pcomp & "series or groups for conditioning"

[ev7u]

Hi there,

Regarding the group procedure "make principal components", documentation for syntax does not seem to mention how to replicate the corresponding GUI option called "series or groups for conditioning".

Said a bit diferently, a direct question would be the following: what would be the corresponding option in "group_name.pcomp(options) [indices]" that will allow me to specify that the analysis should be conditioned on, say, variable x2.

Many thanks,
ev7u

PS these are the documented options for the covariance portion in the help and documentation [i'm using eviews 7.0]..option "series or groups for conditioning" not mentioned.

Covariance Options

cov=arg (default="corr")
Covariance calculation method: ordinary (Pearson product moment) covariance ("cov"), ordinary correlation ("corr"), Spearman rank covariance ("rcov"), Spearman rank correlation ("rcorr"), uncentered ordinary correlation ("ucorr"). Note that Kendall's tau measures are not valid methods.

wgt=name (optional)
Name of series containing weights.

wgtmethod=arg (default = "sstdev")
Weighting method: frequency ("freq"), inverse of variances ("var"), inverse of standard deviation ("stdev"), scaled inverse of variances ("svar"), scaled inverse of standard deviations ("sstdev").

Only applicable for ordinary (Pearson) calculations where "weights=" is specified. Weights for rank correlation and Kendall's tau calculations are always frequency weights.

pairwise
Compute using pairwise deletion of observations with missing cases (pairwise samples).

df
Compute covariances with a degree-of-freedom correction accounting for the mean (for centered specifications) and any partial conditioning variables (for the default "cov=cov", and the "cov=ucov" specifications).

The default behavior in these cases is to perform no adjustment (e.g. - compute sample covariance dividing by rather than ).

[EViews Gareth]

partial=nameofseries

[ev7u]

Thank you.