Learn to calculate regression equations and perform hypothesis tests with The Manga Guide to Regression Analysis.
You also learn: simple, multiple, and logistic regression to predict iced tea orders and bakery revenues, and calculate confidence intervals and odds ratios.
๐ง Introduces you to the tools of data analysis like graphs, charts, and tables, and exploring how to use samples to answer questions.
๐ก Plus, the author covers common data collection problems like selection bias and measurement error and how to deal with them effectively.
Naked statistics is a classic and bound to be on any and every list of statistics books.
It's a great read with a number of real world case studies.
๐คThe Signal And The Noise breaks it down: sometimes we get overwhelmed by masses of data and forget to be cautious and diligent in finding the important signals.
๐ง๐กHow to Measure Anything teaches you how to make smart decisions using applied logic and behavioral economics.
๐คฏ Discover how misframing what needs to be measured and misperception of measurement elements can lead to mismeasurement and perceptions of the immeasurable.
You won't believe the history behind Bayes' rule: discoverd in 1740s by amateur mathematician to solving WWII codebreaking and now used in DNA decoding and Homeland Security.
๐๐ป The Theory That Would Not Die explores the controversy and obsessions surrounding this theorem. ๐ฅ
How Not To Be Wrong will help you make better decisions, navigate life effortlessly, and assess risks like a pro.
๐ช๐ฝ Here are 3 key lessons to get you started:
1) Math is mostly common sense. 2) Probability โ risk. 3) Scientific research findings can be wrong.
๐ค
๐ค "The Success Equation" helps untangle the intricate strands of skill and luck in our lives and offers concrete tips on how to use this knowledge to make better decisions.
๐ช๐ฝ Don't miss out on this must-read for anyone looking to succeed in business and life.
๐ฒ "Thinking in Bets" shows you how to objectively evaluate your beliefs, work around biases, and learn from the past.
๐ช๐ฝ Every decision is a bet, and this guide will help you navigate the quantifiable risks and come out on top.
๐ฅ๐ค Fooled by Randomness uncovers the role of chance in business and investing, and how it influences our actions, decisions, and risk-taking.
๐คฏ Get a fresh perspective on the role of uncertainty in our world. ๐
The curse of dimensionality is a major roadblock for machine learning practitioners.
But most don't fully understand it.
Don't be left in the dark - join me in this thread as I clarify and demystify this concept ๐๐ฝ๐งต
The Curse of Dimensionality (let's just call it "The Curse") refers to problems that occur when you try to use statistical methods in high-dimensional space.
As the number of features (dimensionality) increases, the data becomes relatively more sparse, and often exponentially more samples are needed to make statistically significant predictions.
Feature selection is a crucial part of building a good machine learning model.
But most data scientists don't think before they select features.
The fact is: feature selection in machine learning is not always necessary.
Here are 5 situation when you don't need it ๐๐ฝ๐งต
1. You have a small dataset that doesn't have many features.
If the data you're using is small and doesn't have many features, you don't need to do feature selection.
2. The features are already carefully selected
If the features you're using have already been carefully chosen and are important for the task you are trying to do, you don't need to do feature selection.