ss16pusa_sample_zeros_miss

<p>Example dataframe for input categorical data with structural zeros (with missing values). It contains 1000 observations and 5 variables.</p><table><tr><td>
    [,1] </td>
<td> AGEP  </td>
<td> age </td>
<td> 7 levels </td>
</tr><tr><td>
    [,2] </td>
<td> MAR </td>
<td> marital status </td>
<td> 5 levels </td>
</tr><tr><td>
    [,3] </td>
<td> SCHL    </td>
<td> educational attainment </td>
<td> 9 levels </td>
</tr><tr><td>
    [,4] </td>
<td> SEX    </td>
<td> sex </td>
<td> 2 levels </td>
</tr><tr><td>
    [,5] </td>
<td> WKL   </td>
<td> When last worked </td>
<td> 3 levels </td>
</tr></table>

These routines create multiple imputations of missing at random categorical data, and create multiply imputed synthesis of categorical data, with or without structural zeros. Imputations and syntheses are based on Dirichlet process mixtures of multinomial distributions, which is a non-parametric Bayesian modeling approach that allows for flexible joint modeling, described in Manrique-Vallier and Reiter (2014) <doi:10.1080/10618600.2013.844700>.

Jingchen Hu

ss16pusa_sample_zeros_miss: Example dataframe for input categorical data with structural zeros (with missing values).

Description

Arguments

[,1]	AGEP	age	7 levels
[,2]	MAR	marital status	5 levels
[,3]	SCHL	educational attainment	9 levels
[,4]	SEX	sex	2 levels
[,5]	WKL	When last worked	3 levels