Week 12/Module 11 - Regression Analysis

This reading introduces regression analysis as a statistical method for modeling relationships between variables, covering its core concepts, purposes, and applications across fields; learners use it to build conceptual understanding before diving into specific regression techniques.

This reading explains simple linear regression, covering the mathematical relationship between one predictor and one outcome variable, how the regression line is fitted, and interpretation of slope and intercept; learners use it as the foundational reference for understanding and applying single-predictor regression models.

This reading extends regression to models with two or more predictor variables, covering how multiple predictors are incorporated simultaneously, coefficient interpretation, and the motivation for using multiple regression over simple linear regression; learners use it to understand and build more realistic predictive models.

This reading covers the metrics and diagnostic tools used to assess how well a regression model fits data, including R-squared, residual analysis, and other performance indicators; learners and instructors use it to evaluate and compare regression models after fitting them.

This reading explains how to read and interpret regression output tables, covering coefficients, p-values, confidence intervals, and common pitfalls in interpretation; learners use it as a practical guide to translate regression results into meaningful, real-world conclusions.

This reading addresses the application of regression analysis to messy, real-world datasets, covering challenges such as missing data, skewed distributions, and multicollinearity, along with strategies to handle them; learners use it to bridge the gap between textbook methods and practical data analysis workflows.

An introductory reading that defines regression analysis, distinguishes predictor from response variables, and explains how fitting a line to scatter data lets engineers describe and quantify relationships — read first to build conceptual grounding before the computational topics.

A lesson on simple linear regression covering the one-predictor straight-line model, least-squares fitting, and interpretation of slope and intercept using engineering examples such as load versus deflection and temperature versus reaction rate; learners use it to turn measured data into a usable prediction equation.

A reading that extends the single-predictor model to multiple regression (y = b0 + b1x1 + ... + bkxk), explaining how a fitted surface replaces a fitted line and how each slope coefficient represents one predictor's effect while holding the others constant.

A topic on assessing model quality, addressing how much variation the model explains, significance testing of individual predictors, the overall F-test comparing the model to predicting the mean, and residual-based checks of model adequacy.

A guide to reading regression software output, explaining coefficients in the units of the problem, p-values and whether a predictor differs from zero, R-squared, and overall model usefulness — used to practice translating computer output into engineering conclusions.

A capstone applied reading that walks through the complete regression workflow on messy real-world data, including selecting and cleaning a dataset, choosing variables, framing an answerable question, and reporting results — used as the bridge from textbook exercises to authentic engineering analysis.

A consolidated module page compiling all six Week 12 regression topics — foundations, simple linear regression, multiple regression, model evaluation, result interpretation, and real-world application — in one continuous document for review or printing.

A hub page linking learners to the Module 11 PowerPoint slides, lecture video, and a Google Colab notebook for hands-on regression analysis practice.

A study reference page explaining key regression analysis concepts—including simple linear regression, model definition, and interpretation—supported by links to the module lecture, used by learners to review and reinforce core content.

A graded discussion assignment asking learners to provide a real-world example from a field of their choice where linear regression would be a good fit, then review and comment on at least one classmate's response.