3
\title{Fisher test for a linear model.}
5
This ROT function, called from a Test C++ object, is given two samples, a
6
scalar and a parameter vector. It predicts the values corresponding to the
7
explanatory variables through the linear model, then computes the Fisher
8
statistic. It is tested against the scalar, then the function returns the
9
result of the test and the Fisher value.
12
testLmFisher(x, beta, y, testLevel = 0.95)
15
\item{x}{A m-by-n matrix containing the explanatory variables.}
16
\item{beta}{A n-by-1 vector containng the linear model parameters.}
17
\item{y}{A n-by-1 vector containng the response variables.}
18
\item{testLevel}{the test level. (scalar in [0:1])}
21
A list is returned, containing two scalars ,
22
\item{testResult}{A scalar simulating a boolean (easier for Rserve)}
23
\item{valueFisher}{A scalar.}
26
As it is not asked in LinearModel.getPredict(), no prediction interval
27
is returned; it is up to the user to be careful about that. It is also to
28
noted that the sample is not assumed to contain the '1's corresponding to
29
the intercept parameter.
31
\author{Pierre-Matthieu Pair, Softia for EDF.}
34
x <- matrix(runif(40), 10, 4)
35
r <- matrix(c(1,2,3,4), 4, 1)
36
y <- x \%*\% r + matrix(rnorm(10, 0, 0.05), 10, 1)
37
LM <- computeLinearModel(x, y)
38
testLmFisher(x, LM$parameterEstimate, y)
40
\keyword{multivariate}
b'\\ No newline at end of file'