Let's say I have around 30k points of time series data with values ranging from 0 to 0.5. I have split this data into 5 buckets of 0.1 each which contains values within that range. I then plot these values with x axis being the bucket sizes and y axis being the number of values.

I noticed that the distribution pattern depends on the size of the buckets. How do I know for sure what type of distribution my data follows?

My knowledge in statistics is not very good and maybe evident from my question. Any help appreciated!

  • $\begingroup$ Perhaps we can best direct you if you tell us a little more about what you are trying to do exactly? What benefit are you hoping to gain from understanding the distribution of your data? Or are you just doing this because you think it's an intermediate step for some larger analysis? If so, what analysis are you carrying out? $\endgroup$ – StatsStudent Sep 3 '20 at 10:10
  • $\begingroup$ @ItamarMushkin omg, yes! Thanks a ton! :) $\endgroup$ – ouila Sep 3 '20 at 10:27