## Search found 2628 matches

Wed Dec 03, 2008 5:33 am
Forum: Estimation
Topic: two-way panel model
Replies: 3
Views: 3172

### Re: two-way panel model

I don't have a reference handy, but from my recollection the idea is pretty straightforward. For balanced designs, the order that the GLS and fixed effects transformations are applied is not relevant since the Kronecker product can be factored into separate period and cross-section transformations. ...
Tue Dec 02, 2008 1:27 pm
Forum: Programming
Topic: math functions for coef
Replies: 3
Views: 2972

### Re: math functions for coef

But it's easy enough to get your coef into a vector object with which you can use functions:

Code: Select all

`coef(2) c1c1.fill 1, 2vector c2 = c1vector c3 = exp(c2)`
Tue Dec 02, 2008 1:22 pm
Forum: Programming
Topic: LogL: How to get the gradient other than at estimated value
Replies: 1
Views: 2046

### Re: LogL: How to get the gradient other than at estimated value

The gradient view will compute the gradients at the current coefficients if the logl is not estimated, and at the estimated coefficients if it is. Unfortunately, the makegrads proc will only work with an estimated logl. Obviously, if you have analytic gradients in your logl specification, you can si...
Mon Dec 01, 2008 12:49 am
Forum: Estimation
Topic: two-way panel model
Replies: 3
Views: 3172

### Re: two-way panel model

It estimates using the mixed model. LSDV for the fixed effect, and GLS on the remainder (though I'm not certain what the "S" in your "SGLS" refers to).
Mon Nov 24, 2008 4:33 pm
Forum: Estimation
Topic: ENGLE-GRANGER
Replies: 6
Views: 12470

### Re: ENGLE-GRANGER

The standard reference for the Engle-Granger critical values is MacKinnon, James G., (1991) "Critical Values for Cointegration Tests", in Long-Run Economic Relationships, R.F. Engle and C.W.J. Granger (eds.), London, Oxford, pp 267-276. As to the Johansen test. To be honest, getting a desc...
Thu Nov 20, 2008 12:16 pm
Forum: Estimation
Topic: ENGLE-GRANGER
Replies: 6
Views: 12470

### Re: ENGLE-GRANGER

Simply regress the difference of Y on the lagged difference of Y and A1 to A5, as well as the error correction term (lagged residual from the first equation). One note on the Engle-Granger test that you've already performed. The test that you've described is only approximate since the critical value...
Thu Nov 20, 2008 11:36 am
Forum: Estimation
Topic: Putting Limits on Coefficients
Replies: 5
Views: 4964

### Re: Putting Limits on Coefficients

(Re: the previous posting by s_pusharaj ) Lest anyone get the wrong impression, I'd just like to point out that the EViews least squares procedure certainly does perform nonlinear estimation. If I had to guess at what is going on here I'd suspect that it's a starting value issue. We will use whateve...
Thu Nov 20, 2008 11:27 am
Forum: EViews 5 and Earlier
Topic: HELP: RANDOM EFFECTS
Replies: 3
Views: 4344

### Re: HELP: RANDOM EFFECTS

To answer the original question...when you click on the Estimate button on your pool object, there is a dialog that contains a set of radio buttons which controls the intercept specification (None, Common, Fixed effects, Random effects). Select the last one, enter the rest of your specification, and...
Mon Nov 17, 2008 10:23 am
Forum: Models
Topic: Forecasting with Models
Replies: 11
Views: 13588

### Re: Forecasting with Models

I think he means that he wants to forecast outside of the workfile and needs to know whether he needs to expand the workfile and to add values for the observations for exogenous variables. The answer to those two questions (if indeed I'm interpreting correctly) is yes. All forecasing in EViews (whet...
Thu Nov 06, 2008 10:31 am
Forum: Estimation
Topic: Marginal effects in Tobit Model
Replies: 41
Views: 20007

### Re: Marginal effects in Tobit Model

That's a moderately complicated specification, especially since you have both continuous and discrete regressors. Even in the best of circumstances, the derivatives of the expected observed Y are a bit messy since you have to worry about (among other things) the derivative of the expected value of t...
Thu Nov 06, 2008 6:59 am
Forum: Estimation
Topic: Pooled Regression
Replies: 15
Views: 9985

### Re: Pooled Regression

You're combining two commands. The pool statement is used to declare a pool object and to define the cross-section identifiers. The ls is an estimation command used with a specific pool object. So your command tells EViews to declare a pool object E_X1 and specify the identifiers "?x1" &qu...
Wed Nov 05, 2008 6:12 pm
Forum: Estimation
Topic: Marginal effects in Tobit Model
Replies: 41
Views: 20007

### Re: Marginal effects in Tobit Model

There is nothing built-in. I'm assuming that you are interested in the derivatives of the conditional mean of the observed dependent, not the those of the latent dependent, since the latter are simply the beta coefficients. The calculations depend a lot on the particulars of your specification (dist...
Fri Oct 31, 2008 2:59 pm
Forum: Data Manipulation
Topic: Reverse order of ordinally scaled variables
Replies: 8
Views: 5798

### Re: Reverse order of ordinally scaled variables

I want to reverse the ranking order of some ordinal variables (some are 5 Likert-scales, some are 10 Likert-scales). To achieve this I recoded the values one after another, and it seems to work, though its quite awkward. Is there an easier solution for my problem? Assuming that the scaling goes fro...
Wed Oct 29, 2008 9:12 am
Forum: Programming
Topic: Principal Component
Replies: 2
Views: 5594

### Re: Principal Component

To perform this operation interactively, select the Proc/Make Principal Components entry from the group menu (see User's Guide I , p. 403) and fill out the resulting dialog. Simply choose your normalization method and enter a name for each component score series you wish to save (the first component...
Tue Oct 28, 2008 12:01 pm
Forum: Estimation
Topic: Principal Components
Replies: 1
Views: 2142

### Re: Principal Components

I did a princial components analysis on spread changes and would like to do a regression on the output (Eigenvectors) with 6 dummy variables. How can I do that in eviews? Before I answer, I just want to make certain you want to do these on the eigenvectors and not the scores. The latter are easier ...