Can a Bayesian framework help us solve real world problems?

Photo by Riho Kroll on Unsplash

When I think back to my high school and college statistics classes, z-tests, t-tests, p-values and alpha values are the main words that come to my mind. Little did I know there was a completely different side to statistics, that in my opinion can be much more intuitive. In this post, I’ll explore the difference between the frequentist and Bayesian frameworks of inferential statistics, why I find the Bayesian philosophy easier to understand, and lastly, apply the Bayesian framework to some real-world events.


How to regularize your model when testing scores aren’t up to par

Photo by Omar Flores on Unsplash

When I first began working on data science projects, I was completely focused on getting the best training scores possible. I believed the higher my training accuracy, the better my model was performing, which is only true to an extent.

Often, a model’s purpose is to be used on future unseen data, to predict a class or value or at least make sense of the inputs. We measure how well this works by running the model on the validation set during model tuning and by running it on the test data after choosing a model. …


Accuracy, precision, recall and F1 score explained in plain English

Photo by Mika Baumeister on Unsplash

When it comes to classification models, the metrics used to determine performance are quite different from those used to evaluate regression models. In my opinion, the metrics used to describe the performance of a classification model are more intuitive. You have likely had experience with some of these metrics when they are used to describe a medical test determining whether or not you have an illness — for example, covid-19 tests. If you are being tested for Covid-19, there are four potential outcomes of the test:

  • True Positive: You have the virus and you test positive for the virus.
  • False…


The basics of when to use and how to interpret

Photo by Chandler Cruttenden on Unsplash

When building a linear regression model, we sometimes hit a roadblock and experience poor model performance and/or violations of the assumptions of linear regression — the dataset in its raw form simply does not perform well. When this occurs, a log transformation may be a saving grace. However, this changes the meaning of our model, and so we need to be careful in our interpretation when a log transformation occurs.

In this article, we will explore the power of log transformation in three simple linear regression examples: when the independent…


While working on my latest data science project, I realized I needed a way to quickly highlight the maximum value in each of my visualizations, so my reader could focus on the conclusion to each of my analyses. I was using seaborn plots in my project, drawn to their simplicity and beautiful built-in format, and thought there must be an easy way to add a special color palette: one color for the maximum value, and one color for all other values. When my search came up empty-handed, I realized I could use what I had learned about Python functions to…

Samantha Knee

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store