<< waldf0 Econometric tests and diagnostics white0 >>

Grocer >> Econometric tests and diagnostics > white

white

White's heteroskedasticity test

CALLING SEQUENCE

[resulwhite]=white(resulols,np)

PARAMETERS

Input

* resulols = results tlist from a first stage estimation returns a tlist

* np = 'noprint' if the user does not want to display the results (optional argument!)

 

Output

* resulwhite = a results tlist with:

  - resulwhite('meth') = 'white'

  - resultwhite('resul1st') = results tlist of the first stage regression

  - resulwhite('f') = White statistic (Fisher form)

  - resulwhite('p') = p-value of the test

  - resulwhite('dfnum') = degrees of freedom of the numerator

  - resulwhite('dfden') = degrees of freedom of the denominator

  - resulwhite('f_pvalue') = p-value of the test

  - resulwhite('chistat') = p-value of the test

  - resulwhite('f_chistat') = p-value of the test

DESCRIPTION

Computes the value of White's heteroskedasticity test (see White, H. (1980) "A heteroskedastic-consistent covariance matrix estimator and a direct test for heteroskedasticity", Econometrica, 48, 817-838). Results are stored in a tlist and displayed on screen if the user has not given as second argument 'noprint'.

EXAMPLE

load(GROCERDIR+'/data/bdhenderic.dat');
bounds('1964q3','1989q2');
rols=ols('delts(lm1-lp)','delts(lp)','delts(lagts(1,lm1-lp-ly))','rnet', 'lagts(1,lm1-lp-ly)', 'const');
r=white(rols)
 
// This example stores in tlist r, and displays on screen, White's test on regression results stored in he.

AUTHOR

Eric Dubois 2002

Report an issue
<< waldf0 Econometric tests and diagnostics white0 >>