<< pfixed1 Panel equation regressions pfixed_mbb1 >>

Grocer >> Panel equation regressions > pfixed_hac1

pfixed_hac1

Panel equation regressions

CALLING SEQUENCE

 rpanel=pfixed_hac1(y,index,x,typvcv,win)

PARAMETERS

Input

* y = a (nobs*nindiv x 1) matrix of all of the individual's observations vertically concatenated. This matrix must include in the first column the dependent variable, the independent variables must follow accordingly.

* index = 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 = a (nobs*nindiv x k) matrix of exogenous variables

* typvcv = 1 or 2 with

  - 1 "clustered" covariance matrix of Arellano (1987) recommended when T is fixed and N large but also "works" when T is large and N fixed see Hansen C. B. (2007) (reference below)

  - 2 a Newey-west type (Driscoll-Kray) estimator recommended when T is large and N fixed

* win = the length of the Barlett window kernel estimator (default = automatic selection by Andrews (1991) using an AR(1) model)

 

Output

* res = a tlist with

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

  -rpanel('y') = y data vector

  -rpanel('x') = x data matrix

  -rpanel('nobs') = nobs

  -rpanel('nvar') = nvars

  -rpanel('beta') = bhat

  -rpanel('yhat') = yhat

  -rpanel('resid') = residuals

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

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

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

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

  -rpanel('tstat') = t-stats

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

  -rpanel('condindex') = multicolinearity cond index

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

  -rpanel('lliked') = log-likelihood

  -rpanel('rsqr') = rsquared

  -rpanel('rbar') = rbar-squared

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

  -rpanel('pvaluef') = its significance level

  -res('hac') = type of robust variance matrix in case of HAC estimation

DESCRIPTION

Performs HAC variance correction for fixed effects panel model. Low level function that works only with matrices.

AUTHOR

Emmanuel Michaux 2012

Report an issue
<< pfixed1 Panel equation regressions pfixed_mbb1 >>