A Really Simple Trick to Correctly Model Your Data (with Probability Plots)

If you fit your data to a probability model/distribution, how do you know if is the 'right' one? Today's video provides a conceptual overview of quantile plots, a simple, intuitive method to visually evaluate whether your data aligns the assumptions of a probabilistic model/distribution. 0:00 Probability Distribution Selection Overview 0:39 Part 1: Compare 2 Probability Distributions Through Quantile Plots 3:48 Part 2: Evaluate a Fitted Probability Distribution to Empirical Data 5:21 Part 3: Python Implementation of Probability Distribution Fitting and Goodness-of-Fit via Quantile Plots 8:47 Key Video Takeaways ===================== Additional Info for Video: You can access the dataset and Jupyter Notebook used to run these scripts, which includes proper commenting, at: https://github.com/RiskByNumbers/Distribution-Fit-Quantile-Plots. For those interested in learning more about quantile plots, I would encourage you to read Wilk and Gnanadesikan (1968), which provides an excellent overview of a range of 'probability plots' (including quantile plots) and their use to address a range of probability and statistical applications: https://www.jstor.org/stable/2334448. Although an older paper, it does a fantastic job of explaining many of the concepts that were removed from this video for sake of brevity. Lastly, if concepts such as a random variable, a probability density function, or a cumulative distribution function are new to you, then I'd encourage you to watch this earlier video on this channel: https://www.youtube.com/watch?v=yRbfLlTmPE8 #probability #statistics #datascience #python #scipy #tutorial #probabilitydistribution ===================== Hello, and welcome to RiskByNumbers! I am a professor sharing educational resources around probability, statistics, optimization methods, algorithms, and programming to a broad audience. Outside of Youtube, you can currently find me in Vancouver, Canada at the University of British Columbia. Thank you, and I look forward to seeing you in future videos! Email: [email protected]. LinkedIn: https://www.linkedin.com/in/omar-swei/