.034838 94.36506 5.634938 3 0.042280 94.60712 5.392882 4 0.048540 94.30725 5.692747 5 0.054060 93.99039 6.009611 6 0.059042 93.67545 6.324554 7 0.063621 93.33405 6.665951 8 0.067885 92.99347 7.006529 9 0.071893 92.65966 7.340337 10 0.075687 92.33266 7.667341 Variance Decomposition of LN_SPOT: Period S.E. LN_SPOT LN_FU 1 0.023745 100.0000 0.000000 2 0.033741 99.51122 0.488785 3 0.041018 99.25339 0.746605 4 0.047204 98.98354 1.016462 5 0.052660 98.62401 1.375990 6 0.057600 98.24985 1.750151 7 0.062155 97.86303 2.136970 8 0.066400 97.46197 2.538034 9 0.070394 97.05655 2.943451 10 0.074176 96.65102 3.348978 Cholesky Ordering: LN_SPOT LN_FU Myquestion is How to interpret those result in layman language? If I sayfollowing : "93.66959% of tomorrow's volatility in LN_FU is explainedby LN_SPOT's today volatility and remaining 6.330413% is explained byit's today's Volatility", is this statement correct? Then what will bethe interpretation of remaining numbers like : 94.36506,5.634938,......etc? And also What could be the interpretation of the SE in layman's term? I already gone through Eviews help file however, did not get anything. If u people here help me on this regard, I will be very very grateful. Regards, Send instant messages to your online friends http://uk.messenger.yahoo.com [[alternative HTML version deleted]]