nlaad: Non-linearity Across All Doses

In drsmooth: Dose-Response Modeling with Smoothing Splines

Description

This function determines whether a non-linear spline model of the dose-response relationship differs significantly from a linear model across all doses.

Usage

nlaad(dosecolumn = "", targetcolumn = "", data = NA)

Arguments

dosecolumn	Name of dose column in dataframe.
targetcolumn	Name of response column in dataframe.
data	Input dataframe.

Details

The non-linear spline model (output "Model 2") is compared to the linear model (output "Model 1") using an anova F-test. If the spline model fits the data signficantly better, the F will be large and the associated p value will be significant.

The nlaad, nlbcd, and lbcd functions are currently only intended for use on continuous outcome data.

Value

The analysis of variance table comparing the non-linear spline model with the linear model to assess non-linearity across all doses.

Examples

# Prints the F test of the difference between the spline model (output "Model 2")
# and the linear model (output "Model 1") as a test of nonlinearity
# across all doses:
nlaad("dose", "MF_Log", data=DRdata)

drsmooth documentation built on May 1, 2019, 10:28 p.m.