Skip to content

Commit

Permalink
Fixed wrong parameterization of the t-distribution in the readme.
Browse files Browse the repository at this point in the history
  • Loading branch information
rasmusab committed Nov 1, 2013
1 parent 06aeea9 commit 5ec5956
Show file tree
Hide file tree
Showing 6 changed files with 8 additions and 18 deletions.
1 change: 0 additions & 1 deletion .~lock.krusche_style_diagrams_template (copy).odg#

This file was deleted.

Binary file modified figure/unnamed-chunk-6.png
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
4 changes: 2 additions & 2 deletions readme.md
Expand Up @@ -98,8 +98,8 @@ Here we see that the t distribution has five named labels and to make a diagram


```r
plot_dist(dists$t, labels = c(mean = expression(mu), left_sd = expression(sigma),
right_df = "df"))
plot_dist(dists$t, labels = c(mean = expression(mu),
left_scale = expression(sigma), right_df = "df"))
```

![plot of chunk unnamed-chunk-6](https://raw.github.com/rasmusab/distribution_diagrams/master/figure/unnamed-chunk-6.png)
Expand Down
2 changes: 1 addition & 1 deletion readme_rel_links.Rmd
Expand Up @@ -64,7 +64,7 @@ dists$t$labels
Here we see that the t distribution has five named labels and to make a diagram with a $\sigma$ to the left, and a `df` to the right we would write:

```{r fig.width=2.25, fig.height=1.688, fig.show='hold'}
plot_dist(dists$t, labels=c(mean = expression(mu), left_sd = expression(sigma), right_df = "df"))
plot_dist(dists$t, labels=c(mean = expression(mu), left_scale = expression(sigma), right_df = "df"))
```

Expand Down
9 changes: 3 additions & 6 deletions readme_rel_links.html

Large diffs are not rendered by default.

10 changes: 2 additions & 8 deletions readme_rel_links.md
Expand Up @@ -41,12 +41,10 @@ The file [plot_dist.R](plot_dist.R) contains all you need to get going: the func

If you don't want to bother with generating your own images you can download png and svg images for all the distributions [here](distribution_diagrams.zip). The actual script that generated the images is available [here](create_diagrams.R) which might be useful to look at as it contains many examples of how `plot_dist` works.

I've also made a nifty templat you can use together with the open-source [Libre Office Draw](http://www.libreoffice.org/features/draw/) that makes it really easy to make Kruschke style diagrams. Download the template [here](krusche_style_diagrams_template.odg). A file with some extra distributions for Libre Office Draw is available [here](extra_distributions.odg). If you
I've also made a nifty template you can use together with the open-source [Libre Office Draw](http://www.libreoffice.org/features/draw/) that makes it really easy to make Kruschke style diagrams. Download the template [here](krusche_style_diagrams_template.odg). A file with some extra distributions for Libre Office Draw is available [here](extra_distributions.odg). I also made a short screencast that shows how to use this template:

[![Screencast video link](screencast_image.jpeg)](http://youtu.be/uSJ2S900UHA)



Plot size and output format
---------------------------
The diagrams produced by `plot_dist` are made to look good when being around 2-3 inches wide and 1.5-2.5 inches high. If you want to make larger plots you have to play around with the scale parameter:
Expand Down Expand Up @@ -100,14 +98,10 @@ Here we see that the t distribution has five named labels and to make a diagram


```r
plot_dist(dists$t, labels = c(mean = expression(mu), left_sd = expression(sigma),
plot_dist(dists$t, labels = c(mean = expression(mu), left_scale = expression(sigma),
right_df = "df"))
```

```
## Error: no coordinates were supplied
```

![plot of chunk unnamed-chunk-6](figure/unnamed-chunk-6.png)


Expand Down

0 comments on commit 5ec5956

Please sign in to comment.