Here is the start of the parsed data:

Here is the start of the uploaded data:

Please check that these summary statistics for your data are as you'd expect.

You can download the statistics with the buttons below the table.

This shows the ECDF of your non-missing data (see summary to check if there were missing values)

You can use the dialogue below the plot to download it chosing the name and the format of the plot

These next two values will need some trial and error to get the best aesthetic and will be different depending on the file size, i.e. the last two values above, and for different download file formats.
The onscreen plot size is set to 800px and can't be altered.You may want a much bigger download graphic file size but if so you may have to increase the plot text size to scale it up to the file size. Experiment!
Download plot

Thanks to Keith Newman for the download handler: shinyDownload

Here are the values of the quantiles and the confidence limits.

You can download the statistics with the buttons below the table.

This shows the quantiles and their CIs as a forest plot.

These next two values will need some trial and error to get the best aesthetic and will be different depending on the file size, i.e. the last two values above, and for different download file formats.
The onscreen plot size is set to 800px and can't be altered.You may want a much bigger download graphic file size but if so you may have to increase the plot text size to scale it up to the file size. Experiment!
Download plot

Thanks to Keith Newman for the download handler: shinyDownload

I am increasingly convinced that percentiles, quantiles, are neglected in our field and more informative than means and SDs.

However, it is easy to assume that percentiles or quantiles you get from a dataset are more precise than they actually are. This app gives you percentiles/quantiles for any given dataset you input WITH the confidence intervals around the observed values.

If your dataset is not large, these intervals may be such that we overlapping CIs for say the 10th and the 5th percentiles.

There are at least three ways to get CIs for quantiles: Nyblom's method, the 'exact' method and bootstrapping.The paper by Nyblom Nyblom, J. (1992). Note on interpolated order statistics. Statistics & Probability Letters, 14(2), 129–131. https://doi.org/10.1016/0167-7152(92)90076-H seems pretty clear that his method is generally better than the 'exact' method and much quicker to computethan the bootstrap so I have used his method here. I have used Michael Höhle's quantileCI package https://github.com/mhoehle/quantileCI to get the CIs.

To complicate things further, though generally ignorably, there are actually a number of ways to compute quantiles. I have used method 8, the default in the R quantile() function. Search for that if it worries you!

If it really, really worries you and you want another quantile method, contact me and I can tweak this app to allow you to choose any of the other R methods for quantiles. But make sure you can persuade me the differences matter!!

App started 16.iv.24 by Chris Evans. PSYCTC.org

Last updated 5.v.24.

Licenced under a Creative Commons, Attribution Licence-ShareAlike Please respect that and put an acknowledgement and link back to here if re-using anything from here.

Background and related resources

This shiny app is one of a growing number in, my shiny server
They complement:

There is a form if you want to contact me: so do please use that if you think there is anything wrong here or anything that could be improved.

There is also now an Email announcement list, never updating more than monthly, where I will put up developments of new apps here, a summary of updates to the glossary and new posts in the Rblog. You can sign up for that here.