Simulate one transient or abortive detection pattern — mbmm_simulate_abortive_pattern • mbmm

The four patterns reflect the reduced manuscript simulation:

noise_like: no intended signal above the LOD;
single_blip: one intended detectable visit;
two_point: two intended near-LOD detections;
fast_rise_drop: one higher isolated peak with neighboring visits remaining near background.

Usage

mbmm_simulate_abortive_pattern(
  times,
  lod = 100,
  sigma_obs = 0.5,
  subtype = NULL,
  subtype_prob = c(noise_like = 0.2, single_blip = 0.35, two_point = 0.3, fast_rise_drop
    = 0.15),
  max_log10_above_lod = 1.5,
  target_detect_prob = 0.9,
  seed = NULL
)

Arguments

times: Observation times.
lod: Natural-scale assay limit of detection.
sigma_obs: Observation-noise SD on the log10 scale.
subtype: Optional fixed subtype. When NULL, one is sampled.
subtype_prob: Named subtype probabilities.
max_log10_above_lod: Maximum signal above log10(LOD).
target_detect_prob: Probability used to protect intended detections from being lost after observation noise.
seed: Optional random seed.

Value

A data frame containing natural-scale observations, censoring, latent log10 signal, and subtype.