lessR (version 2.3.1)

Correlation: Correlation Analysis

Description

Abbreviation: cr, cr.brief

Correlation coefficient with hypothesis test and confidence interval for two variables, or the correlation matrix for a data frame with more than two variables.

Usage

Correlation(x, y, dframe=mydata, ...)
## S3 method for class 'default':
cr(x, y, dframe=mydata, brief=FALSE, \ldots) 
## S3 method for class 'data.frame':
cr(x, ncut=4, digits.d=NULL, \ldots) 
cr.brief(..., brief=TRUE) 
cr(...)

Arguments

x

First variable.

y

Second variable.

dframe

Optional data frame that contains one or both of the variables of interest, default is mydata.

brief

If FALSE, then the sample covariance and number of non-missing and missing observations are displayed.

ncut

When analyzing all the variables in a data frame, specifies the largest number of unique values of variable of a numeric data type for which the variable will be analyzed as a categorical. Set to 0 to turn off.

digits.d

Specifies the number of decimal digits to display in the output.

...

Other parameter values for internally called functions.

Details

Correlation coefficient with hypothesis test, for a null hypothesis of 0, and confidence interval. Also displays the sample covariance. Based on R functions cor, cor.test, cov.

In place of two variables x and y, x can be a complete data frame. All the variables in the data frame must be numeric. If not, then an appropriate error message is displayed. Given such a data frame, the correlation matrix of all the variables in the data frame is displayed.

See Also

cor.test, cov.

Examples

# data
n <- 12
f <- sample(c("Group1","Group2"), size=n, replace=TRUE)
x <- round(rnorm(n=n, mean=50, sd=10), 2)
y <- round(rnorm(n=n, mean=50, sd=10), 2)
z <- round(rnorm(n=n, mean=50, sd=10), 2)
mydata <- data.frame(f,x,y,z)
rm(f); rm(x); rm(y); rm(z)

# correlation and covariance
Correlation(x,y)
# short name
cr(x,y)
# brief form of output
cr.brief(x,y)

# correlation matrix
# first remove the categorical variable f from mydata
mydata <- subset(mydata, select=c(x:z))
# now analyze remaining variables x, y and z
Correlation(mydata)

# analysis with data not from data frame mydata
data(attitude)
Correlation(rating, learning, dframe=attitude)