estimate_network: Estimate a Network (Deprecated)

In Nestimate: Network Estimation, Bootstrap, and Higher-Order Analysis

Estimate a Network (Deprecated)

Description

This function is deprecated. Use build_network instead.

Usage

estimate_network(
  data,
  method = "relative",
  params = list(),
  scaling = NULL,
  threshold = 0,
  level = NULL,
  ...
)

Arguments

data	Data frame (sequences or per-observation frequencies) or a square symmetric matrix (correlation or covariance).
method	Character. Defaults to "relative" for backward compatibility.
params	Named list. Method-specific parameters passed to the estimator function (e.g. list(gamma = 0.5) for glasso, or list(format = "wide") for transition methods). This is the key composability feature: downstream functions like bootstrap or grid search can store and replay the full params list without knowing method internals. Transition estimators accept tna-style sequence options such as weighted and concat (and the low-level begin_state / end_state, of which start / end are the public form – see those arguments). Column-like entries in params (action, id, id_col, time, session, order, codes, and group) are resolved before format detection and must name existing columns. If the same column role is supplied both directly and through params, the names must agree.
scaling	Character vector or NULL. Post-estimation scaling to apply (in order). Options: "minmax", "max", "rank", "normalize". Can combine: c("rank", "minmax"). Default: NULL (no scaling).
threshold	Numeric. Absolute values below this are set to zero in the result matrix. Default: 0 (no thresholding).
level	Character or NULL. Multilevel decomposition for association methods. One of NULL, "between", "within", "both". Requires id_col. Default: NULL.
...	Additional arguments passed to build_network.

Value

A netobject (see build_network).

See Also

build_network

Examples

data <- data.frame(A = c("x","y","z","x"), B = c("y","x","z","y"))
net <- estimate_network(data, method = "relative")

Nestimate documentation built on July 11, 2026, 1:09 a.m.