Generating tables for my Thesis

[Murat Whitestone]

Dear all,

As is mentioned in the title, I need to generate/make a table for my thesis like the tables of Baber et al. (2001). Hereby making a table including the coefficients and t statistics of the 3 factor model of Fama and French for 5 portfolios. And another table including the constants and t statistics of different regressions, also for the 5 portfolios.

I searched for like 2 weeks now, without the results I need. Tried; table, estate, estout, tabstat ...

[Murat Whitestone]

Something like this:
Portfolio - Coefficient Rm-Rf - Coefficient SMB - Coefficient HML
1 ..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
2..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
3..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
4..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
5..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)

And this:

Portfolio - Intercept Market adjusted return - Intercept CAPM - Intercept 3-factor model
1 ..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
2..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
3..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
4..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)
5..................... ...................... ...........................
(t- stat) - (t stat) - (t stat)

[William Lisowski]

Welcome to Statalist.

What is not clear to me is where your problem lies. Is it that you have run the models but do not know how to turn the results into tables? Or is it that you do not know how to produce the requested statistics? Given the commands you have tried, I think your problem is with the former, with getting your results into tables.

The quick answer is to copy and paste your results from Stata's Results window into the document you are creating. That's where I would have gone after two days of failed attempts, much less two weeks.

The longer answer is that you do not tell us enough to be able to advise you. Many of the members are unfamiliar with the "3 factor model of Fama and French", or with financial modeling in general. You've apparently realized in post #2 that expecting the reader to be familiar with, or willing to go searching for, "Baber et al. (2001)" was asking a lot of the reader. Assuming familiarity with the model in question similarly limits the number of members who can respond to you. But it doesn't require familiarity with the model to answer you question. It requires knowing what commands you run, and what output from those commands you want to capture and place in your table.

Please start by reviewing the Statalist FAQ linked to from the top of the page, as well as from the Advice on Posting link on the page you used to create your post. Note especially sections 9-12 on how to best pose your question. The more you help others understand your problem, the more likely others are to be able to help you solve your problem.

It would be particularly helpful to copy commands and output from for one portfolio from your Stata Results window and paste it into your Statalist post using CODE delimiters, as described in section 12 of the FAQ. You will note in your second post that your "samples" do not appear as you expected, because you neglected to use CODE delimiters. For example, the following:

[code]
// sample code
sysuse auto, clear
describe
[/code]

will be presented in the post as the following:

// sample code
sysuse auto, clear
describe

Once you have shared the results with us, be sure to indicate which numbers correspond to the various coefficient estimates and intercepts. With that done, someone may well be able to figure out how to automate the results you need.

[Murat Whitestone]

Sorry for the things that I did wrong in my posts. As I am in a hurry to find solutions.
You was right, that I already have all the information, like the coefficients and t statistics via the stats by command.

The only thing remaining for me is to present the statistics in a nice table, which include those coefficients and t statistics for all portfolios.
Hence, every portfolio (group of stocks) should have a Coefficient for (Rm-Rf), SMB, HML presented. And Underneath the coefficients the t-statistics shown.

See the table of Barber et al (2001) shown in the picture. Hope this will make things more clear.

[William Lisowski]

I think copy-and-paste, or simply retyping the results, into a Microsoft Word table, and fiddling with the formatting in Word, is your answer.

[William Lisowski]

Deleted - somehow #5 got posted twice.