heck2017 {multinomineq}

Data: Multiattribute Decisions (Heck, Hilbig & Moshagen, 2017)

Description

Choice frequencies with multiattribute decisions across 4 item types (Heck, Hilbig & Moshagen, 2017).

Usage

heck2017

Format

A data frame 4 variables:

B1

Frequency of choosing Option B for Item Type 1

B2

Frequency of choosing Option B for Item Type 2

B3

Frequency of choosing Option B for Item Type 3

B4

Frequency of choosing Option B for Item Type 4

Details

Each participant made 40 choices for each of 4 item types with four cues (with validities .9, .8, .7, and .6). The pattern of cue values of Option A and and B was as follows:

Item Type 1:

A = (-1, 1, 1, -1) vs. B = (-1, -1, -1, -1)

Item Type 2:

A = (1, -1, -1, 1) vs. B = (-1, 1, -1, 1)

Item Type 3:

A = (-1, 1, 1, 1) vs. B = (-1, 1, 1, -1)

Item Type 4:

A = (1, -1, -1, -1) vs. B = (-1, 1, 1, -1)

Raw data are available as heck2017_raw

References

Heck, D. W., Hilbig, B. E., & Moshagen, M. (2017). From information processing to decisions: Formalizing and comparing probabilistic choice models. Cognitive Psychology, 96, 26-40. doi:10.1016/j.cogpsych.2017.05.003

Examples

data(heck2017)
head(heck2017)
n <- rep(40, 4)

# cue validities and values
v <- c(.9, .8, .7, .6)
cueA <- matrix(
  c(
    -1, 1, 1, -1,
    1, -1, -1, 1,
    -1, 1, 1, 1,
    1, -1, -1, -1
  ),
  ncol = 4, byrow = TRUE
)
cueB <- matrix(
  c(
    -1, -1, -1, -1,
    -1, 1, -1, 1,
    -1, 1, 1, -1,
    -1, 1, 1, -1
  ),
  ncol = 4, byrow = TRUE
)

# get predictions
strategies <- c(
  "baseline", "WADDprob", "WADD",
  "TTBprob", "TTB", "EQW", "GUESS"
)
strats <- strategy_multiattribute(cueA, cueB, v, strategies)

# strategy classification with Bayes factor
strategy_postprob(heck2017[1:4, ], n, strats)