biqq_lower: biqq from lower level model, taking data as arguments

In macartan/biqq: Package for BIQQ analysis as described in Jacobs, Humphreys (2016)

Description

Prior information is provided for Y_u_prior (16 elements) and K_u_prior (4 elements)

Usage

biqq_lower(fit = fit_biqq_lower, XY = c(0, 0, 0, 0), XYK = c(0, 0, 0,
  0, 0, 0, 0, 0), XYK_data = NULL, Y_u_prior = rep(0.5, 16),
  K_u_prior = rep(0.5, 4), pi_alpha = matrix(0.5, 16, 4),
  pi_beta = matrix(0.5, 16, 4), doubly_decisive = FALSE, iter = 1000,
  chains = 2, ...)

Arguments

fit	a fitted biqq_lower model
XY	XY data – 4-vector 00 01 10 11
XYK	XYK data – 12-vector 000 001 010 011...
XYK_data	XYK data provided as a dataframe
Y_u_prior	Dirichlet hyperparameters on 16 u_Y types
K_u_prior	Dirichlet hyperparameters on 4 u_K types
pi_alpha	16 alpha Beta pramaters for pis
doubly_decisive	if TRUE pobative value defaults to clue traces for a and b types (not extreme 0/1)
pi_alpha	16 beta Beta pramaters for pis

Value

A stan object

Examples

print(biqq_lower(XYK = c(0, 1, 1, 0, 1, 0, 0, 1)))
print(biqq_lower(XYK = c(0, 1, 1, 0, 1, 0, 0, 1), doubly_decisive = TRUE))

macartan/biqq documentation built on May 6, 2019, 6:03 p.m.