cdf-ergmTerm-66ced489: Empirical cumulative distribution function (unnormalized) of...

In ergm: Fit, Simulate and Diagnose Exponential-Family Models for Networks

Empirical cumulative distribution function (unnormalized) of the network's dyad values

Description

For every value x in seq⁠(min, max, by)⁠, compute the number of dyads whose value is less than or equal than x. If not given, the range is autodetected based on the values in the LHS network, subject to adjustment via margin and nmax.

Usage

# valued: cdf(min = NULL, max = NULL, by = NULL, margin = 0.1, nmax = 100)

Arguments

min, max, by	range and step size for values at which to compute the CDF
margin, nmax	autodetection of the range and step size; see Details.

Details

If min, max, and/or by is missing, it is automatically computed based on the LHS network's nonzero edge values, specifically their range and resolution (smallest observed difference between distinct values). Minimum and maximum are taken from the minimal and the maximal edge values, and then expanded by margin multiplied by their range, and rounded up to the nearest multiple of the resolution. The step is set to the smallest multiple of the resolution such that the total number of statistics is no more than nmax.

Note

This term is intended to be used in a gof()'s GOF formula, so its coefficient names are specially formatted to be interpreted by gof() rather than for readability.

See Also

\ergmTerm

ergmatmost()

ergmTerm for index of model terms currently visible to the package.

\Sexpr[results=rd,stage=render]{ergm:::.formatTermKeywords("ergmTerm", "cdf", "subsection")}

ergm documentation built on Dec. 22, 2025, 5:10 p.m.