compute_marg_PR_nested_reg: compute positive rates for nested model with subclass mixing...
In oslerinhealth/baker: Bayesian Analysis Kit for Etiology Research

View source: R/compute_functionals_of_model.R

The array version of this function (compute_marg_PR_nested_reg_array) is used in plot_etiology_regression

1	compute_marg_PR_nested_reg(ThetaBS, PsiBS, pEti_mat, subwt_mat, case, template)

`ThetaBS`	True positive rates for `JBrS` measures (rows) among `K` subclasses (columns)
`PsiBS`	False positive rates; dimension same as above
`pEti_mat`	a matrix of etiology pies for `N` subjects (rows) and `Jcause` causes (columns) rows sum to ones.
`subwt_mat`	a matrix of subclass weights for cases and controls. `N` by `K`. Rows sum to ones.
`case`	a N-vector of `1`s (cases) and `0`s (controls)
`template`	a binary matrix with `Jcause+1` rows (`Jcause` classes of cases and `1` class of controls) and `JBrS` columns for the Bronze-standard measurement (say, pick one type/slice). The ones in each row indicate the measurements that will show up more frequently in cases given the cause.

a matrix of values between 0 and 1 (need not to have row sums of ones); of dimension (number of subjects, dimension of the bronze-standard measurement slice).

oslerinhealth/baker documentation built on May 22, 2021, 12:05 p.m.