Stan.nma.fit: Assess NMA model fit

In augustinewigle/StanNet: StanNet: A Variant of BUGSnet Using Stan

Description

Computes the Deviance Information Criteria, effective number of parameters, and posterior mean of the residual deviance for a given model, and produces a rainbow plot (called a leverage plot in the NICE Technical Support Document 2). Points outside of the purple curve can be said to contribute to the model's poor fit.

Usage

Stan.nma.fit(nma, plot.pD = TRUE, plot.DIC = TRUE, plot.Dres = TRUE, ...)

Arguments

nma	A BUGSnetRun object produced by running nma.run() or convertToBUGSnetRun()
plot.pD	Whether to include the effective number of parameters on the plot, default is TRUE
plot.DIC	Whether to include the DIC on the plot, default is TRUE
plot.Dres	Whether to include the posterior mean of the residual deviance on the plot, default is TRUE
...	Graphical arguments such as main= to be passed to plot()

Value

DIC - The Deviance Information Criteria leverage - A vector of leverages calculated for each data point (one per arm per study) w - A vector of each data point's contribution to the posterior mean deviance pmdev - A vector of the posterior mean residual deviance for each data point Dres - The posterior mean of the residual deviance pD - The effective number of parameters, calculated as the sum of leverage

augustinewigle/StanNet documentation built on July 21, 2020, 12:13 a.m.