Module 1: Inference for Linear Regression

In this module, you will learn about inference for linear regression. You'll learn how to test for statistical significance between quantitative variables, conduct t-tests for slope parameters, build confidence intervals, and identify violations of linear regression assumptions.

Objective 1: Identify the hypotheses to apply to linear relationships

Learn how to formulate appropriate hypotheses when working with linear relationships between variables.

• Understanding null and alternative hypotheses for linear relationships
• Formulating hypotheses for testing relationships between variables
• Interpreting what a slope of zero means in linear regression
• Working with sample and population statistics

Objective 2: Conduct a t-test for slope parameters

Learn how to perform and interpret t-tests for slope parameters in linear regression models.

• Understanding the t-test for slope parameters
• Calculating and interpreting p-values
• Making statistical inferences about relationships
• Determining statistical significance of regression coefficients

Objective 3: Build a confidence interval for a linear regression model

Learn how to construct and interpret confidence intervals for regression parameters.

• Identifying key elements in regression output
• Understanding standard errors and their significance
• Building confidence intervals for slope terms
• Interpreting confidence intervals in the context of regression

Objective 4: Logarithmic transformations

Learn how to apply and interpret logarithmic transformations in linear regression models.

• Understanding when to use logarithmic transformations
• Applying log transformations to address non-linearity
• Interpreting coefficients after log transformations
• Working with log-linear and log-log models

Inference for Linear Regression

Resources:

The notebook for this guided project is DS_131_Inference_For_Regression.ipynb in the GitHub repository.

Inference for Linear Regression Assignment

In this module assignment, found in the file DS_131_Inference_For_Regression_Assignment_AG.ipynb in the GitHub repository, you'll apply your knowledge of inference for linear regression to a real-world dataset:

Tasks:

1. Formulate hypotheses to test relationships between variables
2. Conduct t-tests for slope parameters
3. Construct and interpret confidence intervals
4. Identify and discuss assumption violations
5. Distinguish between correlation and causation in your findings