Reanalyses of data from Horne, Powell, Hummel & Holyoak (2015)
git clone
Log | Files | Refs | README | LICENSE

commit e906e43be9f64d6654248590b62f1c13515247da
parent ddc983158d7b79042ea81d6ea68070e56304050a
Author: eamoncaddigan <>
Date:   Sun, 30 Aug 2015 14:31:28 -0400


Mantivax-attitudes.Rmd | 8+++++---
1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/antivax-attitudes.Rmd b/antivax-attitudes.Rmd @@ -88,6 +88,8 @@ print(p2) The above figure shows pre- and post-intervention responses to each question. Each line represents represents a single participant's responses before and after the intervention to a single question. Lines are colored by the magnitude of the change in response; blue lines indicate more agreement (toward a more pro-vaccine stance) and red lines indicate less agreement (a more anti-vaccine stance). +The JAGS code for the model is shown below. It's essentially a Bayesian analog to the three-factor ANOVA, using a thresholded cummulative normal distribution as a link function. Such models geenrally do a good job of capturing the ordinal responses obtained in surveys. The thresholds and variance of the link function are set separately for each question. The mean of the normal distribution is determined by a linear function of the question, the interval (pre-test vs. post-test) and intervention for each response, and all interactions between these factors. + ```{r, echo=FALSE} # Get the data ready for JAGS x1 <- as.numeric(as.factor(questionnaireData[["question"]])) @@ -158,12 +160,12 @@ modelString <- " a2[j2] ~ dnorm(0.0, 1/(NyLvl)^2) } - # Constant sigma for beta3 (for now) + # Constant sigma for beta3 for (j3 in 1:Nx3Lvl) { a3[j3] ~ dnorm(0.0, 1/(NyLvl)^2) } - # Interaction terms also has homogenous variance (for now) + # Interaction terms also have homogenous variance for (j1 in 1:Nx1Lvl) { for (j2 in 1:Nx2Lvl) { a1a2[j1, j2] ~ dnorm(0.0, 1/(NyLvl)^2) @@ -234,7 +236,7 @@ modelString <- " } } " # close quote for modelString -print(modelString) +cat(modelString) # Write out modelString to a text file writeLines(modelString , con="TEMPmodel.txt")