fit_sep_2pLL: Fitting separate 2pLL models for (exposure) times

In jcduda/td2pLL: Fitting a time-dose two-parameter log-logistic model to time-dose-response data

Fitting separate 2pLL models for (exposure) times

Description

fit_sep_2pLL is used in the anova pre-test of the time-dose-response analysis pipeline in TDR(). For each (exposure) time, a 2pLL dose-response model is fitted with upper limit 100 and lower limit 0. For each exposure time, an independent ED50 parameter is modeled. However, a common h parameter (or -b in the often used parametrization of the 4pLL model) is shared across the dose-response models of the (exposure) times.

Usage

fit_sep_2pLL(data)

Arguments

data	(data.frame()) Data frame containing dose (numeric), resp (numeric) and time (factor) variables.

Details

The model serves as the full model, denoted by Q_1 in duda et al. (2021). fit_sep_2pLL is a wrapper function that uses the drc::drm() function. At first, the optimization method BFGS is used to fit the model. If this fails, the Nelder-Mead method is used.

Value

An object of class drc.

Note

The LL.2 option from drc::drm() is used, as here, opposed to fit_joint_2pLL(), it seems to lead to more stable fits.

jcduda/td2pLL documentation built on May 14, 2022, 6:48 p.m.