Hi all, in case interesting/useful: some research I've been involved in takes a different approach to online quantile estimation (our work is based on Hermite series estimators) and compares favorably to online quantile estimation approaches based on stochastic approximation for example. We've recently released the code:
I've done some comparisons versus the P^2 algorithm (using the OnlineStats implementation in Julia) and the Hermite series based algorithm appears to have comparable accuracy in the tests conducted. The Hermite based approach has the advantage that it estimates the full quantile function though, so arbitrary quantiles can be obtained at any point in time.
https://github.com/MikeJaredS/hermiter
I've done some comparisons versus the P^2 algorithm (using the OnlineStats implementation in Julia) and the Hermite series based algorithm appears to have comparable accuracy in the tests conducted. The Hermite based approach has the advantage that it estimates the full quantile function though, so arbitrary quantiles can be obtained at any point in time.