Bootstrapped – A Python library to generate confidence intervals
Published in 2017, this chronicle by @jimarcey details the mechanics of building a profitable, self-funded business without venture backing.
Core Principles for Independent Builders:
Charging customers from day one acts as the ultimate filter for building software that solves genuine, high-urgency problems.
Keeping fixed overhead low and leveraging lean infrastructure allows founders to stay alive until market tailwinds kick in.
Small, repetitive improvements in customer retention and conversion rates yield massive returns over multi-year horizons.
Community Debate Themes:
The community focused on B2B customer acquisition channels, cold email vs SEO distribution, and balancing full-time employment with side-project development.
CATEGORY Bootstrapping & MRR →
HISTORICAL ERA Cloud & Mobile Era (2014–2019)
COMMUNITY SCORE 94 points
TOTAL DISCUSSIONS 30 comments
From the project README:
How bootstrapped works tldr - Percentile based confidence intervals based on bootstrap re-sampling with replacement.
---
MIT OCW 18.05 has this to say about the technique:
https://ocw.mit.edu/courses/mathematics/18-05-introduction-to-probability-and-statistics-spring-2014/readings/MIT18_05S14_Reading24.pdf ↗
The bootstrap percentile method is appealing due to its simplicity. However it depends on the bootstrap distribution of mean(x') based on a particular sample being a good approximation to the true distribution of mean(x). Rice says of the percentile method, “Although this direct equation of quantiles of the bootstrap sampling distribution with confidence limits may seem initially appealing, it’s rationale is somewhat obscure.”
In short, don’t use it.
Use the empirical bootstrap instead (we have explained both in the hopes that you won’t confuse the empirical bootstrap for the percentile bootstrap).
---
Updated to reflect suggestions in comments below.
Neat!
OP, how does this compare to scikits.bootstrap [1] feature/performance-wise?
[1] https://scikits.appspot.com/bootstrap ↗
While on the topic of confidence intervals, has anyone encountered a package capable of generating multinomial confidence intervals similar to CRAN's MultinomialCI? I've yet to find a Python solution.
There are better algorithms for bootstrap intervals that you perhaps should look into. Better in the sense of quality, not speed.
Google e.g. "interval BCa"
Is there a reason you chose the percentile instead of something like the pivotal (and for not adding the options for other intervals)? Is it solely for simplicity?