The Pod of Asclepius is a healthcare technology podcast for the technical crowd.
No fluff, no sales pitches, just important health tech ideas (described well!) to help everyone keep learning and becoming more of an expert in the field.
Our guests are top researchers (from academia and industry), entrepreneurs, and regulatory experts. They will talk about cool technology, from data science to engineering, but also share insights on practical concerns of bridging the gap between technical innovation and a clinical solution.
All content for Data & Science with Glen Wright Colopy is the property of Glen Wright Colopy and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
The Pod of Asclepius is a healthcare technology podcast for the technical crowd.
No fluff, no sales pitches, just important health tech ideas (described well!) to help everyone keep learning and becoming more of an expert in the field.
Our guests are top researchers (from academia and industry), entrepreneurs, and regulatory experts. They will talk about cool technology, from data science to engineering, but also share insights on practical concerns of bridging the gap between technical innovation and a clinical solution.
Jingyi Jessica Li | Statistical Hypothesis Testing vs Machine Learning Binary Classification
Data & Science with Glen Wright Colopy
55 minutes 55 seconds
4 years ago
Jingyi Jessica Li | Statistical Hypothesis Testing vs Machine Learning Binary Classification
Jingyi Jessica Li | Statistical Hypothesis Testing versus Machine Learning Binary Classification
Jingyi Jessica Li (UCLA) discusses her paper "Statistical Hypothesis Testing versus Machine Learning Binary Classification". Jingyi noticed several high-impact cancer research papers using multiple hypothesis testing for binary classification problems. Concerned that these papers had no guarantee on their claimed false discovery rates, Jingyi wrote a perspective article about clarifying hypothesis testing and binary classification to scientists.
#datascience #science #statistics
0:00 – Intro1:50 – Motivation for Jingyi's article3:22 – Jingyi's four concepts under hypothesis testing and binaryclassification8:15 – Restatement of concepts12:25 – Emulating methods from other publications13:10 – Classification vs hypothesis test: features vs instances21:55 - Single vs multiple instances23:55 - Correlations vs causation24:30 - Jingyi’s Second and Third Guidelines30:35 - Jingyi’s Fourth Guideline36:15 - Jingyi’s Fifth Guideline39:15 – Logistic regression: An inference method & a classification method42:15 – Utility for students44:25 – Navigating the multiple comparisons problem (again!)51:25 – Right side, show bio-arxiv paper
Data & Science with Glen Wright Colopy
The Pod of Asclepius is a healthcare technology podcast for the technical crowd.
No fluff, no sales pitches, just important health tech ideas (described well!) to help everyone keep learning and becoming more of an expert in the field.
Our guests are top researchers (from academia and industry), entrepreneurs, and regulatory experts. They will talk about cool technology, from data science to engineering, but also share insights on practical concerns of bridging the gap between technical innovation and a clinical solution.
