countsTab: Counts sequences of length d+1 in a sample

In hdMTD: Inference for High-Dimensional Mixture Transition Distribution Models

Counts sequences of length d+1 in a sample

Description

Creates a tibble containing all unique sequences of length d+1 found in the sample, along with their absolute frequencies.

Usage

countsTab(X, d)

Arguments

X	A numeric vector, a single-column data frame, or a list with a sample from a Markov chain. The first element must be the most recent observation.
d	A positive integer specifying the number of elements in each sequence, which will be d+1. Typically, d represents the chain order or serves as an upper limit for it.

Details

The function generates a tibble with d+2 columns. In the first d+1 columns, each row displays a unique sequence of size d+1 observed in the sample. The last column, called Nxa, contains the number of times each of these sequences appeared in the sample.

The number of rows in the output varies between 1 and |A|^{d+1}, where |A| is the number of unique states in X, since it depends on the number of unique sequences that appear in the sample.

Value

A tibble with all observed sequences of length d+1 and their absolute frequencies.

Examples

countsTab(c(1,2,2,1,2,1,1,2,1,2), 3)

# Using test data.
countsTab(testChains[, 1], 2)

hdMTD documentation built on June 8, 2025, 10:30 a.m.