Skip to contents

The functions the Shiny app uses, available for analyses in R scripts: build a column mapping, prepare the data, fit and compare Models 1-10, predict population trajectories, and read the diagnostics, the interpretation notes and the reproducible code.

Usage

disappr_mapping(...)

disappr_prepare(data, mapping, dup_action = "keep")

disappr_fit(
  x,
  models = MODEL_IDS,
  age_function = "Quadratic",
  family = "gaussian",
  ...
)

disappr_compare(fit)

disappr_predict(fit, model, ages = NULL, by = NULL)

disappr_diagnose(fit)

disappr_interpret(fit)

disappr_code(fit, x, source_label = "your_data.csv")

disappr_simulate(...)

disappr_read(path)

disappr_example(key)

disappr_provenance(fit)

Arguments

...

For disappr_mapping(): column roles (id, age, trait, alr, life, entry, covars, cov_factor, cov_age, group, group2, random, ...) and trait_specific_ages (default TRUE: automatic ALR and AFR are the last and first ages with a trait value; FALSE: of any record). For disappr_fit(): further settings passed to the model suite (random_slope, standardise, zi_str, among, include_invalid, extra). For disappr_simulate(): simulation settings (n_id, seed, sd_type, missingness, form, ...).

data

A data frame with one row per record.

mapping

A column mapping from disappr_mapping().

dup_action

What to do with repeated individual-by-age records: "keep" (default) keeps every row; "mean" collapses rows identical in every mapped column into one (nothing is averaged; the name is kept for compatibility).

x

Prepared data from disappr_prepare().

models

Model identifiers, "M1" to "M10".

age_function

Ageing function: "Linear", "Quadratic", "Cubic", "Logarithmic" or "Asymptotic exponential".

family

Error family, e.g. "gaussian", "poisson", "nbinom2", "binomial".

fit

A fitted comparison from disappr_fit().

model

One model identifier, e.g. "M4".

ages

Ages at which to predict (default: a fine grid over the observed ages).

by

Optional categorical covariate whose levels get separate predictions.

source_label

File name the exported script reads.

path

Path to a CSV or other delimited text file.

key

Name of a bundled example, e.g. "bouwhuis" (see names(disappR:::EXAMPLES)).

Value

disappr_mapping(): a mapping list. disappr_prepare(): a list with data and meta. disappr_fit(): the model comparison (AIC table, coefficients, fits, validity). disappr_compare(): the AIC table. disappr_predict(): predicted population trajectory. disappr_diagnose(): validity, status, dropped rows and notes. disappr_interpret(): interpretation notes. disappr_code(): an R script as a string. disappr_simulate(): a simulated data set.

Examples

if (FALSE) { # \dontrun{
sim <- disappr_simulate(n_id = 150, seed = 1, sd_type = "both")
map <- disappr_mapping(id = "ID", age = "age", trait = "body_mass", life = "lifespan")
x <- disappr_prepare(sim, map)
fit <- disappr_fit(x, models = c("M1", "M2", "M4"))
disappr_compare(fit)
} # }