Confidence intervals of coefficients
These functions calculate the confidence intervals of the
coefficients from an object returned by systemfit.
## S3 method for class 'systemfit'
confint( object, parm = NULL, level = 0.95,
useDfSys = NULL, ... )
## S3 method for class 'systemfit.equation'
confint( object, parm, level = 0.95,
useDfSys = NULL, ... )object |
an object of class |
parm |
not used yet. |
level |
confidence level. |
useDfSys |
logical. Use the degrees of freedom of the whole system
(in place of the degrees of freedom of the single equation)
to calculate the confidence intervals of the coefficients.
If it not specified ( |
... |
other arguments. |
An object of class confint.systemfit, which is a matrix
with columns giving lower and upper confidence limits
for each estimated coefficient. These will be labelled as
(1-level)/2 and 1 - (1-level)/2 in % (by default 2.5% and 97.5%).
Arne Henningsen arne.henningsen@googlemail.com
data( "Kmenta" ) eqDemand <- consump ~ price + income eqSupply <- consump ~ price + farmPrice + trend system <- list( demand = eqDemand, supply = eqSupply ) ## perform OLS on each of the equations in the system fitols <- systemfit( system, data = Kmenta ) ## confidence intervals of all coefficients confint( fitols ) ## confidence intervals of the coefficients of the first equation confint( fitols$eq[[1]] ) ## confidence intervals of the coefficients of the second equation confint( fitols$eq[[2]] )
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.