In tmcd82070/Rdistance: Distance-Sampling Analyses for Density and Abundance Estimation

This is where you are:

Need to test:

1. [DONE]presence of covariates (point and line)
2. [DONE] Testing methods for Point surveys (start with x_test_points_noCovars.R maybe)
3. Test methods for all the options in controls$ esp $requireunits
4. Test methods for by.site = T in abundEstim
5. [DELAY] Test methods that compare to past values, not just for presence of output
6. [DONE] Test file for different units to check equality. e.g., set w.hi = "100 m" then w.hi = 100 m in ft and check that answers are same.

Need To Do:

1. Remove requirement of no missing values from abundEstim. Missing distances in detection data frame are okay. But, we stop when missing distances show up in abundEstim.
2. Include one numerical integration routine. Maybe use R::integrate(). Call this routine from integration.constant() and ESW(). Upgrade to Simpson's alternate composite formula. https://en.wikipedia.org/wiki/Simpson's_rule

(dx/48) * (17f(x_0) + 59f(x_1) + 43f(x_2) + 49f(x_3) + 48f(x_4) + 48f(x_5) + ... + 48f(x_n-4) + 49f(x_n-3) + 43f(x_n-2) + 59f(x_n-1) + 17f(x_n))

1. In addition to the above, you know the integral of several likelihoods. Integral of halfnormal is 0.5sigmasqrt(pi). I think you can work out integral of negative exponential. Use numerical integration for the others.
2. Consolidate the help using @inherit methods

tmcd82070/Rdistance documentation built on April 10, 2024, 10:20 p.m.