preorder: Ad-hoc methods for determining the order of variables

In factorstochvol: Bayesian Estimation of (Sparse) Latent Factor Stochastic Volatility Models

Ad-hoc methods for determining the order of variables

Description

In factor SV models, the ordering of variables is often chosen through a preliminary static factor analysis. These methods are implemented in preorder. After a maximum likelihood factor model fit to the data, factor loadings are ordered as follows: The variable with the highest loading on factor 1 is placed first, the variable with the highest loading on factor 2 second (unless this variable is already placed first, in which case the variable with the second highest loading is taken).

Usage

preorder(
  dat,
  factors = ledermann(ncol(dat)),
  type = "fixed",
  transload = identity
)

Arguments

dat	Matrix containing the data, with n rows (points in time) and m columns (component series).
factors	Number of factors to be used, defaults to the Ledermann bound.
type	Can be "fixed" or "dynamic". The option "fixed" means that that a factors-factor model is fit once and the entire ordering is determined according to this fit (the default). The option "dynamic" means that the model is re-fit factors times with the number of factors going from 1 to factors and in each round the correspondingly largest loading is chosen.
transload	Function for transforming the estimated factor loadings before ordering. Defaults to the identity function.

Value

A vector of length m with the ordering found.

See Also

ledermann

factorstochvol documentation built on Nov. 24, 2023, 5:08 p.m.