Search found 63 matches

by stefanp
Wed Jan 09, 2019 8:02 am
Forum: Estimation
Topic: How to cluster SE
Replies: 1
Views: 316

Re: How to cluster SE

Any thoughts?
by stefanp
Tue Jan 08, 2019 7:32 am
Forum: Estimation
Topic: How to cluster SE
Replies: 1
Views: 316

How to cluster SE

I use a panel data set in which the cross sections are state-industry pairs. How can I cluster SE on the state level?
by stefanp
Wed Dec 05, 2018 2:31 am
Forum: Data Manipulation
Topic: Sample depending on number of NAs and zeros
Replies: 1
Views: 443

Sample depending on number of NAs and zeros

I would like to set the sample if the number of NAs and zeros does not exceed a certain number. Is that possible simply using the smpl command instead of a combination of commands?
by stefanp
Thu Nov 15, 2018 1:02 am
Forum: Data Manipulation
Topic: NAs in sample
Replies: 8
Views: 931

Re: NAs in sample

Because I need to know the value of series_a in the other period, i.e. when it is not NA
by stefanp
Wed Nov 14, 2018 10:14 am
Forum: Data Manipulation
Topic: NAs in sample
Replies: 8
Views: 931

Re: NAs in sample

But that does not allow me to look at the value of series_a in 2012m01. Is there any way to use a particular date as an index for a series (i.e., what I try to do with series_a(@obsid=12)?
by stefanp
Wed Nov 14, 2018 9:19 am
Forum: Data Manipulation
Topic: NAs in sample
Replies: 8
Views: 931

Re: NAs in sample

I have a panel data set which contains monthly data for several years. However, I am primarily interested in two specific periods (before and after some policy change). Hence, I set the sample to these two periods: smpl 2012m01 2012m01 2013m01 2013m01 Additionally, I need to check how many of my cro...
by stefanp
Wed Nov 14, 2018 8:44 am
Forum: Data Manipulation
Topic: NAs in sample
Replies: 8
Views: 931

Re: NAs in sample

I do not know if I can adopt that suggestion for what I need. My problem is a little more complex. In my pseudo-code below it should be something like smpl time time time(+12) time(+12) if and series_a(@obsid=time)=na and series_a(@obsid=time+12)<>na I do not know if I can achieve that sampling with...
by stefanp
Wed Nov 14, 2018 8:24 am
Forum: Data Manipulation
Topic: NAs in sample
Replies: 8
Views: 931

NAs in sample

I wish identify cross-sections in a panel data set if their value for a series at a certain time equals NA. I thought of something like smpl @all if series_a(@obsid=12)=na show series_a However, some cross sections of series_a are still being displayed besides having numeric value. Anything wrong wi...
by stefanp
Wed Nov 14, 2018 3:03 am
Forum: Estimation
Topic: Fixed effects estimation
Replies: 1
Views: 1098

Fixed effects estimation

In Stata, something like

Code: Select all

xtreg some_equation, fe
estimates an equation with cross-section fixed effects.

Does this correspond to

Code: Select all

ls(cx=f) some_equation
in Eviews?
by stefanp
Tue Nov 06, 2018 3:53 am
Forum: Data Manipulation
Topic: sum up series in panel data set
Replies: 1
Views: 1598

sum up series in panel data set

I have a panel data set which contains several series. I need to sum up the values for some cross sections (across identifiers, not time) depending on some specific conditions. I thought of something like this: smpl @all if condition_a=1 series test=@sum(series_a) However, the values of test appear ...
by stefanp
Thu Sep 20, 2018 12:59 am
Forum: Programming
Topic: Makeresid
Replies: 1
Views: 1554

Makeresid

I use panel data and estimate equations for each cross section individually. In the next step, I want to create the residuals of each regression. For some cross sections, this works just fine. However, the residuals for some other cross sections are "NA". If I manually compute the residual...
by stefanp
Tue Sep 18, 2018 4:47 am
Forum: Programming
Topic: NA in series
Replies: 4
Views: 1361

Re: NA in series

I still haven't figured out a way to exclude a cross section if there are too many NAs in this cross section.
by stefanp
Mon Sep 17, 2018 7:43 am
Forum: Programming
Topic: Wilcard in smpl
Replies: 1
Views: 889

Wilcard in smpl

Is it possible to use wildcard expressions in the sampling command?
by stefanp
Mon Sep 17, 2018 7:09 am
Forum: Data Manipulation
Topic: Match identifiers
Replies: 1
Views: 1227

Match identifiers

Is is possible to match different identifier series? What I have in mind is something like VLOOKUP in Excel.
by stefanp
Fri Sep 14, 2018 6:23 am
Forum: Programming
Topic: NA in series
Replies: 4
Views: 1361

Re: NA in series

series.@obs has exactly the same value for every observation.

Go to advanced search