⌘K
Change language Switch ThemeSign In
Narrow Mode
Debunking Statistical Fallacies in Time Series Data
Debunking Statistical Fallacies in Time Series Data
 ### François Chollet@fchollet
Ok, this thread has apparently been a magnet for hordes drooling morons who not only don't get stats, but can't even read. If you're a normally intelligent reader of this tweet, here's an extra example of my point:
If you take two RANDOM, INDEPENDENT timeseries (i.e. knowing one gives you NO information about the other) that are each highly temporally autocorrelated (e.g. two random walks), and you plot one against the other as a scatter plot, what you get is a single X/Y trajectory that will ALWAYS look very structured. Yet it is random. Like the figure below.
Code to reproduce the figure and play around with this idea: colab.research.google.com/drive/1FIk8j_A…
Of course if the two series happen to be correlated, then you will ALSO see something very structured. It's just that this type of visualization is a completely retarded way to look at such data. If you think this is deep, you are innumerate.Show More
Apr 5, 2026, 4:37 PM View on X
4 Replies
3 Retweets
47 Likes
6,236 Views F François Chollet @fchollet
One Sentence Summary
Chollet critiques the misinterpretation of structured patterns in random time series data and provides a reproducible example.
Summary
This tweet serves as a technical correction regarding the misinterpretation of correlation in time series. Chollet explains that plotting two independent random walks against each other can create misleadingly structured scatter plots. He provides a Google Colab link to demonstrate this statistical fallacy, emphasizing the importance of statistical literacy.
AI Score
87
Influence Score 11
Published At Today
Language
English
Tags
Data Science
Statistics
Time Series
Data Visualization
Code Example HomeArticlesPodcastsVideosTweets