Omnibus test

OmnibusTest calculates overall p-value for linear combination of variables using likelihood ratio test.

omnibusTest(
  object,
  omnibus_groups,
  placeholder = "term",
  correction = "bonferroni",
  n_correction = NULL
)

Arguments

object

An existing fit from a model function such as lm, glm and many others.

omnibus_groups

List of character vectors giving sets of variables for which omnibus test should be applied.

placeholder

String specifying term in object's formula which should be substituted with variables during analysis.

correction

String specifying multiple testing correction method. See details for further information.

n_correction

Integer specifying number of comparisons to consider during multiple testing correction calculations. For Bonferroni correction it is possible to specify a number lower than the number of comparisons being made. This is useful in cases when knowledge about the biology or redundance of alleles reduces the need for correction. For other methods it must be at least equal to the number of comparisons being made; only set this (to non-default) when you know what you are doing!

Value

Data frame with columns:

  • "group" Omnibus group name

  • "term" Elements of omnibus group added to base model

  • "df" Difference in degrees of freedom between base and extended model

  • "logLik" Difference in log likelihoods between base and extended model

  • "statistic" Chisq statistic

  • "p.value" P-value

  • "p.adjusted" Adjusted p-value

Details

Likelihood ratio test is conducted by comparing a model given in an object with an extended model, that is created by including the effect of variables given in variables as their linear combination.

Examples

midas <- prepareMiDAS(hla_calls = MiDAS_tut_HLA,
                      colData = MiDAS_tut_pheno,
                      experiment = "hla_aa")

# define base model
object <- lm(disease ~ term, data = midas)
omnibusTest(object,
            omnibus_groups = list(
              A_29 = c("A_29_D", "A_29_A"),
              A_43 = c("A_43_Q", "A_43_R")
            ))
#> Warning: While evaluating the model problems occured:
#> 
#> • Warnings:
#> • Coefficients for variables: A_29_A could not be estimated, those variables will not be included in likelyhood ratio test result.; occured 1 times, including variables: A_29_D
#> • Coefficients for variables: A_43_R could not be estimated, those variables will not be included in likelyhood ratio test result.; occured 1 times, including variables: A_43_Q
#>   group   term df    logLik statistic    p.value p.adjusted
#> 1  A_29 A_29_D  1 0.5007512  1.001502 0.31694726 0.63389452
#> 2  A_43 A_43_Q  1 2.1307456  4.261491 0.03898569 0.07797137