poolcost_t: Visualize Total Costs for Pooling Design as a Function of...

In vandomed/pooling: Fit Poolwise Regression Models

Description

Useful for determining whether pooling is a good idea, what pool size minimizes costs, and how many assays are needed for a target power.

Usage

poolcost_t(g = 1:10, d = NULL, mu1 = NULL, mu2 = NULL,
  sigsq = NULL, sigsq1 = sigsq, sigsq2 = sigsq, sigsq_p = 0,
  sigsq_m = 0, multiplicative = FALSE, alpha = 0.05, beta = 0.2,
  assay_cost = 100, other_costs = 0, labels = TRUE, ylim = NULL)

Arguments

g	Numeric vector of pool sizes to include.
d	Numeric value specifying true difference in group means.
mu1, mu2	Numeric value specifying group means. Required if multiplicative = TRUE.
sigsq	Numeric value specifying the variance of observations.
sigsq1, sigsq2	Numeric value specifying the variance of observations for each group.
sigsq_p	Numeric value specifying the variance of processing errors.
sigsq_m	Numeric value specifying the variance of measurement errors.
multiplicative	Logical value for whether to assume multiplicative rather than additive errors.
alpha	Numeric value specifying type-1 error rate.
beta	Numeric value specifying type-2 error rate.
assay_cost	Numeric value specifying cost of each assay.
other_costs	Numeric value specifying other per-subject costs.
labels	Logical value.
ylim	Numeric vector.

Value

Plot of total costs vs. pool size generated by ggplot.

Examples

# Plot total study costs vs. pool size for d = 0.25, sigsq = 1, and costs of
# $100 per assay and $0 in other per-subject costs.
poolcost_t(d = 0.25, sigsq = 1)

# Repeat but with additive processing error and $10 in per-subject costs.
poolcost_t(d = 0.25, sigsq = 1, sigsq_p = 0.5, other_costs = 10)

vandomed/pooling documentation built on Feb. 22, 2020, 8:58 p.m.