Matt Haberland
Matt Haberland (@mdhaber) is an Assistant Professor in the BioResource and Agricultural Engineering Department at Cal Poly. He earned his Ph.D. in Mechanical Engineering at MIT in 2014 for his thesis "Extracting Principles from Biology for Application to Running Robots", and previously created the Contact Sensor / Stabilizer for the rock drill of the Mars rover Curiosity. Matt has been attending the SciPy conference since 2019 as maintainer of the SciPy library.
Sessions
Resampling and Monte Carlo statistical techniques are surprisingly intuitive, and they are often more flexible and accurate than their better-known analytical counterparts. In this tutorial, participants will develop their intuitive understanding of frequentist statistics and apply it using three functions in scipy.stats
- monte_carlo_test
, permutation_test
, and bootstrap
- to dramatically expand the statistical analyses they can perform with the SciPy Library.
"Intuitive Statistics" may sound like an oxymoron, but perhaps this is because traditional academic treatments of hypothesis tests and confidence intervals focus either on a set of procedures to memorize or, at a more advanced level, their formal underpinnings. However, statistical resampling and Monte Carlo techniques are surprisingly understandable, and these techniques are often more flexible and accurate than their better-known counterparts. This poster presents three functions in scipy.stats
- monte_carlo_test
, permutation_test
, and bootstrap
- which are relatively simple to understand, yet flexible enough to replace almost all other hypothesis test and confidence interval functions in the SciPy library.