I played around with moving averages, but for an iterative algorithm and low memory requirements (storing a lot of values), exponential smoothing seems the way to go. To calculate the smoothed value over time I came up with this monster: smooth(t,x,w) = getindex.( accumulate( (a,b)->(b[1],(a…

I don’t see the option to use time values in the discussed cases.

OK, but maybe it’s worth trying with linear interpolation on a constant time step? Another package: Moving Averages · MarketTechnicals.jl (juliahub.com)

Exponential smoothing for non-constant time steps

General Usage

rafael.guerra October 12, 2024, 10:34pm 2

Check this post.

Topic		Replies	Views
Exponential smoothing Statistics question	9	2286	June 8, 2021
Smoothing Noisy Data using Moving Mean General Usage data , smoothing	9	8813	November 15, 2021
Make EWMA as fast as pandas General Usage performance , dataframes	29	1299	November 23, 2023
[ANN] Smoothers: Collection of basic smoothers and smoother related applications Package Announcements statistics , smoothing	5	1213	September 4, 2021
Mean of array General Usage smoothing	3	2404	July 7, 2019

Exponential smoothing for non-constant time steps

Related topics