nodesplit.network.data: Assessing consistency using node-splitting model
In MikeJSeo/network-meta: Bayesian Network Meta-Analysis

Description Usage Arguments References

This function is used to make node-splitting inconsistency model. The structure is similar to the function network.data

1 2	nodesplit.network.data(Outcomes, Study, Treat, N = NULL, SE = NULL, response = NULL, type = "random")

`Outcomes`	Arm-level outcomes. If it is a multinomial response, the matrix would be arms (row) by multinomial categories (column). If it is binomial or normal, it would be a vector.
`Study`	A vector of study indicator for each arm
`Treat`	A vector of treatment indicator for each arm. Treatments should have positive integer values starting from 1 to total number of treatments. In a study, lowest number is taken as the baseline treatment. Also, in each study first arm should be the baseline treatment and lower number treatment arms should come before the higher ones. (i.e. treatment arm should go 1, 2, 4 and not 1, 4, 2). See example data for clarification.
`N`	A vector of total number of observations in each arm. Used for binomial and multinomial responses.
`SE`	A vector of standard error for each arm. Used only for normal response.
`response`	Specification of the outcomes type. Must specify one of the following: "normal", "binomial", or "multinomial".
`type`	Type of model fitted: either "random" for random effects model or "fixed" for fixed effects model. Default is "random".

S. Dias, N.J. Welton, D.M. Caldwellb, A.E. Ades (2010), Checking consistency in mixed treatment, Statistics in Medicine 29(7-8, Sp. Iss. SI): 932-944. [https://doi.org/10.1002/sim.3767]

MikeJSeo/network-meta documentation built on May 3, 2019, 4:31 p.m.