# leiv-internal: Probability Density Utilities In leiv: Bivariate Linear Errors-In-Variables Estimation

## Description

`p50` calculates the median of the `leiv` posterior probability density. `probInt` calculates the shortest probability interval of the `leiv` posterior probability density for a given probability level.

## Usage

 ```1 2 3 4 5 6 7``` ```p50(p, interval, subdivisions = 100, rel.tol = .Machine\$double.eps^0.25, abs.tol = rel.tol) probInt(p, interval, level, subdivisions = 100, rel.tol = .Machine\$double.eps^0.25, abs.tol = rel.tol) ```

## Arguments

 `p` a normalized probability density function. `interval` a vector containing the endpoints of the interval to be searched. `level` the probability level requested. `subdivisions` the maximum number of subintervals (see `integrate`). `rel.tol` the relative accuracy requested (see `integrate`). `abs.tol` the absolute accuracy requested (see `integrate`, `optimize` and `uniroot`).

## Details

Internal functions for integrating the posterior density returned by the function `leiv`. These functions are not meant to be called by the user.

## Value

`p50` returns a numeric scalar. `probInt` returns a 2-dimensional numeric vector of interval endpoints.

## Note

`p` must accept a vector of inputs and produce a vector of function evaluations at those points. `rel.tol` cannot be less than `max(50*.Machine\$double.eps, 0.5e-28)` if `abs.tol <= 0`.

`leiv` for general information; `integrate` for control parameters.