lrt {merror}

Likelihood ratio test for all betas equalling one.

Description

Likelihood ratio test statistic - H0: all betas = one.

Usage

lrt(x, M = 40)

Arguments

x

n (no. of items) x N (no. of methods) matrix or data.frame containing the measurements. N must be greater than 3 and n > N.

M

Maximum no. of iterations for convergence.

Details

See Jaech, pp. 204-205.

Value

n.items

No.of items.

N.methods

No. of methods.'

beta.bars

N vector of estimated betas.

lambda

Chi-square test statistic.

df

Degrees of freedom for the test (N-1).'

p.value

Empirical significance level for the observed test statistic.'

Author(s)

Richard A. Bilonick

References

Jaech, J. L. (1985) Statistical Analysis of Measurement Errors. New York: Wiley.

See Also

ncb.od,cb.pd,pm2.5

Examples

data(pm2.5)

lrt(pm2.5) # compare all 5 samplers (4 personal and 1 frm)

lrt(pm2.5[,1:4]) # compare only the personal samplers

stem(lrt(pm2.5)$beta.bars) # examine the estimated betas