In NumXL 1.63, the (*)_PARAM functions-family (e.g. ARMA_PARAM, SARIMA_PARAM, etc.) can now compute compute not only the calibrated values of the model's parameters, but the standard error in the estimated values as well.
Next, using conventional statistical test of hypothesis (under Normal distribution assumption), calculate the test-stat (Z-Score), P-Value and examine the significance of each value.
Comments
In NumXL 1.63, the (*)_PARAM functions-family (e.g. ARMA_PARAM, SARIMA_PARAM, etc.) can now compute compute not only the calibrated values of the model's parameters, but the standard error in the estimated values as well.
Next, using conventional statistical test of hypothesis (under Normal distribution assumption), calculate the test-stat (Z-Score), P-Value and examine the significance of each value.
Please sign in to leave a comment.