Note from Dave: This post is actually a replacement due to the previous Twitter Prediction post being weirdly targeted by spambots. |
If you’ve read my series up to this point, you know the pattern being identified should be not only be reproducible, but predictive. So for my 22nd blood test, I decided to have a little fun. Instead of predicting about where it landed myself, I tweeted…
I need a few twitter volunteers from the audience…
— Dave Keto (@DaveKeto) July 7, 2016
I got three: Raphi Sirt @raphaels7, Richard Morris @khiron, and Jeff Winkler @winkler1. I invited them to a secret page with these instructions:
- Review the graph below. It has 21 points plotted in the red line and 22 points plotted in the blue.
- Make your best guess as to where the next point will be on the red line.
- Tweet a funny sentence about anything that includes:
- @DaveKeto
- #Predict
- (Your predicted number)
Click here for the larger sized graph
They followed up with these tweets:
@DaveKeto #Predict 257 bottles of beer on the wall, 257 bottles of beer …
— Richard Morris (@khiron) July 7, 2016
Hey @DaveKeto, I #Predict the next point on the red line will be a double dozen dozen.. 288
— Jeff Winkler (@winkler1) July 7, 2016
Hi @DaveKeto, to correctly #predict lab results I look to Anchorman wisdom – so 260#keto #science #statistics pic.twitter.com/HkfEbVwo2Z
— Raphi Sirt (@raphaels7) July 7, 2016
Reminder — all these tweets are dated July 7, 2016, the night before my blood test.
To replot the graph with their predictions:
The LDL-C result from my July 8th test just came in Friday and is as follows:
And thus, here’s the updated graph with the new 283 result plotted on the red line:
Here’s the close up:
Thus making Jeff Winkler @winkler1 the winner!
If you’re wondering how I could have three total strangers could predict where my cholesterol numbers would be in such a tight range, you haven’t been reading my series! (See Part I, Part II, and Part III)
Your correlations may be even stronger than you think if you have not corrected for autocorrelation (typical for time series data). You may already be doing this, but if you want to know how, I’ll explain.