relevance_f.study: Creates a table showing the standardized mean difference...

In StefanThoma/ReplicationRelevance: Calculates Relevance for Many Labs Replication Projects

Creates a table showing the standardized mean difference obtained by each of the 36 universities that tried to replicate a specific study. This function relies on the relevance package by Stahel. The function is called by the relevance_table.study function

Description

Creates a table showing the standardized mean difference obtained by each of the 36 universities that tried to replicate a specific study. This function relies on the relevance package by Stahel. The function is called by the relevance_table.study function

Usage

relevance_f.study(
  dat,
  treatment_var,
  response_var,
  orig,
  var.of.interest,
  family = "gaussian",
  relevance.threshold = 0.1,
  variables
)

Arguments

dat	data.frame containing the full data from the manyLabs experiments
treatment_var	Name of the column in dat that contains the treatment assignments.
response_var	Name of the column in dat that contains the response.
orig	Statistic of original study
family	distribution family
relevance.threshold	is the threshold specified
variables	this is the slot variables forwarded from the calling function This is needed if we would like to compute power based on intercept and effect of the binomial regression, not only on the effect. At the moment this variable is not used.

Value

output data.frame with one row for each of the 36 replication attempts. Each row of output contains the sample sizes and means for both treatment groups as well as the the effect estimate and power estimate.

Author(s)

Stefan Thoma

StefanThoma/ReplicationRelevance documentation built on Feb. 6, 2023, 4:03 a.m.