ML: Maximum likelihood estimation for a random effects...

In nshi-stat/netiim3: Improved Inference Methods for Network Meta-Analysis

Description

Maximum likelihood estimation for a random effects model for multivariate meta-analysis.

Usage

ML(y, S, maxitr = 200)

Arguments

y	N x p matrix of outcome variables.
S	Series of within-study covariance matrices of the outcome variables. A matrix or data frame with N rows and p(p+1)/2 columns.
maxitr	The maximum iteration number of the Newton-Raphson algorithm.

Details

The correlation matrix of the between-studies covariance matrix is set to compound symmetry with the correlation coefficient 0.50. It can be changed by modifying the source code. Please see Noma et al. (2017) for details.

Value

Coefficients	The maximum likeliood estimate of the grand mean vector and its standard error (SE) with the 95% confidence interval.
Between-studies_SD	The maximum likeliood estimate of the between-studies standard deviance (SD).
Between-studies_COR	The correlation coefficient of the between-studies correlation matrix.
Loglikelihood	The loglikelihood at the converged point.

References

Jackson, D., Riley, R., White, I. R. (2011). Multivariate meta-analysis: Potential and promise. Statistics in Medicine. 30: 2481-2498.

Noma, H., Nagashima, K., Maruo, K., Gosho, M., Furukawa, T. A. (2017). Bartlett-type corrections and bootstrap adjustments of likelihood-based inference methods for network meta-analysis. ISM Research Memorandum 1205.

See Also

Other ML: REML

Examples

# dae <- data.aug.edit(smoking)
# y <- dae$y
# S <- dae$S

# ML(y, S)

nshi-stat/netiim3 documentation built on May 6, 2019, 10:51 p.m.