startlba {glba}R Documentation

Specify and fit lba models.

Description

Specification of lba models with explanatory variables on the parameters. Models are fitted using full information maximum likelihood.

Usage

startlba(rt, resp, ...)

Arguments

rt

A vector of response times.

resp

A vector of (binary) responses.

...

Not currently used.

Details

The startlba function returns a named vector with starting values for the (intercepts) of the parameter models. Currently defined as: the standard deviation of the RTs is used as the standard deviation of the drift rate; the drift rate for the correct responses is initialized as the mean accuracy; the non-decision parameter is set to half the minimum of the response times; the start point parameter is set to drift*(qrt2-nond) where drift is the drift rate, qrt2 the second quartile of the RT distribution, and nond is the non-decision time; the bound is set to drift*(qrt4-nond) where qrt4 is the fourth value of quartiles of the RT distribution.

Value

The startlba function returns a named vector with starting values for the (intercepts) of the parameter models.

Author(s)

Ingmar Visser

Examples

data(bh08)
# remove extreme RTs
bh08 <- bh08[bh08$rt>.180&bh08$rt<2,]
startlba(bh08$rt,bh08$acc)

[Package glba version 0.3 Index]