RBF_Ftest: Calculate a Replication Bayes Factor for F-Tests.

In neurotroph/ReplicationBF: Calculating Replication Bayes Factors for Different Scenarios

Description

RBF_Ftest calculates a Replication Bayes Factor for F-Tests from balanced fixed effect, between subject ANOVA designs (Harms, 2018).

Usage

RBF_Ftest(F.orig, df.orig, N.orig, F.rep, df.rep, N.rep, M = 1e+05,
  store.samples = FALSE)

Arguments

F.orig	F-statistic from the original study.
df.orig	Numeric vector containing the degrees of freedom for the F-test from the original study.
N.orig	Total number of observations in the original study.
F.rep	F-statistic from the replication study.
df.rep	Numeric vector containing the degrees of freedom for the F-Test from the replication study.
N.rep	Total number of observations in the replication study.
M	Number of draws from the posterior distribution to approximate the marginal likelihood.
store.samples	If TRUE, the samples of the original's posterior distribution are stored in the return object.

Details

The Replication Bayes Factor is a marginal likelihood ratio between two positions (see Verhagen & Wagenmakers, 2014):

• H0: The position of a skeptic, who does not place confidence in the findings of the original study and assumes θ \approx 0.

• Hr: The position of a proponent, who expects the original study to be a faithful estimation of the effect size and for which the replication offers additional evidence. This is formulated as θ \approx θ_{orig} with θ_{orig} being the effect size estimate from the original study.

The Bayes factor is estimated through Importance Sampling (Gamerman & Lopes, 2006). The importance density is half-normal with parameters estimated from the posterior distribution. Posterior distribution is sampled using Metropolis-Hastings from MCMCpack::MCMCmetrop1R.

Value

An ReplicationBF object containing the value of the Replication Bayes Factor in bayesFactor.

References

• \insertRef

  Verhagen2014ReplicationBF

• \insertRef

  Harms2016ReplicationBF

Examples

## Not run: 
RBF_Ftest(27.0, c(3, 48), 52, 3.2, c(3, 33), 37)

## End(Not run)

neurotroph/ReplicationBF documentation built on May 28, 2019, 3:39 p.m.