How much do you like Coke over Pepsi?
How much do you like Pepsi?
University of Padova (IT)
How much do you like Coke over Pepsi?
How much do you like Pepsi?
The IAT and SC-IAT effects (i.e., the difference between the associative conditions) are expressed by using the so-called D-score, computed as:
\[\text{D-score} = \frac{M_{conditionA} - M_{conditionB}}{sd_{pooled}}\]
The steps that have to be undertaken to clean and prepare the data set for the computation make it an error prone procedure, raising replicability issues.
implicitMeasures
It’s on CRAN!
install.packages("implicitMeasures") # Install
library("implicitMeasures") # upload
…and there’s a data set you can play with:
data(raw_data)
Function | Description |
---|---|
clean_iat() |
Clean IAT data |
computeD() |
Compute IAT D-score |
IATrel() |
Compute IAT realibility |
multi_dscore() |
Compute & Plot multiple IAT D-scores |
Function | Description |
---|---|
clean_sciat() |
Clean SC-IAT data |
Dsciat() |
Compute SC-IAT D-score |
multi_dsciat() |
Plot D-scores from two SC-IATs |
The objects obtained from functions computeD()
or Dsciat()
can be passed to the following functions:
Function | Description |
---|---|
descript_d() |
Descriptive table of the D-scores (even in LaTeX format!) |
d_distr() |
Plot of the results at the sample level |
d_plot() |
Plot of the results at the individual level |