From the course: Mistakes to Avoid in Machine Learning

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Forgetting traditional statistics tools

Forgetting traditional statistics tools

From the course: Mistakes to Avoid in Machine Learning

Start my 1-month free trial

Forgetting traditional statistics tools

“

- Long before machine learning and AI were the buzzwords of the century. The humble discipline of statistics laid the foundation for the work we do as data scientists. The rise of machine learning has been made possible by the unprecedented amount of computational resources we have at our fingertips. And has become the defacto approach for delivering high predictive accuracy for big data problems. But what if we're not as interested in predicting the future, as we are in explaining the past. I recommend you familiarize yourself with some traditional regression techniques as this is an excellent skillset to have in your tool belt. One benefit to over aggression is the richness of information you get from the regression output. This provides an R-squared value, variable coefficients, and P-values among other things. All of which lend themselves very well to interpretability. In the case of a regression approach, you can…

Contents