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: Fwd: How to manipulate crsp data to construct momentum portfolio
From
Robson Glasscock <[email protected]>
To
[email protected]
Subject
Re: st: Fwd: How to manipulate crsp data to construct momentum portfolio
Date
Tue, 4 Oct 2011 10:11:12 -0400
Your explanation is clear, but you haven't said where your problem is.
How far are you able to get before getting stuck?
On Mon, Oct 3, 2011 at 1:08 AM, Tang, Fang <[email protected]> wrote:
> Hi, statalist,
>
> This question really bothers me a lot.
> I want to construct 10 momentum portfolios and calculate their monthly
> return. Part of the monthly data is as follows. At the end of each
> month, I have the data of price(prc), ret(current month return),
> market capitalization for all the stocks--all variables possibly
> missing. My methodology is as follows. At the end of month, I exclude
> all stocks with 1) price< $5 2) market cap in the smallest 10%
> 3) no missing monthly return for previous 6 months.(Here, I understand
> the sequence of these operations matters, but any choice is fine).
> After this, I split all the left stocks into 10 deciles based on
> their previous 6 months cumulative return and keep track of these 10
> portfolios to calculate corresponding equally weighted monthly returns
> for the future 6 months. Note some of the stocks may be unlisted in
> the next 6 months so missing values may emerge here. If this happens,
> just reduce the number of stocks contained in each portfolio to
> calculate the equally weighted monthly returns. Lastly, since all
> those portfolios will be held for 6 months, at the end of each month,
> I actually have 6 portfolios available in each decile.One formed right
> now, one formed 1 month ago, one formed 2 months ago, and ....one
> formed 5 months ago. So the real monthly return is equally weighted
> return of those 6 portfolios for each decile. The final output is
> monthly returns for each of the 10 decile portfolio.
>
> I hope I made myself clear enough. Thanks very much
>
> Stanley Tang
>
> +----------------------------------------------------------------------------------------------------------------------+
> | date year month cusip ticker permno permco
> shrout prc ret time cap |
> |----------------------------------------------------------------------------------------------------------------------|
> 1. | 01/31/1964 1964 1 04559140 AOE 29233 23606
> 16 5.6875 -.031915 31jan1964 91 |
> 2. | 01/31/1964 1964 1 91102630 UMO 37647 24250
> 16 5.71875 -.056701 31jan1964 91.5 |
> 3. | 01/31/1964 1964 1 25474130 DIL 31245 23763
> 51 3.59375 -.128788 31jan1964 183.2813 |
> 4. | 01/31/1964 1964 1 74099090 PMW 39001 24352
> 415 .53125 .0625 31jan1964 220.4688 |
> 5. | 01/31/1964 1964 1 36959520 GLE 32168 23832
> 26 9.25 -.130667 31jan1964 240.5 |
> |----------------------------------------------------------------------------------------------------------------------|
> 6. | 01/31/1964 1964 1 14444770 CRL 30373 23700
> 318 .78125 -.074074 31jan1964 248.4375 |
> 7. | 01/31/1964 1964 1 88880320 TSU 37372 24225
> 97 2.75 -.083333 31jan1964 266.75 |
> 8. | 01/31/1964 1964 1 88880330 TSU 37380 24225
> 34 7.9375 .024194 31jan1964 269.875 |
> 9. | 01/31/1964 1964 1 04999290 ASW 29364 23616
> 890 .375 0 31jan1964 333.75 |
> 10. | 01/31/1964 1964 1 95969010 WSI 38017 24279
> 677 .5 0 31jan1964 338.5 |
> +----------------------------------------------------------------------------------------------------------------------+
>
> *
> * 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/