Shades of Time: I don’t buy it, and that’s why it’s so great.

UPDATE 1/15/2014: This blog is no longer in service.

This post is now located at: http://slendermeans.org/shades-of-time.html

Thanks,
-c.

Advertisements
This entry was posted in Data Visualization and tagged . Bookmark the permalink.

2 Responses to Shades of Time: I don’t buy it, and that’s why it’s so great.

  1. drewconway says:

    Very thoughtful analysis, thank you. I completely agree that there is absolutely no model in the analysis presented. I tried to be reserved in my language, e.g., “appears” rather than “is.” But as you rightly point out, this is much more an exercise in exploratory data analysis than statistical analysis.

    I have come to believe that the only real advantage of the dynamic visualizations that a tool like d3.js provide is the ability to move from the initial discovery in exploratory data analysis to the second-order questions immediately. I am delighted to see that this is exactly the process you went through while playing with the tool.

    Great blog, by the way, add to me RSS!

  2. Carl says:

    Drew,
    Thanks for the comment. Hopefully it didn’t sound like a dig that you weren’t model fitting here; since I was working backwards from conclusion to data, I just wanted to be clear what was driving the conclusion (visual inspection vs. stat. inference). I think you phrased your observations just right, and pointed out some of the same issues I did with the classifier. So, overall I didn’t mean to imply your were coming out with some grand scientific result here.

    Thanks again for doing and sharing this, and the book as well. They’re great pedagogical tools and have given me a lot to think about.

Comments are closed.