This generic synthetic long-format data set has a dichotomous response <code>Y</code>
and two factors <code>X1</code> and <code>X2</code>. The response has categories <code>{yes, no}</code>.
Factor <code>X1</code> has levels <code>{a, b}</code>, and factor <code>X2</code> has levels
<code>{c, d}</code>. It also has a <code>PId</code> column for a participant identifier.
Participant identifiers are repeated across rows.

datasets

Dichotomous responses having two categories can be analyzed
with stats::glm() or lme4::glmer() using the family=binomial option.
Unfortunately, polytomous responses with three or more unordered
categories cannot be analyzed similarly because there is no analogous
family=multinomial option. For between-subjects data,
nnet::multinom() can address this need, but it cannot handle random
factors and therefore cannot handle repeated measures. To address this
gap, we transform nominal response data into counts for each categorical
alternative. These counts are then analyzed using (mixed) Poisson regression
as per Baker (1994) <doi:10.2307/2348134>. Omnibus analyses of variance can be
run along with post hoc pairwise comparisons. For users wishing to analyze nominal
responses from surveys or experiments, the functions in this package essentially
act as though stats::glm() or lme4::glmer() provide a family=multinomial option.

Jacob O. Wobbrock

multpois

Analyze Nominal Response Data with the Multinomial-Poisson Trick

ws2 function

A data frame with 60 observations on the following 4 variables:<dl>
<dt>PId</dt>
<dd>a participant identifier with levels <code>"1"</code> ... <code>"15"</code></dd><dt>X1</dt>
<dd>a within-subjects factor with levels <code>"a"</code>, <code>"b"</code></dd><dt>X2</dt>
<dd>a within-subjects factor with levels <code>"c"</code>, <code>"d"</code></dd><dt>Y</dt>
<dd>a dichotomous response with categories <code>"yes"</code>, <code>"no"</code></dd>
</dl>

Format

Within-subjects 2×2 design with dichotomous response data — ws2

A data frame with 60 observations on the following 4 variables:<dl>
<dt>PId</dt>
<dd>a participant identifier with levels <code>"1"</code> ... <code>"15"</code></dd>

<dt>X1</dt>
<dd>a within-subjects factor with levels <code>"a"</code>, <code>"b"</code></dd>

<dt>X2</dt>
<dd>a within-subjects factor with levels <code>"c"</code>, <code>"d"</code></dd>

<dt>Y</dt>
<dd>a dichotomous response with categories <code>"yes"</code>, <code>"no"</code></dd>


</dl>

ws2: Within-subjects 2×2 design with dichotomous response data

Description

Arguments

Format

See Also

Examples