st: Question "using 2sls with 2 simulatanious eqation

[Talal <talalesm@yahoo.com>]

Hi all,

* I want to check the impact of different level of Operating costs on Fare which in turns impacts Demand. So Costs --> Fare --> Demand.

1) First I estimated a bus demand function using Fixed Effect Method using real data as follows :

demand equation is

D= f (Fare, Income, , Time Trend, Regional Dummies)…..(1)



2) In latter stage, I also estimated Fare functions using Fixed Effect Method and real data as follows:

Fare function is 

F = f( Operating Cost, Time Trend, Regional Dummies)………………….(2)

* Now I will assume there was a different policy applied before 10 years and which affected operating costs (I have a forecasted data of operating costs).

Before I can substitute the new values of operating costs in fare equation and use the estimated values of fare in the demand equation, I have been asked first to use 2sls technique, Why?:

1)    Is that because two-stage least squares regression (2SLS) is a method of extending regression to cover models which violate ordinary least squares (OLS) regression's assumption of recursivity, specifically models where the researcher must assume that the disturbance term of the dependent variable is correlated with the cause(s) of the independent variable(s)?

 In my case, since I used Fixed Effect method which allow for correlation between regressors and error term.


2)    If yes, a problematic causal variable is an endogenous variable whose disturbance term is posited to be correlated with the disturbance term of another endogenous variable on which it has a direct effect. Problematic causal variables are replaced by substitutes in the first stage of 2SLS.

I can see the Fare is a problematic causal variable, but  what and how to specify the 2nd endogenous variable (is it the dependent variable in Eq 1 “Demand” or one of the other explanatory variables in that equation.

3)Regarding instruments: In my Case ; the instruments are ( Operating Cost , Time Trend, Regional Dummies), right?


Finally the STATA commands will be:

. ivreg Demand Income Timetrend, RegionalDummies (Fare = OperatingCost  TimeTrend RegionalDummies)


I am very thankful in advance for any answers or comments on my question


Kind Regards
Talal



      

*
*   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/