se.slope {vcmeta}

Computes a slope and standard error

Description

This function can be used to compute a slope and its standard error for a simple linear regression model (random-x model) using the estimated Pearson correlation and the estimated standard deviations of the response and predictor variables. This function is useful in a meta-analysis of slopes of a simple linear regression model where some studies report the Pearson correlation but not the slope.

Usage

se.slope(cor, sdy, sdx, n)

Arguments

cor

estimated Pearson correlation

sdy

estimated standard deviation of the response variable

sdx

estimated standard deviation of the predictor variable

n

sample size

Value

Returns a one-row matrix:

• Estimate - estimated slope

• SE - standard error

References

Snedecor GW, Cochran WG (1980). Statistical methods, 7th edition. ISU University Pres, Ames, Iowa.

Examples

se.slope(.392, 4.54, 2.89, 60)

# Should return: 
#          Estimate        SE
# Slope:  0.6158062 0.1897647