Data Statistics & Regression is a plugin that helps generating data regression, prediction and basic data statistics.
Takes as input 2 lists of numbers (X and Y) do some magic on it (regression), and returns a new list of numbers that is the Y values of the trend line.
We provide 5 types of regressions:
Check the editor at:
If you need any help, send me an email at email@example.com or post here.
We have been looking for something like this for some time. So thank you! We have time series data, where the x axis is a date. I assume for this X axis data we just ensure the data is sorted ASC by date and convert the date to a number so it’s monotonically increasing? Example: 20230103,20230104,20230105
Apologize for my delayed response. I just noticed you comment here.
Yes, you would need to sort the data first and pass the X and Y values ordered the same way,
Let me know if you need any help implementing
Does your plugin support multiple linear regression?
Hello @Atomily .
Yes it does. You can add multiple elements to the page, each with a different series to perform the regression.
Let me know if you run into any trouble so I can assist you.
Thanks for the response. Perhaps I wasn’t too clear. I’m referring to multivariant linear regression. I.e. Instead of just one independent variable it can include multiple independent variables: Y = b0 + b1 * X1 + b2 * X2 + … + bn * Xn
Hi @Atomily .
Sorry for my confusion.
At this point, we offer only polynomial regression from the same variant.
I understand this could be a enhancement on our side, so i will take a look to implement this
This would be epic @mayco. Please let me know if you have an ETA as I need this for my app rather urgently
Hey @Atomily did you find any other way to achieve this? Yesterday, while testing, we found that the plugin only calculates the regression on Y values and are looking to achieve a correlation of 2 different variables.
I could not find a solution on bubble.io so for the meantime I’ve got a developer to do it on python