<< stdboot Resampling Tests >>

Stixbox >> Stixbox > Resampling > stdjack

stdjack

Jackknife estimate of the standard deviation of a parameter estimate.

Calling Sequence

s=stdjack(x,T)
[s,y]=stdjack(x,T)

Parameters

x :

a matrix of doubles

T :

a function or a list, the function which computes the empirical estimate from x.

s :

a 1-by-1 matrix of doubles, the estimate of the standard deviation

y :

a 1-by-n matrix of doubles, the values of T of the resamples, where n is the size of the parameter estimate

Description

Jackknife estimate of the standard deviation of the parameter estimate T(x).

The function T must have the following header:

p=T(x)
where x is the sample or the resample and p is a m-by-1 matrix of doubles. In the case where the parameter estimate has a more general shape (e.g. 2-by-2), the shape of p is reshaped into a column vector with m components.

See "T and extra arguments" for details on how to pass extra-arguments to T.

The function is equal to

sqrt(diag(covjack(x,T)))

Examples

n = 20;
x=distfun_chi2rnd(3,n,1);
m=mean(x) // Empirical mean
s=stdev(x)/sqrt(n) // Standard error for the mean
s=stdjack(x,mean) // Standard error with Jackknife
// Get y
[s,y]=stdjack(x,mean);
size(y)
// Estimate the standard deviation of the median
m=median(x)
s=stdjack(x,median)

// With extra arguments
x=distfun_chi2rnd(3,50,5);
mean(x,"r")
[s,y]=stdjack(x,list(mean,"r"));
size(y)

Authors


Report an issue
<< stdboot Resampling Tests >>