Forum: help
Monitor Forum | 
Start New Thread
| RE: MicEconCES p-value [ Reply ] By: Arne Henningsen on 2019-11-03 13:53 | [forum:47116] |
| I don't understand this question. Sorry! | |
| RE: MicEconCES p-value [ Reply ] By: Darius Ma on 2019-10-14 10:02 | [forum:47012] |
|
Thank you for the answer. But how do I choose the estimated rho? When running different algorithms, I have different estimated values. Do I look only on the R squared and SSR? Cause, usually, one would look at the significancy of the value. However, in my case, I just want the best estimated elasticity that fits the most my model. Thank you again |
|
| RE: MicEconCES p-value [ Reply ] By: Arne Henningsen on 2019-10-14 06:15 | [forum:47011] |
| The null hypothesis of the test is that the elasticity of substitution is zero (so that the t-statistic is 0.04253 / 0.21546 = 0.197). Perhaps, it could make sense to change this so that a test with the null hypothesis that the elasticity of substitution is one is presented instead or additionally. You could do this test also manually by calculating the t-value by ( 0.04253 - 1 ) / 0.21546 = -4.443841, which corresponds to a very small P-value. | |
| MicEconCES p-value [ Reply ] By: Darius Ma on 2019-07-26 16:10 | [forum:46865] |
|
Good evening, When I run several algorithm, I get these results: Elasticities of Substitution: Estimate Std. Error t value Pr(>|t|) E_1_2 (HM) 0.04253 0.21546 0.197 0.844 E_(1,2)_3 (AU) NA NA NA NA I would like to know to which test the p-value corresponds? What is the null hypothesis here? I recall that this value gives you the significancy of the estimate, ok. But what is the H1 and the H0 (null hypothesis) of the test here? For example, a null hypothesis could be that the coefficient is equal to zero, hence if the coefficient is significant, the value is different from 0. Thank you in advance. Best, |
|
