termtable {relevance}R Documentation

Statistics for Linear Models, Including Relevance Statistics

Description

Calculate a table of statistics for (multiple) regression mdels with a linear predictor and respective print method

Usage

termtable(object, summary = NULL, testtype = NULL, r2x = TRUE,
  rlv = TRUE, rlvthres = NULL, testlevel = NULL)

## S3 method for class 'termtable'
print(x, columns = NULL, printstyle = NULL, legend = NULL,
  digits = NULL, na.print = "  ", ...)

Arguments

object

result of a model fitting function like lm

summary

result of summary(object). If NULL, the summary will be called.

testtype

type of test to be applied for dropping each term in turn. If NULL, it is selected according to the class of the object, see Details.

r2x

logical: should the collinearity measures "R2.x" for the terms be calculated?

rlv

logical: Should relevances be calculated?

rlvthres

Relevance threshold. May be a vector with the components
rel: threshold for relative effects,
stand: for standardized coefficients,
drop: for drop effects,
pred: for prediction intervals.

testlevel

1 - confidence level

For print.termtable

x

termtable to be printed

columns

columns to be printed

printstyle

determines which columns are selected if columns is NULL.

legend

logical: should the legend(s) for the symbols characterizing p-values and relevances be printed?

digits

number of significant digits to be printed

na.print

string by which NAs are shown

...

further arguments, passed to print.data.frame

Details

If testtype is not specified, it is determined by the class of object and its attribute family as follows: ...

Value

data.frame with the following columns:

coef

coefficients for terms with a single degree of freedom

df

degrees of freedom

se

standard error of coef

ciLow, ciUp

confidence interval for coef

signif0

significance value for coef

stcoef

standardized coefficient (standardized using sigma instead of the response's standard deviation)

stciLow, stciUp

confidence interval for stcoef

testst

test statistic

p.value, p.symbol

p value and symbol for it

R2.x

collinearity measure (= 1 - 1 / vif, wheere vif is the variance inflation factor)

coefRle

estimated relevance of coef

coefRls

secured relevance, lower end of confidence interval for coefRle

coefRlp

potential relevance, upper end of confidence interval for coefRle

dropRle, dropRls, dropRlp

analogous values for drop effect

predRle, predRls, predRlp

analogous values for prediction effect

coefRls.symbol, dropRls.symbol, predRls.symbol

symbols for the secured relevances

Attributes: testtype, fitclass, family, dist as determined by the argument testtype and the class and attributes of object

Author(s)

Werner A. Stahel

References

Werner A. Stahel (2020). Measuring Significance and Relevance instead of p-values. Submitted

See Also

summary(object)$coefficients

Examples

  data(swiss)
  rr <- lm(Fertility ~ . , data = swiss)
  rt <- termtable(rr)
  rt
  names(rt)
  data.frame(rt)

[Package relevance version 1.0 Index]