Package {EDE}

Title:	Extinction Date Estimation from Sighting Records
Version:	0.2.0
Maintainer:	Rodrigo Fonseca Villa <rodrigo03.villa@gmail.com>
Description:	Estimates the historic date of extinction of a species from a time-ordered record of sighting events. Given a table of sighting counts per year, computes extinction date estimators from the sighting-record literature: optimal linear estimation and its Weibull extreme-value persistence test (Roberts & Solow, 2003; Solow, 2005), constant-rate and declining-rate persistence tests (Solow, 1993), a sighting-rate persistence test comparable across records with different observation periods (McInerny, Roberts, Davy & Cribb, 2006), a classical confidence interval on the end of a temporal range (Strauss & Sadler, 1989), a truncation-point extrapolation (Robson & Whitlock, 1964), and a combinatorial persistence test based on inclusion-exclusion over sighting-gap occupancy (Burgman, Grimson & Ferson, 1995). Also implements a nonparametric endpoint test (Solow & Roberts, 2003), a sighting-interval trend index (Jarić & Ebenhard, 2010), and reliability-adjusted inference for uncertain records (Jarić & Roberts, 2014). Every estimator is built on a validated input object and returns a common result class with, where defined, a point estimate, a confidence interval, or a full p-value curve.
Language:	en-US
License:	GPL (≥ 3)
URL:	https://github.com/rodrigosqrt3/EDE
BugReports:	https://github.com/rodrigosqrt3/EDE/issues
Encoding:	UTF-8
RoxygenNote:	7.3.3
Depends:	R (≥ 4.1.0)
Suggests:	testthat (≥ 3.0.0), knitr, rmarkdown, ggplot2
VignetteBuilder:	knitr
Config/testthat/edition:	3
NeedsCompilation:	no
Packaged:	2026-09-19 21:58:53 UTC; rodri
Author:	Rodrigo Fonseca Villa [aut, cre]
Repository:	CRAN
Date/Publication:	2026-09-21 10:10:37 UTC

Burgman, Grimson & Ferson (1995) combinatorial persistence test

Description

Computes the probability that, if sighting events were distributed uniformly at random over the candidate observation window, a run of empty periods at least as long as the largest observed run would occur. Uses an inclusion-exclusion (Stirling-number) argument on the occupancy of time bins by sighting events (equation 4 of the source paper).

Usage

burgman1995(sd, alpha = 0.05, test_year, data_out = FALSE)

Arguments

Value

An ede_estimate object, or (if data_out = TRUE) a data frame with columns time and chance.

References

Burgman, M. A., Grimson, R. C., & Ferson, S. (1995). Inferring threat from scientific collections. Conservation Biology, 9(4), 923-928.

Extinction date estimate

Description

Common S3 result class returned by every estimator in this package.

Format

A list with components:

estimate

Point estimate, or NA if not defined for this method.

lower, upper

Confidence interval bounds, or NA if not defined.

interval_type

Either "two-sided" or "one-sided".

method

Character string identifying the estimator.

alpha

Significance level used to compute the estimate.

Jaric & Ebenhard (2010) sighting-trend index

Description

Tests persistence from the average interval between distinct sighting times, optionally adjusted by the mean trend in consecutive interval lengths. The trend-adjusted calculation implements equations 5-6 of Jaric & Ebenhard (2010); trend = FALSE implements equations 3-4.

Usage

jaric2010(sd, alpha = 0.05, test_year, data_out = FALSE, trend = TRUE)

Arguments

Value

An ede_estimate object, or (if data_out = TRUE) a data frame with columns time and chance. The latter contains index p-values; the column name is retained for compatibility with EDE 0.1.0.

References

Jaric, I., & Ebenhard, T. (2010). A method for inferring extinction based on sighting records that change in frequency over time. Wildlife Biology, 16(3), 267-275.

Reliability-adjusted extinction inference

Description

Modifies the constant-rate Solow model by assigning a reliability in ⁠[0, 1]⁠ to each occupied sighting time. Implements equations 4, 6, and 8-10 of Jaric & Roberts (2014), returning the reliability-adjusted point estimate and upper confidence bound.

Usage

jaric_roberts2014(sd, reliability, alpha = 0.05)

Arguments

Value

An ede_estimate object.

References

Jaric, I., & Roberts, D. L. (2014). Accounting for observation reliability when inferring extinction based on sighting records. Biodiversity and Conservation, 23(11), 2801-2815.

McInerny, Roberts, Davy & Cribb (2006) sighting-rate persistence test

Description

A modification of the Solow (1993) persistence test that conditions on the sighting rate observed up to the last sighting, n / tn, instead of on the length of the whole observation window. This makes the test comparable across records with very different total observation periods: species discovered recently and species discovered long ago, but sighted at the same rate, are inferred extinct after the same length of silence.

Usage

mcinerny2006(sd, alpha = 0.05, test_year, data_out = FALSE)

Arguments

Details

Following the source paper, the first sighting is used to anchor the time origin (t = 0) rather than counted as one of the n sighting events being tested, so the count entering the formula is n - 1, where n is the number of distinct sighting times with a positive count.

Value

An ede_estimate object, or (if data_out = TRUE) a data frame with columns time and chance.

References

McInerny, G. J., Roberts, D. L., Davy, A. J., & Cribb, P. J. (2006). Significance of sighting rate in inferring extinction and threat. Conservation Biology, 20(2), 562-567.

Optimal Linear Estimation of extinction date

Description

Estimates the extinction date from the sighting times with a positive count, using the best linear unbiased estimator (BLUE) of Roberts & Solow (2003) under a Weibull-type record-value model for the spacing of the largest order statistics.

Usage

ole(sd, alpha = 0.05, k = NULL)

Arguments

Value

An ede_estimate object.

References

Roberts, D. L., & Solow, A. R. (2003). Flightless birds: When did the dodo become extinct? Nature, 426(6964), 245. Solow, A. R. (2005). Inferring extinction from a sighting record. Mathematical Biosciences, 195(1), 47-55.

Robson & Whitlock (1964) truncation point estimator

Description

Estimates the extinction date by jackknife bias correction of the most recent sighting. If the two most recent distinct sighting times are t[n-1] and t[n], the estimate is t[n] + (t[n] - t[n-1]).

Usage

robson1964(sd, alpha = 0.05)

Arguments

Value

An ede_estimate object.

References

Robson, D. S., & Whitlock, J. H. (1964). Estimation of a truncation point. Biometrika, 51(1/2), 33-39.

Construct a validated sighting record

Description

Builds the common input object used by every estimator in the package: a time-ordered table of sighting counts, checked for the conditions each estimator in the sighting-record literature assumes (numeric, non-negative, no duplicated times).

Usage

sighting_data(data, time_col = 1L, count_col = 2L)

Arguments

Value

An object of class sighting_data: a data frame with columns time and count, sorted by time.

Solow (1993) constant-rate persistence test

Description

Parametric test of the null hypothesis that a species was still extant at a candidate test year, under a stationary Poisson sighting process.

Usage

solow1993(sd, alpha = 0.05, test_year, data_out = FALSE)

Arguments

Value

An ede_estimate object, or (if data_out = TRUE) a data frame with columns time and chance.

References

Solow, A. R. (1993). Inferring extinction from sighting data. Ecology, 74(3), 962-964.

Solow (1993b) declining-population persistence test

Description

Conditional test of the null hypothesis that a declining species was still extant at a candidate test year, under a non-stationary Poisson process with an exponentially declining rate.

Usage

solow1993b(sd, alpha = 0.05, test_year, data_out = FALSE)

Arguments

Value

An ede_estimate object, or (if data_out = TRUE) a data frame with columns time and chance.

References

Solow, A. R. (1993b). Inferring extinction in a declining population. Journal of Mathematical Biology, 32(1), 79-82.

Solow (2005) Weibull extreme-value persistence test

Description

Tests persistence using the Weibull extreme-value model for the k most recent sighting events. This is the hypothesis-test counterpart of ole(). For a candidate time T, the p-value is equation 16 of Solow (2005). Earlier EDE versions incorrectly described a Fisher-gap calculation as a sighting-effort-weighted method from this paper.

Usage

solow2005(sd, alpha = 0.05, test_year, data_out = FALSE, k = NULL)

Arguments

Value

An ede_estimate object, or (if data_out = TRUE) a data frame with columns time and chance.

References

Solow, A. R. (2005). Inferring extinction from a sighting record. Mathematical Biosciences, 195(1), 47-55.

Solow & Roberts (2003) nonparametric persistence test

Description

Tests the null hypothesis that a species persisted to a candidate time using only the two most recent distinct sighting times. For candidate time T, the p-value is (t[n] - t[n-1]) / (T - t[n-1]).

Usage

solow_roberts2003(sd, alpha = 0.05, test_year, data_out = FALSE)

Arguments

Value

An ede_estimate object, or (if data_out = TRUE) a data frame with columns time and chance. The latter contains p-values; the column name is retained for compatibility with EDE 0.1.0.

References

Solow, A. R., & Roberts, D. L. (2003). A nonparametric test for extinction based on a sighting record. Ecology, 84(5), 1329-1332.

Strauss & Sadler (1989) confidence interval for the end of a range

Description

Unbiased point estimator and classical confidence interval for the true endpoint of a temporal range, derived from the distribution of the sample range under a uniform occurrence model.

Usage

strauss1989(sd, alpha = 0.05)

Arguments

Value

An ede_estimate object containing the unbiased point estimate and a one-sided confidence interval.

References

Strauss, D., & Sadler, P. M. (1989). Classical confidence intervals and Bayesian probability estimates for ends of local taxon ranges. Mathematical Geology, 21(4), 411-427.

Full confidence curve for the Strauss & Sadler (1989) estimator

Description

Same estimator as strauss1989(), evaluated over a grid of alpha values from 0.01 to 1, for plotting the confidence curve instead of a single bound.

Usage

strauss1989_curve(sd)

Arguments

Value

A data frame with columns time and chance (1 - alpha).