Gloria González-Rivera, Tae-Hwy Lee, and Santosh Mishra, "Jumps in
Cross-Sectional Rank and Expected Returns: A Mixture Model", Journal of
Applied Econometrics, Vol. 23, No. 5, 2008, pp. 585-606.

The zip file glm-data.zip contains five data files, all of which are 
ASCII files in DOS format. Unix users should use "unzip -a". The 
description of each file is given below.


sp500CrossSectionReturn.txt: This file contains the data for weekly 
returns of S&P 500 constituent firms from January 8th 1990 through 27th 
December 2005. The dataset has 500 columns and 833 rows. Individual 
columns represent the weekly returns of a given company during the time 
period specified above. Thus each row provides information about weekly 
returns of 500 firms on that give day. Further note that Value -5000 
implies that the data were not available for that specific ticker name 
during that time period. One possible reason is, if a company (or the 
ticker) is created on December 16th 1992 then for the time period 
between January 8th 1990 through December 16th 1992 all the observations 
have entry -5000.

Data Source: finance.yahoo.com and Standard and Poor Data services.


sp500TickerName.txt: This file contains the ticker name for the 
constituents of S&P 500 index on December 2000. The order of the ticker 
name is identical to the order of the columns in file 
sp500CrossSectionReturn.txt (for example the first column of the this 
file represents the weekly return of ticker AHC). The dataset has 500 
rows and one column. The sector information for the tickers is given as 
follows.

Energy Sector: Rows 1 through 26
Material Sector: Rows 27 through 68
Industrial Sector: Rows 69 through 137
Consumer goods Sector: Rows 138 through 257
Health Sector: Rows 258 through 298
Finance Sector: Rows 299 through 372
Information Technology Sector: Rows 373 through 461
Utility Sector: Rows 462 through 500

Data Source: http://www2.standardandpoors.com


sp500_price.txt: This provides the closing S&P 500 index value from 
January 2th 1990 through 27th December 2005. It has two columns and 834 
rows. The first column gives the date, and the second column provides 
the closing index value on that given date.

Data Source: finance.yahoo.com


sp500_return.txt: This provides the S&P 500 index weekly percentage 
return from January 8th 1990 through 27th December 2005. It has two 
columns and 833 rows. The first column gives the date, and second column 
provides the weekly percentage on that given date.

Data Source: finance.yahoo.com


Risk_free_rate.txt: This provides the annualized 3 months Treasury bill 
rate from January 8th 1990 through 27th December 2005. It has two 
columns and 833 rows. The first column gives the date, and second column 
provides the interest rate.

Data Source: http://research.stlouisfed.org/fred2/