EViews.com

I made some estimation with VECM and I have problem with forecasting results.Namely I use X13 Cenus method which made seasonal adjustment for my quartaly time series.At the end I make forecasting with VECM but my forecasting values is not in season because my data is seasonal adjustment with X13.So ...

I make some estimation with Error Correction Model-ECM.So I can easy to estimate ECM with two step (Engel-Granger approach).So I first calculate long run coefficent with OLS after that I calculate short run coefficient.So my question is how to write specification for ECM in E-views?

I have question relate with impulse response function in Error Correction Model. Namely I must work with ECM model (with two variables) and I should calculate some elasticity. But here I have problem because I should make graph with impulse response function. So can anybody help me about this proble...

I made some estimation with OLS and have problem with explanation of results from error.Because my time series is convert in log values I don't understand what is meaning of this figures such as: Mean error 0,073, RMSE 0,558,MAE 0,382, MPE 0,400 etc. If I calculate with absolute value(without log) I...

I am performing VECM with around 60-variables(quarterly data) with three variables. I use around 11 dummy and I got VECM which is positive of all test ( sigh of coefficient,autocorrelation, heteroscedasticity, normality of residuals etc.) So my question does this 11 dummy's is normal for VECM? Or ho...

I am performing VECM and I have some dilemmas. Namely for choosing the best VECM model, which variables is most important ( RMSE, R², AIC, SC ) ?

Thank you

I am performing ARDL model with Eviews automatic selection of lags,although I using automatic selection often Eviews suggest me variables which are not significant at 5% level.So my question what should do with this variables which is not significant ? Do I keep them or not ?

I am calculating VECM. In this model I am using three variables (x,y,z). Here for me most important is variable X because lately am planing to make forecasting with equation for this variable. With Y and Z i don't have plan to making forecast. After performing VECM I got significant values for X in ...

My variables are in logs, this mean if dependent variable go up for 1% also and independent variables will go up if sign is positive. But what will happen if dummy have negative sign ? What is the statistical explanation ?

I am calculating some regression with OLS and also I am using dummy (0 zero for all variables and 1 for only one variable).But sign of dummy in final equation is negative.
So my question is, does is important sign of dummy into regression or not?

I am calculating coefficient elasticity with OLS and these is my problem. First I convert time series variable into log and after that caculating elasticity with OLS. So my question is does this coefficient of elasticity are relavant if p-value is not significant or in this case p-value is not relev...

Thank you.
This is very useful for me.
But what happened with quarterly data ?
How many observations is enough for relevant regression ?

How many observations is optimal to use for OLS ? In reality I often face with time series which contains 6-7 observation with yearly data.So my question is does this regression is relevant with this small number of observation?