0

I’m working on a design project where I need to visualize salary data across different roles. I’m considering using a modified box plot to show the salary ranges (minimum, median, maximum salary) instead of the traditional interquartile range (IQR). I believe this would help users quickly understand the overall spread of salaries without diving into statistical quartiles.

My question is:

Is it valid to modify a box plot this way and still call it a box plot?

Are there any potential issues or misinterpretations that could arise from representing ranges rather than quartiles in this format?

Would another type of chart be more suitable for this purpose?

Improve this question

2 Answers 2

Reset to default
0

I think your approach depends on the characteristics of the data. If the data has outliers, then a boxplot that shows 25th to 75th percentile, with the tines extending to minimum and maximum values, can give some information about the shape of the distribution.

Here is an illustration created on Google sheets. They call it the candlestick chart.

A boxplot with four categories

Improve this answer
0

The plot you want to use is alright for showing the data and compare multiple professions salary ranges (I think in the graph above, its only missing the median in the plot). If you want to go deeper into this approach you can use a violin plot which effectively shows the distribution of the data for each group; with this plots you will provide a full understanding of the group's distribution.

violin plot

Or if you think the violin could mislead the conversation you can use the raincloud plot, that is the Interquartile range plot showing the distribution to compare the data.

Raincloud Plot

Improve this answer

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.