simsem (version 0.2-8)

miPoolVector: Function to pool imputed results that saved in a matrix format

Description

The function takes parameter estimates and standard errors of each imputed result and returns pooled parameter estimates and standard errors.

Usage

miPoolVector(MI.param, MI.se, imps)

Arguments

MI.param

A matrix of parameter estimates that the row represents parameter estimates from different imputations and the column represents parameter estimates of different target parameters.

MI.se

A matrix of standard errors that the row represents standard errors from different imputations and the column represents the standard errors of different target parameters.

imps

The number of imputations

Value

• MIpool returns a list with pooled estimates, standard errors, fit indices and fraction missing information
• Estimates
  Pooled parameter estimates.
• SE
  Pooled standard errors.
• FMI.1
  Fraction of missing information for each parameter.
• FMI.2
  Fraction of missing information for each parameter.

Details

Parameters and standard errors are combined using Rubin's Rules (Rubin, 1987).

References

Rubin, D.B. (1987) Multiple Imputation for Nonresponse in Surveys. J. Wiley & Sons, New York.

See Also

• runMIfor imputing missing values by multiple imputation and analyzing the imputed datasets.
• miPoolfor combining results in theSimModelOutformat.

Examples

param <- matrix(c(0.7, 0.1, 0.5,
					0.75, 0.12, 0.54,
					0.66, 0.11, 0.56,
					0.74, 0.09, 0.55), nrow=4, byrow=TRUE)
SE <- matrix(c(0.1, 0.01, 0.05,
				0.11, 0.023, 0.055,
				0.10, 0.005, 0.04,
				0.14, 0.012, 0.039), nrow=4, byrow=TRUE)
nimps <- 4
miPoolVector(param, SE, nimps)