prior_informed | R Documentation |
prior_informed
creates an informed prior distribution based on past
research. The prior can be visualized by the plot
function.
prior_informed(name, parameter = NULL, type = "smd")
name |
name of the prior distribution. There are many options based on prior psychological or medical research. For psychology, the possible options are
For medicine, the possible options are based on Bartoš et al. (2021)
and Bartoš et al. (2023)
who developed empirical prior distributions for the effect size and heterogeneity parameters of the
continuous outcomes (standardized mean differences), dichotomous outcomes (logOR, logRR, and risk differences),
and time to event outcomes (logHR) based on the Cochrane database of systematic reviews.
Use |
parameter |
parameter name describing what prior distribution is supposed to be produced in cases
where the |
type |
prior type describing what prior distribution is supposed to be produced in cases
where the
|
Further details can be found in \insertCiteerp2017estimates;textualRoBMA, \insertCitegronau2017bayesian;textualRoBMA, and \insertCitebartos2021bayesian;textualRoBMA.
prior_informed
returns an object of class 'prior'.
prior()
, prior_informed_medicine_names
# prior distribution representing expected effect sizes in social psychology
# based on prior elicitation with dr. Oosterwijk
p1 <- prior_informed("Oosterwijk")
# the prior distribution can be visualized using the plot function
# (see ?plot.prior for all options)
plot(p1)
# empirical prior distribution for the standardized mean differences from the oral health
# medical subfield based on meta-analytic effect size estimates from the
# Cochrane database of systematic reviews
p2 <- prior_informed("Oral Health", parameter ="effect", type ="smd")
print(p2)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.