fpc (version 2.2-7)

clusexpect: Expected value of the number of times a fixed point cluster is found

Description

A rough approximation of the expectation of the number of times a well separated fixed point cluster (FPC) of size n is found in ir fixed point iterations of fixreg.

Usage

clusexpect(n, p, cn, ir)

Arguments

n

positive integer. Total number of points.

p

positive integer. Number of independent variables.

cn

positive integer smaller or equal to n. Size of the FPC.

ir

positive integer. Number of fixed point iterations.

Value

A number.

Details

The approximation is based on the assumption that a well separated FPC is found iff all p+2 points of the initial coinfiguration come from the FPC. The value is ir times the probability for this. For a discussion of this assumption cf. Hennig (2002).

References

Hennig, C. (2002) Fixed point clusters for linear regression: computation and comparison, Journal of Classification 19, 249-276.

See Also

fixreg

Examples

Run this code
# NOT RUN {
  round(clusexpect(500,4,150,2000),digits=2)
# }

Run the code above in your browser using DataCamp Workspace