CronbachAlpha {DescTools} | R Documentation |
Cronbach's Coefficient Alpha
Description
Cronbach's alpha is a measure of internal consistency and often used for validating psychometric tests. It determines the internal consistency or average correlation of items in a survey instrument to gauge its reliability. This reduces to Kuder-Richardson formula 20 (KR-20) when the columns of the data matrix are dichotomous.
Usage
CronbachAlpha(x, conf.level = NA, cond = FALSE, na.rm = FALSE)
Arguments
x |
|
conf.level |
confidence level of the interval. If set to |
cond |
logical. If set to |
na.rm |
logical, indicating whether |
Value
Either a numeric value or
a named vector of 3 columns if confidence levels are required (estimate, lower and upper ci) or
a list containing the following components, if the argument cond
is set to TRUE
:
unconditional |
Cronbach's Alpha, either the single value only or with confidence intervals |
condCronbachAlpha |
The alpha that would be realized if the item were excluded |
Author(s)
Andri Signorell <andri@signorell.net>, based on code of Harold C. Doran
References
Cohen, J. (1960), A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20, 37-46.
See Also
Examples
set.seed(1234)
tmp <- data.frame(
item1=sample(c(0,1), 20, replace=TRUE),
item2=sample(c(0,1), 20, replace=TRUE),
item3=sample(c(0,1), 20, replace=TRUE),
item4=sample(c(0,1), 20, replace=TRUE),
item5=sample(c(0,1), 20, replace=TRUE)
)
CronbachAlpha(tmp[,1:4], cond=FALSE, conf.level=0.95)
CronbachAlpha(tmp[,1:4], cond=TRUE, conf.level=0.95)
CronbachAlpha(tmp[,1:4], cond=FALSE)
CronbachAlpha(tmp[,1:2], cond=TRUE, conf.level=0.95)
## Not run:
# Calculate bootstrap confidence intervals for CronbachAlpha
library(boot)
cronbach.boot <- function(data,x) {CronbachAlpha(data[x,])[[3]]}
res <- boot(datafile, cronbach.boot, 1000)
quantile(res$t, c(0.025,0.975)) # two-sided bootstrapped confidence interval of Cronbach's alpha
boot.ci(res, type="bca") # adjusted bootstrap percentile (BCa) confidence interval (better)
## End(Not run)