st: panel data analysis

[Erik Paas <noviral@gmail.com>]

I have 269 companies (tickers), their weekly stock returns, weekly
volume and another hopefully related variable (an index named
variable_x).
Aim is to investigate whether variable_x has any predictive power on
returns and/or volume.
How should I proceed using Stata?

Example of data:


Ticker      return_week    volume_week     variable_x           date

AAPL     0.0544                9934332               20                15jan2005

AAPL     0.0223                3432432               18                22jan2005

MSFT     0.0212                7556665               80                15jan2005

MSFT     0.0334                23444444             78                22jan2005

PEP       -0.0221               55665555             56                15jan2005

PEP        0.0865               1223322               89
 22jan2005


Furthermore I would like to add the S&P500 weekly returns as another variable.
Calculate excess return over the market (company  return - S&P500 return)
Then test whether highest growers of variable_x also earn highest
excess returns.


Erik

*
*   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/