Pooled estimation for panel data
namey = a real (Nx1) vector or a string equal to the name of a time series or a (Nx1) real vector between quotes (this last case is the only one authorized if you are using a 'panel data' tlist, see below)
first input of varargin:
- either a 'panel data' tlist (generally imported from a .csv database by function impexc2bd)
- or an endogenous variable taking the form of a time series, a real (Nx1) vector or a string equal to the name of a time series or a (Nx1) real vector between quotes
other input of varargin:
- if first input of varargin was a 'panel data' tlist then other input are optional and can be:
* either 'x=name1; ;namep' where name1, ,namep are a subset of the names of the variables that are in the database
* the string 'nameid=name1, , namen' where name1, are names of individuals present in the database
- if first input of varargin was an endegnous variable then
* either a time series
* a real (TxN) matrix
* a (Nx1) string vector of names of time series, vectors or matrices
* the string 'id=v' where v is the vector of individuals attached to the y and x data (this argument must be present somewhere in the list of variables arguments)
* or the string 'noprint' if the user doesn't want to print the results of the regression
- 'hac=ccm' 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]) or only in case of balanced panel 'hac=nw' for a Newey-west type estimator (recommended when T is large and N fixed, see Arellano (2003)).
When using 'hac' option the string 'id=v' must be given somewhere when calling the function. It can be in the panel tlist or an argument of the function.
res = a results tlist with:
- res('meth') ='pooled panel'
- 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') = 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('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('gls estimation method') = the gls method used
- res('fixed effects') = the estimation of the individual effects
- res('prests') = boolean indicating the presence or absence of a time series in the regression
- res('namey') = name of the y variable
- res('namex') = name of the x variables
- res('hac') = type of robust variance matrix in case of HAC estimation
load(GROCERDIR+'\macros\grocer\db\judgepanel.dat') ; r = ppooled('y',judgepanel); // Example is taken from function panel_d. Provides fixed panel estimation on Judge et alii example. | ![]() | ![]() |