For anyone else who didn’t know whether a higher log score is good or bad, I think I may have figured it out by reading between the lines. It looks like higher log score = better. But please correct me if I got this wrong!
That’s right. When defined using a base 2 logarithm, the score can be interpreted as “bits of information over the maximally uncertain (uniform) distribution”. Forecasts assigning less probability mass to the true outcome than the uniform distribution result in a negative score.
For anyone else who didn’t know whether a higher log score is good or bad, I think I may have figured it out by reading between the lines. It looks like higher log score = better. But please correct me if I got this wrong!
That’s right. When defined using a base 2 logarithm, the score can be interpreted as “bits of information over the maximally uncertain (uniform) distribution”. Forecasts assigning less probability mass to the true outcome than the uniform distribution result in a negative score.
That’s right. (But lower is better for some other common scoring rules, including the Brier score.)