Page 1 of 1
Boxplot outliers
Posted: Thu Mar 25, 2021 6:39 pm
by RangoMcRoony
Under descriptives there's an option to do a box-plot of data, this can be used to see if there are outliers. However i cannot seem to figure out how i get jamovi to indicate the specific participant that is an outlier. I know there's an option for this in Jasp, PSPP, SPSS, sofa-statistics. Pretty much all the popular statistical software. Is this something that is possible with jamovi or is this something that still needs to be developed?
I know it isnt really a sophisticated question, this is my first post so let me know if i did something wrong or posted in the wrong forum
Thank you
Re: Boxplot outliers
Posted: Fri Apr 02, 2021 10:14 pm
by jonathon
hi,
there's a bug on ggplot which is currently preventing us from providing this feature.
we're waiting on a fix there.
kind regards
jonathon
Re: Boxplot outliers
Posted: Tue Aug 17, 2021 8:42 pm
by RangoMcRoony
any updates on this?
Re: Boxplot outliers
Posted: Tue Aug 17, 2021 11:50 pm
by jonathon
i think the bug in ggplot persists.
jonathon
Re: Boxplot outliers
Posted: Wed Jun 22, 2022 10:20 pm
by peszka
I found that you can first calculate what an outlier would be...say for your data it is anything bigger than 15 or smaller than 2. Then use jamovi's filters feature to find these outliers...say in one filter you put =variablename > 15. If you then change the variable to a nominal or ordinal scale (if it isn't already), then go to the exploration module and create a frequency distribution by clicking "Frequency tables". In the output, you'll see how many outliers you have next to N in the descriptives table and in the frequencies table you'll see the row number where each outlier is located under the column labeled "Levels"
Re: Boxplot outliers
Posted: Wed Jun 29, 2022 11:39 pm
by jonathon
an update, the latest version of jamovi does give you case numbers on box plots for outliers.
jonathon
Re: Boxplot outliers
Posted: Sat Jul 30, 2022 12:02 pm
by Solène M
Hello,I'm sorry if this problem has already been solved earlier but I didn't find a solution...
I'm currently trying to identify outliers with Jamovi to exclude them from my analysis.
Is there a way to make Jamovi identify the outliers that I should remove?
Thank you very much for your hepl!
Re: Boxplot outliers
Posted: Sat Jul 30, 2022 2:34 pm
by MAgojam
Solène M wrote:Is there a way to make Jamovi identify the outliers that I should remove?
Hey,
you might be interested in taking a look here, where is my suggestion to a question similar to yours?
viewtopic.php?f=2&t=2234&p=8298
All cases that are outliers for the variable of interest (in the example age) are excluded from the analysis using the "
Median
Absolute
Deviations".
Cheers,
Maurizio