Weather Task with Priming and Precise and Imprecise Probabilities

In this study participants were asked to judge how likely Sunday is to be the hottest day of the week.

Usage

data("WeatherTask", package = "betareg")

Format

A data frame with 345 observations on the following 3 variables.

priming

a factor with levels two-fold (case prime) and seven-fold (class prime).

eliciting

a factor with levels precise and imprecise (lower and upper limit).

agreement

a numeric vector, probability indicated by participants or the average between minimum and maximum probability indicated.

Details

All participants in the study were either first- or second-year undergraduate students in psychology, none of whom had a strong background in probability or were familiar with imprecise probability theories.

For priming the questions were:

two-fold

[What is the probability that] the temperature at Canberra airport on Sunday will be higher than every other day next week?

seven-fold

[What is the probability that] the highest temperature of the week at Canberra airport will occur on Sunday?

For eliciting the instructions were if

precise

to assign a probability estimate,

imprecise

to assign a lower and upper probability estimate.

Source

Taken from Smithson et al. (2011) supplements.

References

Smithson M, Merkle EC, Verkuilen J (2011). Beta Regression Finite Mixture Models of Polarization and Priming. Journal of Educational and Behavioral Statistics, 36(6), 804–831. doi:10.3102/1076998610396893

Smithson M, Segale C (2009). Partition Priming in Judgments of Imprecise Probabilities. Journal of Statistical Theory and Practice, 3(1), 169–181.

Examples

data("WeatherTask", package = "betareg")
library("flexmix")
wt_betamix <- betamix(agreement ~ 1, data = WeatherTask, k = 2,
  extra_components = extraComponent(type = "betareg", coef =
    list(mean = 0, precision = 2)),
  FLXconcomitant = FLXPmultinom(~ priming + eliciting))