Category: R

Steven Sanderson takes us through a powerful regression technique:

LOESS, which stands for LOcal regrESSion, is a versatile and powerful technique for fitting a curve to a set of data points. Unlike traditional linear regression, LOESS adapts to the local behavior of the data, making it perfect for capturing intricate patterns in noisy datasets.

Click through for examples. LOESS works best with quadratic data, like in Steven’s last example image. The downside to it as a technique is that you can find spurious movement that may seem interesting but is just following the noise.

Steven Sanderson understands the power of compound interest:

Before we jump into the code, let’s quickly grasp the concept of exponential regression. In simple terms, it’s a statistical method used to model relationships where the rate of change of a variable is proportional to its current state. Think of scenarios like population growth, viral spread, or even financial investments.

Read on to see how you can perform a regression in this kind of scenario.

Steven Sanderson needs more than a line:

In the realm of data analysis, quadratic regression emerges as a powerful tool for uncovering the hidden patterns within datasets that exhibit non-linear relationships. Unlike its linear counterpart, quadratic regression ventures beyond straight lines, gracefully capturing curved relationships between variables. This makes it an essential technique for understanding a wide range of phenomena, from predicting stock prices to modeling population growth.

Embark on a journey into the world of quadratic regression using the versatile R programming language. We’ll explore the steps involved in fitting a quadratic model, interpreting its parameters, and visualizing the results. Along the way, you’ll gain hands-on experience with this valuable technique, enabling you to tackle your own data analysis challenges with confidence.

Read on to see how you can model a quadratic relationship between one independent variable (or multiple independent variables) and the dependent variable in lm().

Steven Sanderson lays out some updates:

One of the standout additions is the introduction of util_log_ts(). This function seems like a game-changer, providing a streamlined way to log time series data. This is incredibly useful, especially when dealing with extensive datasets, making the whole process more efficient and user-friendly. This is a helper function for auto_stationarize().

There’s a lot in this update and the blog post also includes several examples of automating stationarity and ARIMA.

Steven Sanderson isn’t content with regressing against a single variable:

Multiple linear regression is a powerful statistical method that allows us to examine the relationship between a dependent variable and multiple independent variables.

Read on to see how you can do this in R, as well as some of the types of things you should think about along the way, including the concept of multicollinearity.

Steven Sanderson builds a prediction interval:

Prediction intervals are a powerful tool for understanding the uncertainty of your predictions. They allow you to specify a range of values within which you are confident that the true value will fall. This can be useful for many tasks, such as setting realistic goals, making informed decisions, and communicating your findings to others.

In this blog post, we will show you how to create a prediction interval in R using the mtcars dataset. The mtcars dataset is a built-in dataset in R that contains information about fuel economy, weight, displacement, and other characteristics of 32 cars.

Click through to see an example based on linear regression.

Michael Mayer lays some groundwork:

SHAP is the predominant way to interpret black-box ML models, especially for tree-based models with the blazingly fast TreeSHAP algorithm.

For general models, two slower SHAP algorithms exist:

1. Permutation SHAP (Štrumbelj and Kononenko, 2010)
2. Kernel SHAP (Lundberg and Lee, 2017)

Read on to understand more about these two forms of SHAP, as well as how they compare in two datasets of differing levels of difficulty.