two stage least squares coding problem

[spasico]

Syntax error occurs when I run 2SLS, but the data should be fine as the file I attached. I think the problem might be the part of running regression, but I don't know where wrong.

my first stage function is : batie = ln_ta ROA leverage growth age CPA big4 ibsize loss loss_lag liquidity INVplusAR_TA btm employ LD 

where "batie" is an endogenous variable, "employ" and "LD" are Instrument Variables for batie, other variables are exogenous variable ; 

my second stage function is : am = batie ln_ta ROA leverage growth age CPA big4 ibsize loss loss_lag liquidity INVplusAR_TA btm ;

SAS code are as following:

libname ok 'd:\all\ipo';
run;

proc model data=ok.www;
instruments employ LD;
batie = ln_ta ROA leverage growth age CPA big4 ibsize loss loss_lag liquidity INVplusAR_TA btm employ LD;
am = batie ln_ta ROA leverage growth age CPA big4 ibsize loss loss_lag liquidity INVplusAR_TA btm ;
fit batie am / 2sls outv=vdata vardef=n kernel=(bart,0,);
title '2sls results';
run;
quit;

How can I fix this?

[kessler · Accepted solution]

PROC MODEL requires that your model is specified using a mathematical expression including explicit parameters rather than just using a list of variables.  To do a two stage least squares estimation for your model you could use something like the following:

proc model data=new;
	am = p_batie*batie + p_ln_ta*ln_ta + p_ROA*ROA + p_leverage*leverage + p_growth*growth + p_age*age 
           + p_CPA*CPA + p_big4*big4 + p_ibsize*ibsize + p_loss*loss + p_loss_lag*loss_lag 
           + p_liquidity*liquidity + p_INVplusAR_TA*INVplusAR_TA + p_btm*btm;
	fit  am / 2sls outv=vdata vardef=n kernel=(bart,0,);
	instruments _exog_ employ LD;
	title '2sls results';
quit;