<< threesls Multivariate regressions VAR estimations >>

Grocer >> Multivariate regressions > twosls

twosls

Two-Stage Least-squares Regression

CALLING SEQUENCE

[results]=twosls(arg1,...,argn)

PARAMETERS

Input

* argi= arguments which can be:

  - an equation of the following form:

  'vary = coef1*varx1+...+coefi*varxi' where:

    . coefi = the name of a coefficient

    . varxi = the name of a variable

  - 'coef=coef1;coef2;...coefn' where coef1,...,coefn are the names of the coefficients in the system (optional; default: 'coef=a1;...,an')

  - 'endo =[endo1;...;endon]' where endo1,...,endon are the names of the endogenous variables (optional; necessary if the names of the endogenous variables in the rhs of the equations are not the same as those of the lhs; default: the names of all the lhs sides of the equations)

  - the string 'noprint' if you do not want to print the results

  - the string 'dropna' if the user wants to remove the NA values from the data

 

Output

* results = a results tlist with:

  - results('meth') = 'tsls'

  - results('namecoef') = the matrix of the names of the coefficients

  - results('riv1'),...,results('rivn) = the results of the iv estimation for each equation (see iv for more details)

DESCRIPTION

Computes Two-Stage Least-squares Regression.

EXAMPLE

x1 = rand(200,1,'n');
x2 = rand(200,1,'n');
evec = rand(200,2,'n');
//
// create simultaneously determined variables y1,y2
y1 =1+x1+evec(:,1);
y2 = 1+y1+x2+evec(:,2);
 
rt=twosls('y1=a+b*x1','y2=d+e*(y1-x2)+f*x2','coef=a;b;d;e;f')
 
// Example taken from function twosls_d. The equations are 'y1=a+b*x1' and 'y2=d+e*(y1-x2)+f*x2'.
// Coefficients are a, b, d, e and f. Their name is given to the function through the input 'coef=a;b;d;e;f'.

AUTHOR

Eric Dubois 2002-2007

Report an issue
<< threesls Multivariate regressions VAR estimations >>