How to calculate the variability of the instrument indicator (directivity index)?

Question

Mathematics

Good afternoon comrades. I admit right away that I am a layman in this matter.
The task was set as follows:
There is a measuring daily metric where the indicator is very variable and varies from 1 to 4 (more is better). In this case, we are interested in data for 90 days. It is necessary to give an overall evaluation score for the entire metric in order to understand whether it tends to be bad or good.
I understand that the task is very vague, I will be glad for any reference material or an indication of the direction where to actually google.
Sample data:

[3,2,3,3,2,1,3,3,3,3,3,2,2,3,3,2,2,2,2,2,3,3,2,3,4,3,3,3,3,2,2,2,3,3,1,2,3,2,2,1,3,3,2,2,3,2,3,4,4,3,2,2,2,2,4,2,2,2,2,2,2,2,2,2,3,3,3,3,2,3,2,2,2,2,2,2,2,2,2,3,3,2,3,3,3]

Answer 1

Your data is measured on an order scale, which means that you cannot directly compare the average, etc.
For such data, their own methods of evaluation are used. For example, you can break your series into several consecutive windows (45:45 limit, i.e. two windows, but I would start with 4 or 5 windows), and then compare between each two consecutive subsamples using any non-parametric comparison method, for example, the simplest - Wilcoxon-Mann-Whitney. ( https://ru.wikipedia.org/wiki/Mann_—_Whitney U-Test) The test will show if there is a statistically significant "improvement".