<< pfixed1 Panel equation regressions phaussman >>

Grocer >> Panel equation regressions > pfixed_hac1

pfixed_hac1

Robust variance matrix for fixed effect panel data

CALLING SEQUENCE

res=pfixed_hac1(y,index,x,typvcv)

PARAMETERS

Input

• y = a (T x 1) vector of endogenous variable

• index = a (T x 1) index vector that identifies each observation with an individual

• e.g. 1 (first 2 observations for individual # 1)

• 1

• 2 (next 1 observation for individual # 2)

• 3 (next 3 observations for individual # 3)

• 3

• 3

• x = matrix of exogenous variables

• typvcv = 1 or 2 with

 - 1 for  "clustered" covariance matrix of Arellano (1987) (detailed references are available in the Grocer manual) recommended when T is fixed and N large

• (but "works" also when T is large and N fixed, see Hansen C. B. [2007])

 - 2 (only in case of balanced panels) for a Newey-west type estimator (recommended when T is large and N fixed, see Arellano (2003))

Output

• res = a results tlist with:

  - res('meth')='panel with fixed effects'

  - res('y') = y data vector

  - res('x') = x data matrix

  - res('nobs') = nobs

  - res('nvar') = nvars

  - res('beta') = bhat

  - res('yhat') = yhat

  - res('resid') = residuals

  - res('vcovar') = estimated variance-covariance matrix of beta

  - res('sigu') = sum of squared residuals

  - res('sige') = estimated variance of the residuals

  - res('ser') = standard error of the regression

  - res('tstat') = robust t-stats

  - res('pvalue') = pvalue of the betas

  - res('condindex') = multicolinearity cond index

  - res('prescte') = boolean indicating the presence or absence of a constant in the regression

  - res('llike') = log-likelihood

  - res('rsqr') = rsquared

  - res('rbar') = rbar-squared

  - res('f') = F-stat for the nullity of coefficients other than the constant

  - res('pvaluef') = its significance level

  - res('hac') = type of HAC variance matrix

DESCRIPTION

Performs HAC variance correction for fixed effects estimation panel model (for balanced or unbalanced data). Low level function that works only with matrices.

EXAMPLE

res=pfixed_hac1(y,index,x,typvcv)
 
// In this example, y and index should be (nobs x 1) vectors, x a (nobs x k) matrix.

AUTHOR

Eric Dubois 2005 and Emmanuel Michaux 2010

<< pfixed1 Panel equation regressions phaussman >>