|
Pi to the power of pi
SAS’ Rick Wicklin celebrates the importance of mathematics in this Pi Day blog post.
The quantile fit plot: Comparing empirical and predicted quantiles for a univariate model
PROC UNIVARIATE in SAS produces a table, called the FitQuantiles table, which indicates how well the quantiles of the model distribution agree with the empirical distribution of the data. This post discusses the FitQuantiles table, shows how to visualize it with a graph, and demonstrates how to create a larger version of the table, offering further insight into how well the model's "estimation of probabilities" agrees with empirical evidence.
Deviance residuals and the DEVIANCE function in SAS
The parameters for generalized linear models are fit by using maximum likelihood estimation. The deviance is based on the loglikelihood function for the model. The deviance statistic is a goodness of fit statistic, and the deviance residuals are a generalization of the familiar least squares residuals. You can use the DEVIANCE function in the DATA step to compute the deviance statistic and the deviance residuals.
Install VS Code Extensions Offline: A step-by-step guide
There are a lot of reasons why you might not be able to find the extension you want within VS Code and install directly within the tool. SAS’ Sean Ford introduces you to a way to install any extension manually.
How to create and manage Python virtual environments
Wouldn’t it be great if you could create a Python environment with only the packages and versions you need? A virtual environment may be what you need. SAS’ Stu Sztukowski gives 5 reasons to create one.
SAS Container Runtime Testbench: A field developed tool for SAS Intelligent Decisioning
SAS’ Simon Topp demonstrates the power of running/debugging decisions locally on you own desktop, where you have full control. The benefit? Testing/debugging becomes very easy and accessible.
Training code, scoring code, and what makes a model
Learn the definitions of machine learning model, training code and scoring code in this post by Sophia Rowland and Colby Hoke of SAS. You’ll also see their recommendation for handoffs between data scientists and engineering.
How to fix unformatted URL job results
Have you recently updated your release of SAS Viya and noticed that jobs submitted via a URL produce results that no longer appear formatted using standard SAS formatting? This is due to an update in the default content security policy setting in Stable 2024.02 onwards. In this SAS Support Community article, SAS’ Greg Treiman explains the issue and show you how to resolve it so that you get the job results you need.
Ever wonder what’s in those credit card agreements you never read? Let’s see if SAS can help us out!
It’s easy to incur credit card debt at exorbitant interest rates, posing a mountain of financial burden that can be extremely difficult to get out of. With credit card agreements often exceeding 15 pages in length, no wonder they are not on top of your reading list. Still, by looking at the fine print of credit card agreements before signing up for one, you can save money when you do have to carry credit charges over several billing periods. For this post, SAS’ Peter Christie downloaded and analyzed hundreds of credit card agreements from dozens of financial institutions. The data is generally available from the Consumer Financial Protection Bureau.
Smart Conversations, Smarter Decisions: Integrating SAS Intelligent Decisioning with Azure Open AI
Imagine an AI assistant that not only listens to you but drives critical workflows—flawlessly calculating risk ratings, explaining complex outcomes, and ensuring decisions align with trusted, replicable standards. SAS’ Bogdan Teleuca’ article, which includes a demo, says that by integrating Azure OpenAI conversational capabilities with SAS Intelligent Decisioning, the approach in the post blends the power of conversational AI and advanced analytics into a unified experience. From secure login to rule-based decisioning, this AI-powered system tackles complex decision-making with speed, transparency, and reliability.
Unsupervised variable selection: Identifying input spaces that maximize data variance
Variable selection is an important data preprocessing task that improves model performance by removing irrelevant and/or redundant inputs, enhancing accuracy, and minimizing computational complexity. Variable selection can be supervised (using the target variable) or unsupervised (ignoring the target). SAS Viya supports both, with supervised methods reducing irrelevant inputs and unsupervised methods removing redundant ones. In this article, SAS’ Sharad Saxena highlights a specific unsupervised method known as variance-based unsupervised variable selection.
|
