binary_belief_trajectory: Compute a binary belief trajectory from per-marker likelihood...

In mispitools: Missing Person Identification Tools

Compute a binary belief trajectory from per-marker likelihood ratios

Description

For the two-hypothesis forensic case, computes the trajectory of P(H_1) as markers are added sequentially.

Usage

binary_belief_trajectory(per_marker_lrs, prior_odds = 1)

Arguments

per_marker_lrs	Named numeric vector. Per-marker likelihood ratios \mathrm{LR}_k = P(\mathrm{profile}_k | H_1) / P(\mathrm{profile}_k | H_2).
prior_odds	Numeric scalar. Prior odds for H_1 vs H_2 (default 1, i.e., equal prior).

Value

A data frame with one row per step (including the prior at step 0) and the following columns:

step

Integer, 0 for prior, 1 to K for markers.

marker

Character, "Prior" or the marker name.

log10_lr

Per-step \log_{10} \mathrm{LR}_k.

cum_log10_lr

Cumulative \log_{10} \mathrm{LR} up to and including step step.

posterior_h1

P(H_1) at step step.

posterior_h2

P(H_2) at step step.

References

Marsico, F. L. & Egeland, T. (in preparation). Belief dynamics during the investigative process.

See Also

belief_trajectory for the general multi-hypothesis case, concentration_index for fragility diagnostics.

Examples

lrs <- c(D3S1358 = 5.2, TH01 = 1.8, D21S11 = 12.0, D18S51 = 3.1)
binary_belief_trajectory(lrs)

mispitools documentation built on Aug. 26, 2026, 1:08 a.m.