utils_samples: Random Sampling

In metan: Multi Environment Trials Analysis

Random Sampling

Description

• sample_random() performs Simple Random Sampling or Stratified Random Sampling

• sample_systematic() performs systematic sampling. In this case, a regular interval of size k (k = floor(N/n)) is generated considering the population size (N) and desired sample size (n). Then, the starting member (r) is randomly chosen between 1-k. The second element is r + k, and so on.

Usage

sample_random(data, n, prop, by = NULL, weight = NULL)

sample_systematic(data, n, r = NULL, by = NULL)

Arguments

data	A data frame. If data is a grouped_df, the operation will be performed on each group (stratified).
n, prop	Provide either n, the number of rows, or prop, the proportion of rows to select. If neither are supplied, n = 1 will be used.
by	A categorical variable to compute the sample by. It is a shortcut to dplyr::group_by() that allows to group the data by one categorical variable. If more than one grouping variable needs to be used, use dplyr::group_by() to pass the data grouped.
weight	Sampling weights. This must evaluate to a vector of non-negative numbers the same length as the input. Weights are automatically standardised to sum to 1.
r	The starting element. By default, r is randomly selected between 1:k

Value

An object of the same type as data.

Examples

library(metan)
sample_random(data_ge, n = 5)
sample_random(data_ge,
              n = 3,
              by = ENV)

sample_systematic(data_g, n = 6)

metan documentation built on March 7, 2023, 5:34 p.m.