td_tests {terminaldigits}

Tests of independence and uniformity for terminal digits in a data frame

Description

The function td_tests() is a wrapper which applies the functionstd_independence() and td_uniformity to a data frame. When a group is specified, tests are conducted separated for each group. P-values and p-values adjusted by the false discovery rate (Benjamini and Hochberg, 1995) are reported.

Usage

td_tests(
  data,
  variable,
  decimals,
  group = NULL,
  reps = 10000,
  test = "Chisq",
  tolerance = 64 * .Machine$double.eps
)

Arguments

data

A data frame

variable

A numeric variable. Tests for terminal digits are performed on this variable.

decimals

an integer specifying the number of decimals. This can be zero if the terminal digit is not a decimal.

group

A variable used to group the primary variable such that p-values are calculated separately for each group. The default is set to NULL in which case p-values are simply calculated for the whole data set.

reps

an integer specifying the number of Monte Carlo simulations. The default is set to 10,000.

test

a string specifying the test of independence. The default is Pearson's chi-squared statistic ("Chisq"). Also available is the log-likelihood ratio statistic ("G2"), the Freeman-Tukey statistic ("FT"), and the Root-mean-square statistic ("RMS").

tolerance

sets an upper bound for rounding errors when evaluating whether a statistic for a simulation is greater than or equal to the statistic for the observed data. The default is identical to the tolerance set for simulations in the chisq.test function from the stats package in R.

Value

A data frame containing the following components:

statistic

the value of the test statistic

p_value_independence

the simulated p-value for the test of independence

P_value_uniformity

the simulated p-value for the test of uniformity (chi-squared GOF)

p_value_independence_fdr

the simulated p-value for the test of independence adjusted via the false discovery rate (if the group variable is specified)

P_value_uniformity

the simulated p-value for the test of uniformity (chi-squared GOF) adjusted via the false discovery rate (if the group variable is specified)

References

Benjamini, Y., and Hochberg, Y. (1995). Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society Series B, 57, 289–300. doi: 10.1111/j.2517-6161.1995.tb02031.x. https://www.jstor.org/stable/2346101.

Examples

td_tests(decoy, weight, decimals = 2, group = subject, reps = 1000)