Bits per Spike as a Betting Game: An Interpretable Unit for Held-Out Log-Likelihood in Neural Data Analysis
Converting confusing neural statistics into seconds of recording time
Neuroscientists comparing models of brain activity use a metric called "bits per spike," but this number is hard to interpret—is 0.34 bits good or bad? This paper translates bits per spike into a concrete unit: how many seconds of recorded neural data you'd need to prove one model is actually better than another. The conversion uses a betting framework borrowed from statistics, turning an abstract information measure into something directly meaningful.
Neuroscientists spend months collecting expensive neural recordings to test competing models of how the brain works. This framework lets them know upfront whether a model improvement is large enough to matter—for instance, whether they need 120 milliseconds or 11 seconds of additional recording to confidently reject a simpler baseline model. That clarity helps researchers allocate limited recording time efficiently and judge whether their hard-won data actually supports their scientific claims.