# t1way: A heteroscedastic one-way ANOVA for trimmed means. In WRS2: A Collection of Robust Statistical Methods

## Description

The `t1way` function computes a one-way ANOVA on trimmed means. Homoscedasticity assumption not required. It uses a generalization of Welch's method. Corresponding post hoc tests can be performed using `lincon`.

## Usage

 ```1 2``` ```t1way(formula, data, tr = 0.2) lincon(formula, data, tr = 0.2) ```

## Arguments

 `formula` an object of class formula. `data` an optional data frame for the input data. `tr` trim level for the mean.

## Details

In the post hoc computations, confidence intervals are adjusted to control FWE, but p-values are not adjusted to control FWE.

## Value

`t1way` returns an object of class `"t1way"` containing:

 `test` value of the test statistic (F-statistic) `df1` degrees of freedom `df2` degrees of freedom `p.value` p-value `effsize` explanatory measure of effect size `call` function call

`lincon` returns an object of class `"mcp1"` containing:

 `comp` inference for all pairwise comparisons `fnames` names of the factor levels

## References

Wilcox, R. (2012). Introduction to Robust Estimation and Hypothesis Testing (3rd ed.). Elsevier.

`med1way`,`t1waybt`

## Examples

 ```1 2 3 4``` ```t1way(libido ~ dose, data = viagra) ## post hoc tests lincon(libido ~ dose, data = viagra) ```

### Example output

```Call:
t1way(formula = libido ~ dose, data = viagra)

Test statistic: 3
Degrees of Freedom 1: 2
Degrees of Freedom 2: 4
p-value: 0.16

Explanatory measure of effect size: 0.79

Call:
lincon(formula = libido ~ dose, data = viagra)

psihat ci.lower ci.upper p.value
placebo vs. low      -1 -5.31858  3.31858 0.43533
placebo vs. high     -3 -7.31858  1.31858 0.06017
low vs. high         -2 -6.31858  2.31858 0.15830
```

WRS2 documentation built on May 2, 2019, 4:46 p.m.