View source: R/design_effect.R
design_effect | R Documentation |
This function calculates the design effect of the supplied weights. A design effect is an estimate of the variance inflation caused by the design of a study. If a vector of weights is provided without any outcome, this function implements the estimator in Kish (1992), which assumes no correlation between provided weights and an outcome of interest. If an outcome of interest is provided, this function implements the estimator in Spencer (2000), which accounts for correlation between outcomes and weights. For a broader discussion of design effects in weighted surveys, see Spencer (2000).
design_effect(weights, outcome = NULL)
weights |
The weights for which a design effect is desired |
outcome |
A vector outcome of interest. |
A numeric design effect for the weights
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.