dlg_bivariate: Bivariate density estimation
In hotneim/lg: Locally Gaussian Distributions: Estimation and Methods

Description Usage Arguments Details Value Examples

dlg_bivariate returns the locally Gaussian density estimate of a bivariate distribution on a given grid.

dlg_bivariate(
  x,
  eval_points = NA,
  grid_size = 15,
  bw = c(1, 1),
  est_method = "1par",
  tol = .Machine$double.eps^0.25/10^4,
  run_checks = TRUE,
  marginal_estimates = NA,
  bw_marginal = NA
)

`x`	The data matrix (or data frame). Must have exactly 2 columns.
`eval_points`	The grid where the density should be estimated. Must have exactly 2 columns.
`grid_size`	If `eval_points` is not supplied, then the function will create a suitable grid diagonally through the data, with this many grid points.
`bw`	The two bandwidths, a numeric vector of length 2.
`est_method`	The estimation method, must either be "1par" for estimation with just the local correlation, or "5par" for a full locally Gaussian fit with all 5 parameters.
`tol`	The numerical tolerance to be used in the optimization. Only applicable in the 1-parameter optimization.
`run_checks`	Logical. Should sanity checks be run on the arguments? Useful to disable this when doing cross-validation for example.
`marginal_estimates`	Provide the marginal estimates here if estimation method is "`5par_marginals_fixed`", and the marginal estimates have already been found. Useful for cross-validation. List with two elements as returned by `dlg_marginal_wrapper`.
`bw_marginal`	Vector of bandwidths used to estimate the marginal distributions.

This function serves as the backbone in the body of methods concerning local Gaussian correlation. It takes a bivariate data set, x, and a bivariate set of grid points eval_points, and returns the bivariate, locally Gaussian density estimate in these points. We also need a vector of bandwidths, bw, with two elements, and an estimation method est_method

A list including the data set $x, the grid $eval_points, the bandwidths $bw, as well as a matrix of the estimated parameter estimates $par_est and the estimated bivariate density $f_est.

  x <- cbind(rnorm(100), rnorm(100))
  bw <- c(1, 1)
  eval_points <- cbind(seq(-4, 4, 1), seq(-4, 4, 1))

  estimate <- dlg_bivariate(x, eval_points = eval_points, bw = bw)