Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: Comparing two timeseries regressions using esttab


From   Robson Glasscock <[email protected]>
To   [email protected]
Subject   Re: st: Comparing two timeseries regressions using esttab
Date   Mon, 18 Apr 2011 12:49:29 -0400

Hi Victor,
If I'm understanding you correctly, you are trying to conduct a
hypothesis test to see if there is a difference between two parameters
obtained from separate regressions. Let's call the first parameter B1
and the second parameter B2. Under the null hypothesis of parameter
equality B1= B2, so  B1-B2= 0. To find the statistical significance of
the difference, you need estimates of the variance of each parameter
and the covariance between them.

The test statistic will be (B1-B2)/ [Var(B1) + Var(B2) + 2Cov(B1,B2)] ^.5

The covariance between the parameters should be 0 if they are from
separate regressions, so you can drop the third term in the
denominator.

best,
Robson Glasscock


On Mon, Apr 18, 2011 at 11:03 AM, Victor Kihlgren <[email protected]> wrote:
> Thank you for the tip. Is significance level of differences possible to obtain using only t-statistics? I am trying to replicate an essay comparing two different set of funds exposure to risk-classes.
>
> many thanks
>
> victor
>
> ________________________________________
> Från: [email protected] [[email protected]] f&#246;r Charles Koss [[email protected]]
> Skickat: den 18 april 2011 16:31
> Till: [email protected]
> Ämne: Re: st: Comparing two timeseries regressions using esttab
>
> use Excel to get the difference. Why do you want to obtain the
> significance level of each difference?
>
> Charles
>
> On Mon, Apr 18, 2011 at 2:19 AM, Victor Kihlgren <[email protected]> wrote:
>>
>> Hello,
>>
>> I would like to compare two timeseries regressions using esttab. Ive managed to tabulate the results but i would like a column showing the difference between each beta and the significance level of each difference, how is this possible?
>>
>> Thanks
>>
>> Victor
>> *
>> *   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/
> *
> *   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/
>



--
Robson Glasscock, CPA
Accounting PhD Student
Virginia Commonwealth University
Snead Hall, B3132
P.O. Box 844000
Richmond, VA 23284

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index