consistency: MSC network meta-analysis models

Description Usage Arguments Details Value Functions See Also Examples

View source: R/consistency.R

Description

MSC network meta-analysis models

Usage

1
2
3
consistency(x, mods = NULL, ...)

inconsistency(x, mods = NULL, ...)

Arguments

x

A set of aggregated performance score data, as computed with the aggregate_performance function.

mods

Which moderators should be included in the model? These can be any of the same moderators included in get_bs_samples, all others will be ignored.

...

Any other arguments will be passed directly to rma.mv

Details

The consistency and inconsistency models are those found in Law et al 2016:

Specifically, we fit one of two models using "Jackson's Model", as described in the paper, which differ only in their random effects:

consistency

First item

random contrast within study

inconsistency

Second item

random contrast within study, and random contrast within design

Value

The results of an rma.mv multivariate/multilevel Linear (mixed-effects) model (class "rma.mv"), with the following additional components, which can be passed along to other functions: #'

reference

name of reference score

scores

vector of scores analysed

model

If consistency was used, "consistency", else "inconsistency"

performance

Label of performance, as used in previous functions

Functions

See Also

Law, M.; Jackson, D.; Turner, R.; Rhodes, K. & Viechtbauer, W. Two new methods to fit models for network meta-analysis with random inconsistency effects BMC Medical Research Methodology, 2016, 16, 87.

Examples

1
2
3
4
5
6
7
8
9
dat <- msc_sample_data()
bssamp <- get_bs_samples(dat, id, study, outcome, n.samples = 10, 
                  scores = c("a", "b", "c", "d", "e", "f"), 
                  moderators = c("age", "female", "x1"))
perf <- compute_performance(bssamp, fn = calibration_slope, lbl = "CS")
agg <- aggregate_performance(perf)
consistency(agg)
agg.c <- aggregate_performance(perf, "c")
consistency(agg.c)

srhaile/mscpredmodel documentation built on Sept. 13, 2019, 3:44 p.m.