# modeHuntingBlock: Multiscale analysis of a density via block procedure In modehunt: Multiscale Analysis for Density Functions

## Description

Simultanous confidence statements for the existence and location of local increases and decreases of a density f, computed via the block procedure.

## Usage

 1 2 modeHuntingBlock(X.raw, lower = -Inf, upper = Inf, d0 = 2, m0 = 10, fm = 2, crit.vals, min.int = FALSE) 

## Arguments

 X.raw Vector of observations. lower Lower support point of f, if known. upper Upper support point of f, if known. d0 Initial parameter for the grid resolution. m0 Initial parameter for the number of observations in one block. fm Factor by which m is increased from block to block. crit.vals 2-dimensional vector giving the critical values for the desired level. min.int If min.int = TRUE, the set of minimal intervals is output, otherwise all intervals with a test statistic above the critical value (in their respective block) are given.

## Details

See blocks for details how \mathcal{I}_{app} is generated and modeHunting for a proper introduction to the notation used here. The function modeHuntingBlock uses the test statistic T^+_n({\bf X}, \mathcal{B}_r), where \mathcal{B}_r contains all intervals of Block r, r=1,…,\#blocks. Critical values for each block individually are received via finding an \tilde α such that

P(B_n({\bf{X}}) > q_{r,\tilde α / (r+tail)^γ} \ for \ at \ least \ one \ r) ≤ α,

where q_{r,α} is the (1-α)–quantile of the distribution of T^+_n({\bf X}, \mathcal{B}_r). We then define the sets \mathcal{D}^\pm(α) as

\mathcal{D}^\pm(α) := \Bigl\{\mathcal{I}_{jk} \ : \ \pm T_{jk}({\bf{X}}) > q_{r,\tilde α / (r+tail)^γ} \, , \ r = 1,… \#blocks\Bigr\}.

Note that γ and tail are automatically determined by crit.vals.

If min.int = TRUE, the set \mathcal{D}^\pm(α) is replaced by the set {\bf{D}}^\pm(α) of its minimal elements. An interval J \in \mathcal{D}^\pm(α) is called minimal if \mathcal{D}^\pm(α) contains no proper subset of J. This minimization post-processing step typically massively reduces the number of intervals. If we are mainly interested in locating the ranges of increases and decreases of f as precisely as possible, the intervals in \mathcal{D}^\pm(α) \setminus \bf{D}^\pm(α) do not contain relevant information.

## Value

 Dp The set \mathcal{D}^+(α) (or \bf{D}^+(α)). Dm The set \mathcal{D}^-(α) (or \bf{D}^-(α)).

## Note

Critical values for some combinations of n and α are provided in the data sets cvModeBlock. Critical values for other values of n and α can be generated using criticalValuesApprox.

## Author(s)

Kaspar Rufibach, kaspar.rufibach@gmail.com,
http://www.kasparrufibach.ch

Guenther Walther, gwalther@stanford.edu,
www-stat.stanford.edu/~gwalther

## References

Duembgen, L. and Walther, G. (2008). Multiscale Inference about a density. Ann. Statist., 36, 1758–1785.

Rufibach, K. and Walther, G. (2010). A general criterion for multiscale inference. J. Comput. Graph. Statist., 19, 175–190.

modeHunting, modeHuntingApprox, and cvModeBlock.
 1 2 3 ## for examples type help("mode hunting") ## and check the examples there