• How to Judge a Quantitative Model  

    Recently, FiveThirtyEight posted a review of how accurate their models have been. The blog talks about calibration, which “measures whether, over the long run, events occur about as often as you say they’re going to occur.” As you could probably guess, their models are fairly well calibrated. This is not surprising given they are in the business of making predictions; and if they were bad at making predictions they probably wouldn’t still be around or be posting about it…The same could be said about us!

  • Top 5 Reads of the Week | 361 Capital Blog  

    Our favorite reads of the week and the quotes that make them worthy…

    The best forecasters, by contrast, view their own ideas as hypotheses in need of testing. If they make a bet and lose, they embrace the logic of a loss just as they would the reinforcement of a win. This is called, in a word, learning.

  •  

    The room is surrounded with people and cameras and in the middle of it all sits an oval table with bright green felt big enough to sit nine people, a dealer, and two piles of poker chips. Before the cards are even dealt you have a good feeling about this hand, so you peek and see a 7 of clubs and a 2 of hearts. Despite knowing that this is statistically the worst hand in poker, you trust your “gut” and decide to call your opponent. To your delight, 7, 7, 2 comes on the flop, with these cards you know that you’ve gone from the statistically worst hand in poker to one of the best possible outcomes. Question: Did you make a good decision?

  • Top 5 Reads of the Week | 361 Capital Blog  

    Our favorite reads of the week and the quotes that make them worthy…

    The second might matter more in the long run, as the Fed embarks on its first review of its 2% inflation target set seven years ago. Mr. Powell and Vice Chairman Richard Clarida have already made clear that the target itself isn’t up for debate but the way it is implemented could change, with big implications for markets.

  • Has the Value Trend Reversed?  

    A year ago, we posted this piece showing the wide gap between the returns of the Russell 2000 Growth (RUO) and Value (RUJ) indices. At the time, RUO’s relative outperformance was approaching two standard deviations above average, measured on a rolling 52-week basis. The gist of the post was that it was a large difference, but not abnormal, with the implication that the trend should reverse, but not sure when. With another year of data, we can see how things have played out.