beran.select: Tuning parameter selector for Beran (1974)'s location...
In nilanjanalaha/log.location: What the Package Does (One Line, Title Case)

Description Usage Arguments Details Value Author(s) References See Also Examples

beran.est computes the location estimator in a location shift model using Beran (1974)'s estimator. This function depends on tuning parameters theta and M. We estimate the MSE of the estimators and to choose the best (theta, M) from a set of options.

1	beran.select(x, t, Mvec, inth, B)

`x`	An array of length n; the dataset.
`t`	Optional, an array of real numbers, contains values of theta, parameter needed for estimating the Fourier coefficient.
`Mvec`	Optional, an array of integers, the number of basis functions to use. See details.
`inth`	A number; the initial estimator. The default is the median.
`B`	Optional, the number of bootstrap samples. The default is 100.

To this end, we generate B Bootstrap samples and for each pair of (theta, M), we estimate the MSE by computing

\frac{∑_{i=1}^B(\hatθ_i(theta, M)-θ)^2}{B}

where θ_i(theta, M) is the estimator based on the i-th bootstrap sample and θ is the true theta.

We take theta to be in c(0.01, seq(0.10, 0.80, by=0.05)) and take M to be in (2, 4, 6, ..., 10).

A vector of foure numbers.

param: A 2 columns, the number of rows is same as the length of inth. Each row gives the optimal (dn, tn) for the corresponding inth value.
estimte: Gives the estimators of θ using the optimal (dn, tn)'s.

Nilanjana Laha (maintainer), nlaha@hsph.harvard.edu.

Laha, N. Location estimation fr symmetric and log-concave densities. Submitted.

Stone, C. (1975). Adaptive maximum likelihood estimators of a location parameter, Ann. Statist., 3, 267-284.

beran.est