aides (version 1.3.3)

TestDiscordance: Test assumption of discordance between theoretical and observed study scale.

Description

TestDiscordance() is a function for discordance in rank of study size analysis.

Usage

TestDiscordance(
  n,
  se,
  data,
  study = NULL,
  method = "prop",
  coval = 0.2,
  tot = 0,
  plot = FALSE,
  color = "lightpink"
)

Value

TestDiscordance() returns a summary of result of discordance in rank of study size.

Arguments

n

NUMERIC values for sample size (n) of each study.

se

NUMERIC values for standard error of each study.

data

DATA FRAME consists of three columns for study label, sample size, and standard error.

study

CHARACTER for study label of each study.

method

CHARACTER of "rank" or "prop" for indicating which method should be used.

coval

NUMERIC value of cutoff point ranged from 0 to 1 in order to detecting of discordance between theoretical and observed study scale.

tot

NUMERIC value of tolerate discordance in ranks between theoretical and observed study scale. The numeric value should be ranged from 0 to 1 / 4 number of studies.

plot

LOGIC value for indicating whether to illustrate discordance plot.

color

CHARACTER of a color name for emphasizing the studies with discordance in ranks between theoretical and observed study size.

Author

Enoch Kang

References

Howell, D. C. (2012). Statistical methods for psychology (7th ed.). Belmont, CA: Thomson. Available online: https://labs.la.utexas.edu/gilden/files/2016/05/Statistics-Text.pdf.

See Also

TestDisparity

Examples

## Not run:
# 1. Import a dataset of study by Fleiss (1993)
library(meta)
data("Fleiss1993bin")
data <- Fleiss1993bin

# 2. Calculate total sample size and standard error of each study
data$n  <- data$n.asp + data$n.plac
data$se <- sqrt((1 / data$d.asp) - (1 / data$n.asp) + (1 / data$d.plac) - (1 / data$n.plac))

# 3. Test discordance in ranks between theoretical and observed study size.
output <- TestDiscordance(n = n, se = se, study = study, data = data)

# 4. Illustrate discordance plot
TestDiscordance(n = n, se = se, study = study, data = data, plot = TRUE)

## End(Not run)