Hi,
I ran the Im-Pesaran-Shin individual unit root test for my (panel) variables.
I get insanely large W-stats for all of them, for example -248,579,613,373,436 (p-values are all 0, "of course")
Is this reason for concern?
Search found 17 matches
- Thu Jun 26, 2014 2:36 pm
- Forum: Econometric Discussions
- Topic: Extremely high w-stat for Im-Pesaran-Shin unit root test
- Replies: 0
- Views: 2373
- Wed Jun 18, 2014 1:54 am
- Forum: Econometric Discussions
- Topic: Heteroskedasticity in panel data
- Replies: 1
- Views: 2797
- Tue Jun 17, 2014 9:10 am
- Forum: Estimation
- Topic: Again: near singular matrix
- Replies: 2
- Views: 4304
Re: Again: near singular matrix
Ah I have found the reason! LIST2 is NA if fam=1 (no family firm in my sample is listed). Excluding it solves the problem. But does it induce an identification problem in my two equation system? My structural equations will be (w/o LIST2) 1) roa1_win c lev1_win (1/2)*lev1_win^2 ind1 size1_win age2_w...
- Tue Jun 17, 2014 8:25 am
- Forum: Estimation
- Topic: Again: near singular matrix
- Replies: 2
- Views: 4304
Again: near singular matrix
Hi, I know this question has been posed a lot of times before, but the thing is that I cannot figure out which variables are colinear in my regressions. I tried to estimate these two equations: roa1_win c ind1 size1_win age2_win gr1_win risk1_win herf shceo tan_win list2 med_lev1 Sample: 2000 2012 i...
- Fri Jun 13, 2014 1:39 am
- Forum: Estimation
- Topic: ADF/unit root test in EViews 7.2
- Replies: 3
- Views: 3891
Re: ADF/unit root test in EViews 7.2
Thank you! So I'll just use the "Individual root - Fisher -ADF"?
- Thu Jun 12, 2014 5:23 am
- Forum: Econometric Discussions
- Topic: Heteroskedasticity in panel data
- Replies: 1
- Views: 2797
Heteroskedasticity in panel data
Hi, I'm using EViews 7.2. I have found out that there is no built-in method to test/control for heteroskedasticity in panel data. But in when estimating, I can choose from some options under Coef covariance method (see picture). Doesn't that solve the problem? If yes, which option do I need to choos...
- Thu Jun 12, 2014 5:17 am
- Forum: Estimation
- Topic: ADF/unit root test in EViews 7.2
- Replies: 3
- Views: 3891
ADF/unit root test in EViews 7.2
Hi, so I wanted to do and ADF/unit-root test on a series (which is part of a panel) in EViews 7.2, but the choices are not as in EViews 7.0, and neither are the outputs. The second picture shows the options that I get to choose from - which one is the ADF test? The first picture shows the output - l...
- Thu Jun 12, 2014 2:55 am
- Forum: Add-in Support
- Topic: Trim
- Replies: 32
- Views: 51900
Re: Trim
Will this add-in work with EViews 8 as well?
- Thu Jun 12, 2014 1:42 am
- Forum: Econometric Discussions
- Topic: Fixed effects - cross-section, period or both?
- Replies: 0
- Views: 5216
Fixed effects - cross-section, period or both?
Hi, so I familiarized myself a little with the Hausman test and found out how to do it in EViews. But I can't seem to find out whether to use Fixed effects (assume Hausman test p-value =0) for cross-sections (will further call it CS), periods or both. What I did is: I estimated my model with CS rand...
- Tue Jun 10, 2014 2:35 am
- Forum: Econometric Discussions
- Topic: Equations identified? 2-equation model
- Replies: 1
- Views: 2614
Equations identified? 2-equation model
Hi, I have created the following two simultaneous equations models (see the attached pictures). I think they should be exactly identified, I checked for rank and order condition. However, I am not sure, as this is the first time I do this. Could somebody please be so kind and check whether they are ...
- Sun Jun 08, 2014 9:44 am
- Forum: Estimation
- Topic: Creating quintiles and running regressions on each
- Replies: 1
- Views: 2753
Creating quintiles and running regressions on each
Hi, I have a panel. I want to estimate a simultaneous equations model (2 equations) using 2SLS. My DV is ROA (performance), my IV is LEV (leverage), and vice versa in the 2nd equation. Both equations contain other variables such that they are identified. Now I want to divide the panel into quintiles...
- Thu Jun 05, 2014 8:59 am
- Forum: Estimation
- Topic: Dummy Variables
- Replies: 144
- Views: 285595
Re: Dummy Variables
We get asked questions on dummy variable creation in EViews fairly regularly, so I thought I'd write up a quick all-inclusive guide. Simple Dummies The easiest way to create a dummy variable is with the @recode function. @recode lets you specify a logical test, and the values a variable should take...
- Thu Jun 05, 2014 7:54 am
- Forum: Data Manipulation
- Topic: Creating an industry median variable
- Replies: 3
- Views: 4619
Re: Creating an industry median variable
Hey, thanks for your suggestion. Unfortunately, this doesn't work. What the command does is create the median leverage for industry with the code 1 and for year 2000. I need the median for each industry, for each year. The variable that the median should be taken of: LEV1 Name of the year variable: ...
- Wed May 14, 2014 4:23 am
- Forum: Data Manipulation
- Topic: Creating an industry median variable
- Replies: 3
- Views: 4619
Creating an industry median variable
Hi, I have a panel in which I want to generate a new series. I have firm IDs as cross-sections, the panel is dated annualy. The panel looks appx. like this (of course more observations and years in the actual panel): ID YEAR INDUSTRY LEVERAGE MEDIAN LEVERAGE 1 2010 63 0.5 0.4 1 2011 63 0.6 0.5 2 201...
- Thu Apr 10, 2014 4:29 am
- Forum: Econometric Discussions
- Topic: 2SLS procedure in EViews
- Replies: 1
- Views: 3199
Re: 2SLS procedure in EViews
Isn't there anyone who can help? I'm sure this isn't done for the first time...
Thanks!
Thanks!