GSboot_multireg {FRB} | R Documentation |
Calculates bootstrapped GS-estimates and bootstrap confidence intervals using the Fast and Robust Bootstrap method.
GSboot_multireg(X, Y, R, conf=0.95, ests = GSest_multireg(X, Y))
X |
a matrix or data frame containing the explanatory variables. |
Y |
a matrix or data frame containing the response variables. |
R |
number of bootstrap samples |
conf |
confidence level of the bootstrap confidence intervals. Default is conf=0.95 |
ests |
GS-estimates as returned by GSest_multireg () |
Called by FRBmultiregGS
and typically not to
be used on its own. If no original GS-estimates are provided the function uses the value of GSest_multireg
.
The fast and robust bootstrap was first developed by Salibian-Barrera and Zamar (2002) for univariate regression MM-estimators.
The value centered
gives a matrix with R
columns and p*q+q*q rows (p is the number of explanatory variables without intercept
and q is the number of response variables), containing the recalculated GS-estimates. Each column represents a different bootstrap sample.
The first p*q rows are the recalculated slope estimates and the next q*q rows are the covariance estimates
(the estimates are vectorized, i.e. columns stacked on top of each other). These bootstrap estimates are centered by the original
estimates, which are also returned through vecest
in vectorized form.
The output list further contains bootstrap standard errors, as well as so-called basic bootstrap confidence intervals and bias corrected and accelerated confidence intervals (Davison and Hinkley, 1997, p.194 and p.204 respectively).
A list containing the following components:
centered |
a matrix of all fast and robust bootstrap recalculations where the recalculations are centered by the original estimates (see Details). |
vecest |
a vector containing the orginal estimates stacked on top of each other |
SE |
bootstrap standard errors for the estimates in vecest |
CI.bca |
a matrix containing bias corrected and accelerated confidence intervals, corresponding to the
estimates in vecest (first column are lower limits, second column are upper limits) |
CI.basic |
a matrix containing basic bootstrap intervals, corresponding to the
estimates in vecest (first column are lower limits, second column are upper limits) |
Ella Roelant and Gert Willems
data(schooldata) school.x <- data.matrix(schooldata[,1:5]) school.y <- data.matrix(schooldata[,6:8]) #computes 10 bootstrap recalculations starting from the GS-estimator #obtained from GSest_multireg bootres <- GSboot_multireg(school.x,school.y,R=10)