Search found 3289 matches

by startz
Sat May 19, 2018 7:21 am
Forum: Estimation
Topic: Non-linear least squares regression
Replies: 3
Views: 93

Re: Non-linear least squares regression

Since your equation is nonlinear in parameters you need to write it out in equation form, as shown in the documentation.

The easiest way to indicate that a parameter needs to be estimated is to call it c(1) or c(2), etc. That's how EViews knows it is a parameter rather than a data series.
by startz
Fri May 18, 2018 9:11 am
Forum: Econometric Discussions
Topic: Significance of impulse response VAR
Replies: 6
Views: 4041

Re: Significance of impulse response VAR

All it means is that there is not strong statistical evidence that the response is different from zero.
by startz
Thu May 17, 2018 6:03 am
Forum: General Information and Tips and Tricks
Topic: merge graph series and smoothed markov switching
Replies: 3
Views: 69

Re: merge graph series and smoothed markov switching

open a group with both series and graph them.
by startz
Wed May 16, 2018 4:17 pm
Forum: Econometric Discussions
Topic: Question on GMM estimation
Replies: 1
Views: 45

Re: Question on GMM estimation

You can't have fewer instruments than coefficients.
by startz
Wed May 16, 2018 8:56 am
Forum: General Information and Tips and Tricks
Topic: merge graph series and smoothed markov switching
Replies: 3
Views: 69

Re: merge graph series and smoothed markov switching

After the estimation, proc/make regime results will create a series for you.
by startz
Mon May 07, 2018 5:34 pm
Forum: Estimation
Topic: Functional form in Box estimation
Replies: 2
Views: 89

Re: Functional form in Box estimation

Aktar wrote:Dear Moderator,

I would like to estimate the coefficent theta in a logistic functional form. My model is

y = exp(theta x) / (1+exp(\theta x) + e

How can I specify it in the box estimation?

Thank you,

Something like

Code: Select all

ls y=exp(c(1)*x)/(1+exp(c(1)*x))
by startz
Sun May 06, 2018 11:50 am
Forum: Estimation
Topic: Toda and Yamamoto causality test
Replies: 25
Views: 9468

Re: Toda and Yamamoto causality test

Capture.PNG
Capture.PNG (27.14 KiB) Viewed 99 times
by startz
Sun May 06, 2018 11:25 am
Forum: Estimation
Topic: Toda and Yamamoto causality test
Replies: 25
Views: 9468

Re: Toda and Yamamoto causality test

The site, which is an excellent resource, was last updated a week ago.
by startz
Sun May 06, 2018 7:00 am
Forum: Estimation
Topic: State Space Error Improving Likehood
Replies: 10
Views: 270

Re: State Space Error Improving Likehood

You may have converged to a local optima. Try the starting values from the full model.
by startz
Sat May 05, 2018 4:29 pm
Forum: General Information and Tips and Tricks
Topic: Two-Tailed Test
Replies: 1
Views: 96

Re: Two-Tailed Test

The t-test is two-tailed. Not quite sure what a two-tailed F-test is.
by startz
Fri May 04, 2018 8:42 am
Forum: Estimation
Topic: State Space Error Improving Likehood
Replies: 10
Views: 270

Re: State Space Error Improving Likehood

Maybe the parameter c(72) is important.
by startz
Fri May 04, 2018 8:20 am
Forum: Estimation
Topic: State Space Error Improving Likehood
Replies: 10
Views: 270

Re: State Space Error Improving Likehood

Maybe. But state space models are generally nonlinear in that they don't have closed form solutions, so a search algorithm is necessary.
by startz
Fri May 04, 2018 5:53 am
Forum: Estimation
Topic: State Space Error Improving Likehood
Replies: 10
Views: 270

Re: State Space Error Improving Likehood

Sometimes nonlinear models are hard to estimate. Try different starting values.
by startz
Tue May 01, 2018 8:11 am
Forum: Econometric Discussions
Topic: GMM estimation and Durbin-Wu-Hausman test
Replies: 12
Views: 283

Re: GMM estimation and Durbin-Wu-Hausman test

It does not mean that OLS is preferred. It means GMM or IV has a problem.
by startz
Tue May 01, 2018 7:34 am
Forum: Econometric Discussions
Topic: GMM estimation and Durbin-Wu-Hausman test
Replies: 12
Views: 283

Re: GMM estimation and Durbin-Wu-Hausman test

It is certainly possible that adding an invalid instrument would switch a rejection to a non-rejection. The way to test for validity of a set of over-identifying instruments, as you know, is to use the J-statistic.

Go to advanced search