Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Regression with different firms


From   "felix kreppel" <felix.kreppel@gmx.de>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Regression with different firms
Date   Thu, 09 Aug 2012 21:43:19 +0200

Sorry,

it worked when I used the following command:
reshape long firm std, i(date) j(firm_id)

When I did the regression: regress firm std market_return, however, it produced an oddly low R² (0.09) and extremely high t-statists (~74.73). Is there a special command for time series regression in this case?


-------- Original-Nachricht --------
> Datum: Thu, 9 Aug 2012 20:00:52 +0100
> Von: Nick Cox <njcoxstata@gmail.com>
> An: statalist@hsphsun2.harvard.edu
> Betreff: Re: st: Regression with different firms

> We can't see anything that you don't tell us. "seems to work" and
> "seems as if" are no help. Please give details in order not to waste
> your own time by asking questions that no one can answer.
> 
> Nick
> 
> On Thu, Aug 9, 2012 at 7:44 PM, felix kreppel <felix.kreppel@gmx.de>
> wrote:
> > I tried the following commmand:
> >
> > reshape long firm std, i(date) j(firm)
> >
> > This seems to work. My dataset, however, is quite large (1000 firms &
> 1000 volatilites). It seems as if Stata cannot perform the conversion. Am I
> doing something wrong, or is there another way to do this?
> >
> > The regression command I would end up with after reshaping would be
> >
> > regress firm std market_return, right?
> >
> > Thanks.
> > -------- Original-Nachricht --------
> >> Datum: Thu, 9 Aug 2012 14:34:09 -0400
> >> Von: Fernando Rios Avila <f.rios.a@gmail.com>
> >> An: statalist@hsphsun2.harvard.edu
> >> Betreff: Re: st: Regression with different firms
> >
> >> Exactly. You might end up with a data set that looks like:
> >> Year   firm_id  return  std  market_return
> >> 1985     1
> >> 1985     2
> >> 1985     3
> >> 1986     1
> >> just check the reshape examples from wide to long.
> >> and if you tried already something, send the commands you have tried,
> >> so its possible to tell you where is the syntaxis mistake.
> >> Fernando
> >> On Thu, Aug 9, 2012 at 2:21 PM, felix kreppel <felix.kreppel@gmx.de>
> >> wrote:
> >> > Hello Fernando,
> >> >
> >> > Thank you for your quick response.
> >> >
> >> > I thought of this. Do you mean, that I should reshape my dataset in
> the
> >> following way?
> >> >
> >> >
> >> >       year   return std market_return
> >> > firm1 1985
> >> >       1986
> >> >       1987
> >> > firm2 1985
> >> >       1986
> >> >       1987
> >> >
> >> > and then run a simple linear regression?
> >> >
> >> > I tried different reshape commands-, but none of them seems to work..
> >> >
> >> > -------- Original-Nachricht --------
> >> >> Datum: Thu, 9 Aug 2012 14:01:33 -0400
> >> >> Von: Fernando Rios Avila <f.rios.a@gmail.com>
> >> >> An: statalist@hsphsun2.harvard.edu
> >> >> Betreff: Re: st: Regression with different firms
> >> >
> >> >> Felix,
> >> >> Look at -help reshape-
> >> >> HTH
> >> >> Fernando
> >> >> On Thu, Aug 9, 2012 at 1:58 PM, felix kreppel <felix.kreppel@gmx.de>
> >> >> wrote:
> >> >> >
> >> >> > Hello,
> >> >> >
> >> >> > I have regression problem:
> >> >> >
> >> >> > I have a dataset consisting of yearly firm returns (for
> firm1-firm3)
> >> and
> >> >> the volatility of each firm in that month(std1-std3) and a data on a
> >> >> monthly market return (market_return) over a specific timepriod.
> >> >> >
> >> >> > No I want to estimate the following regression over the whole time
> >> >> period:
> >> >> >
> >> >> > return_firm_i = a*std_i + b* market_return
> >> >> >
> >> >> > Its not a problem to do this with only one firm:
> >> >> >
> >> >> > regress firm1 std1 market_return, robust
> >> >> >
> >> >> > However, I want to do this for the whole dataset and estimate
> single
> >> >> coefficients.
> >> >> >
> >> >> > Could somebody help me?
> >> >> >
> >> >> >
> >> >> > My dataset looks like this:
> >> >> >
> >> >> > date    firm1 firm2 firm3 std1 std2 std3 market_return
> >> >> > 1985    0.03   0.04  0.05  0.3  0.4  0.5    0.6
> >> >> > 1986   ..
> >> >> > 1987    ...
> >> >> >
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index