There is a newer version of this record available.

Software Open Access

sjPlot - Data Visualization for Statistics in Social Science.

Daniel Lüdecke


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.1310947", 
  "title": "sjPlot - Data Visualization for Statistics in Social Science.", 
  "issued": {
    "date-parts": [
      [
        2018, 
        7, 
        12
      ]
    ]
  }, 
  "abstract": "<p>New functions</p>\n\n<ul>\n\t<li><code>tab_model()</code> as replacement for <code>sjt.lm()</code>, <code>sjt.glm()</code>, <code>sjt.lmer()</code> and <code>sjt.glmer()</code>. Furthermore, <code>tab_model()</code> is designed to work with the same model-objects as <code>plot_model()</code>.</li>\n\t<li>New colour scales for ggplot-objects: <code>scale_fill_sjplot()</code> and <code>scale_color_sjplot()</code>. These provide predifined colour palettes from this package.</li>\n\t<li><code>show_sjplot_pals()</code> to show all predefined colour palettes provided by this package.</li>\n\t<li><code>sjplot_pal()</code> to return colour values of a specific palette.</li>\n</ul>\n\n<p>Deprecated</p>\n\n<p>Following functions are now deprecated:</p>\n\n<ul>\n\t<li><code>sjp.lm()</code>, <code>sjp.glm()</code>, <code>sjp.lmer()</code>, <code>sjp.glmer()</code> and <code>sjp.int()</code>. Please use <code>plot_model()</code> instead.</li>\n\t<li><code>sjt.frq()</code>. Please use <code>sjmisc::frq(out = &quot;v&quot;)</code> instead.</li>\n</ul>\n\n<p>Removed / Defunct</p>\n\n<p>Following functions are now defunct:</p>\n\n<ul>\n\t<li><code>sjt.grpmean()</code>, <code>sjt.mwu()</code> and <code>sjt.df()</code>. The replacements are <code>sjstats::grpmean()</code>, <code>sjstats::mwu()</code> and <code>tab_df()</code> resp. <code>tab_dfs()</code>.</li>\n</ul>\n\n<p>Changes to functions</p>\n\n<ul>\n\t<li><code>plot_model()</code> and <code>plot_models()</code> get a <code>prefix.labels</code>-argument, to prefix automatically retrieved term labels with either the related variable name or label.</li>\n\t<li><code>plot_model()</code> gets a <code>show.zeroinf</code>-argument to show or hide the zero-inflation-part of models in the plot.</li>\n\t<li><code>plot_model()</code> gets a <code>jitter</code>-argument to add some random variation to data points for those plot types that accept <code>show.data = TRUE</code>.</li>\n\t<li><code>plot_model()</code> gets a <code>legend.title</code>-argument to define the legend title for plots that display a legend.</li>\n\t<li><code>plot_model()</code> now passes more arguments in <code>...</code> down to <code>ggeffects::plot()</code> for marginal effects plots.</li>\n\t<li><code>plot_model()</code> now plots the zero-inflated part of the model for <code>brmsfit</code>-objects.</li>\n\t<li><code>plot_model()</code> now plots multivariate response models, i.e. models with multiple outcomes.</li>\n\t<li>Diagnostic plots in <code>plot_model()</code> (<code>type = &quot;diag&quot;</code>) can now also be used with <code>brmsfit</code>-objects.</li>\n\t<li>Axis limits of diagnostic plots in <code>plot_model()</code> (<code>type = &quot;diag&quot;</code>) for Stan-models (<code>brmsfit</code> or <code>stanreg</code> resp. <code>stanfit</code>) can now be set with the <code>axis.lim</code>-argument.</li>\n\t<li>The <code>grid.breaks</code>-argument for <code>plot_model()</code> and <code>plot_models()</code> now also takes a vector of values to directly define the grid breaks for the plot.</li>\n\t<li>Better default calculation for grid breaks in <code>plot_model()</code> and <code>plot_models()</code> when the <code>grid.breaks</code>-argument is of length one.</li>\n\t<li>The <code>terms</code>-argument for <code>plot_model()</code> now also allows the specification of a range of numeric values in square brackets for marginal effects plots, e.g. <code>terms = &quot;age [30:50]&quot;</code> or <code>terms = &quot;age [pretty]&quot;</code>.</li>\n\t<li>For coefficient-plots, the <code>terms</code>- and <code>rm.terms</code>-arguments for <code>plot_model()</code> now also allows specification of factor levels for categorical terms. Coefficients for the indicted factor levels are kept resp. removed (see <code>?plot_model</code> for details).</li>\n\t<li><code>plot_model()</code> now supports <code>clmm</code>-objects (package <em>ordinal</em>).</li>\n\t<li><code>plot_model(type = &quot;diag&quot;)</code> now also shows random-effects QQ-plots for <code>glmmTMB</code>-models, and also plots random-effects QQ-plots for all random effects (if model has more than one random effect term).</li>\n</ul>\n\n<p>Bug fixes</p>\n\n<ul>\n\t<li><code>plot_model(type = &quot;re&quot;)</code> now supports standard errors and confidence intervals for <code>glmmTMB</code>-objects.</li>\n\t<li>Fixed typo for <code>glmmTMB</code>-tidier, which may have returned wrong data for zero-inflation part of model.</li>\n\t<li>Multiple random intercepts for multilevel models fitted with <code>brms</code> area now shown in each own facet per intercept.</li>\n\t<li>Remove unnecessary warning in <code>sjp.likert()</code> for uneven category count when neutral category is specified.</li>\n\t<li><code>plot_model(type = &quot;int&quot;)</code> could not automatically select <code>mdrt.values</code> properly for non-integer variables.</li>\n\t<li><code>sjp.grpfrq()</code> now correctly uses the complete space in facets when <code>facet.grid = TRUE</code>.</li>\n\t<li><code>sjp.grpfrq(type = &quot;boxplot&quot;)</code> did not correctly label the x-axis when one category had no elements in a vector.</li>\n\t<li>Problems with German umlauts when printing HTML tables were fixed.</li>\n</ul>", 
  "author": [
    {
      "family": "Daniel L\u00fcdecke"
    }
  ], 
  "version": "2.5.0", 
  "type": "article", 
  "id": "1310947"
}
3,139
122
views
downloads
All versions This version
Views 3,1391,383
Downloads 12227
Data volume 595.3 MB123.3 MB
Unique views 2,8111,327
Unique downloads 10024

Share

Cite as