Linear modeling is a foundational data skill for anyone who’s interested in using their data to make predictions, or make inferences about the relationships between variables.

For data scientists, being able to make linear models is an absolute requirement, but data analysts and even hobbyists can also benefit greatly from the power of linear modeling.

*Linear Modeling in R*, the newest course in our Data Analyst in R path, will teach you this skill from the ground up. Are you ready to go hands-on and start modeling?

(If you don’t have a subscription yet, you can sign up for a free account and work through our free interactive R programming courses, or click here to check out our subscription plans.)

## What Will I Learn in This Course?

*Linear Modeling in R* will teach you how to get more out of your data by using models to make predictions and inferences. Just as important, it will teach you how to assess the accuracy of these predictions and inferences as you build experience with making, evaluating, and choosing between different sorts of models.

Throughout it all, you’ll be working with our interactive, in-your-browser coding interface. That means you’ll be going hands-on and applying these concepts using R code as you learn them.

You’ll start the course by learning the fundamentals that underlie building and selecting models — skills that you’ll call upon not only in linear modeling, but in all of your future endeavors in machine learning. We’ll go into detail on both predictive models and models that can help you make inferences to determine which variables are affecting your results.

Next, you’ll work through the step-by-step process of actually building a linear model in R, and learn more about how to select input variables to make accurate predictions or inferences.

With your initial model built, you’ll dig into fitting the it. Fitting a model in R is straightforward, but making sense of the output is a bit more involved. In this lesson you’ll learn to interpret your results effectively so you can draw useful conclusions.

Then, we’ll go deeper into assessing your model. You’ll learn to calculate Residual Standard Error and R-squared, how to visualize the residuals, and how these approaches can be used to better understand your model’s strengths and weaknesses.

Having built a single model from beginning to end, you’ll start creating multiple models, using the Broom package to fit, analyze, and visualize a number of linear models quickly and efficiently.

Finally, you’ll be tasked to bring all of this new knowledge together in a guided project that tasks you with analyzing real New York real estate pricing to make predictions using linear models.

By the end of the course, you’ll have a solid understanding of the foundations of modeling, and you’ll be confident building, fitting, and evaluating linear models in R. You’ll also have a course completion certificate and a great portfolio project that uses real-world real estate data to highlight your new skills on job applications.

## Why Should I Learn Linear Modeling?

Linear modeling is a tried and true approach for prediction and inference. If you’ve been working through our data analyst in R path, you’ve learned to analyze data. Learning linear modeling lets you go a step further, enabling you to make predictions about the future.

If your aim is to work in data science, then knowing linear modeling is par for the course. Even if you aim to spend most of your time working with more advanced machine learning applications, the fundamentals you’ll learn in this course are critical to understanding a variety of machine learning model types.

But even if you don’t intend to work as a data scientist or work with data full time at all, linear modeling is a useful skill that enables you to unleash the predictive power of your data while still being relatively accessible to even data hobbyists. Whether you’re an analyst or just someone who’d like to get more out of their data, learning linear modeling is a great way to meet that goal while also building a foundation for future study in machine learning if that’s something that interests you.