# Allocation-Methods: Algorithms for Exact Optimization Allocation In andrewraim/tommysampling: Exact Optimal Allocation Algorithms for Stratified Sampling

## Description

Algorithms III and IV from Wright (2017), and classical (unconstrained) Neyman allocation. Algorithm III finds the optimial allocation for a given total sample size `n`. Algorithm IV samples until the overall variance is smaller than a given `v0`.

## Usage

 ```1 2 3 4 5 6 7``` ```algIII(n, N.str, S.str, lo.str = rep(1, length(N.str)), hi.str = rep(Inf, length(N.str)), verbose = FALSE) algIV(v0, N.str, S.str, lo.str = rep(1, length(N.str)), hi.str = rep(Inf, length(N.str)), verbose = FALSE) neyman(n, N.str, S.str) ```

## Arguments

 `n` Target sample size for Algorithm III (integer) `N.str` Population size for each stratum (integer vector) `S.str` Standard deviation for each stratum (numeric vector) `lo.str` Sample size lower bounds for each stratum (numeric vector) `hi.str` Sample size upper bounds for each stratum (numeric vector) `verbose` Print detailed information for each selection (boolean) `v0` Target variance for Algorithm IV (numeric)

## Value

An object which contains the results; the structure depends on allocation method.

## References

Tommy Wright (2012). The Equivalence of Neyman Optimum Allocation for Sampling and Equal Proportions for Apportioning the U.S. House of Representatives. The American Statistician, 66, pp.217-224.

Tommy Wright (2017), Exact optimal sample allocation: More efficient than Neyman, Statistics & Probability Letters, 129, pp.50-57.

andrewraim/tommysampling documentation built on May 6, 2018, 5:03 a.m.