lc50_improved: LC Estimation by the Improved Linear Regression Method

In insectecol: Insect Ecology Data Analysis Toolkit

LC Estimation by the Improved Linear Regression Method

Description

Estimates the lethal concentration with a weighted least-squares line: the same probit-log transformation as the traditional method, but each concentration is weighted by the inverse of the variance of its observed mortality, which makes the regression more robust.

Usage

lc50_improved(d, lc = 0.5)

Arguments

d	Same as lc50_traditional.
lc	Same as lc50_traditional.

Details

The weights are the inverse-variance (optimal) weights of the probit transform, w = n * phi(z)^2 / (p * (1 - p)), where n is the number of insects tested, p the corrected mortality and z = qnorm(p) the corresponding standard normal quantile: the variance of a probit-transformed mortality is p * (1 - p) / (n * phi(z)^2), smallest at intermediate mortalities and growing without bound at the extremes. Therefore concentrations with mortalities near 50 large sample sizes dominate the fit, while near-0 near-100 delta-method confidence interval and the goodness-of-fit test are computed exactly as in lc50_traditional.

Value

Same as lc50_traditional.

References

Finney, D. J. (1971) Probit Analysis, 3rd edition. Cambridge University Press, Cambridge.

See Also

lc50_traditional, lc50_probit

insectecol documentation built on Oct. 5, 2026, 5:08 p.m.