Skip to content

Get the full experience in the app More learning modes, track your progress, detailed topics

Start Now

Regression Analysis

Master the fundamentals of regression analysis for predicting outcomes and understanding relationships between variables. Learn simple linear regression, interpret coefficients, assess model quality, and apply regression to real-world prediction problems.

Intermediate
10 modules
420 min
4.7

Overview

Master the fundamentals of regression analysis for predicting outcomes and understanding relationships between variables. Learn simple linear regression, interpret coefficients, assess model quality, and apply regression to real-world prediction problems.

What you'll learn

  • Understand the purpose of regression analysis
  • Fit a simple linear regression model
  • Interpret slope and intercept coefficients
  • Evaluate model fit using R-squared
  • Make predictions using regression equations
  • Recognize assumptions and limitations

Course Modules

10 modules
1

Introduction to Regression

Understanding what regression analysis does and when to use it.

Key Concepts
Regression Analysis Dependent Variable (Y) Independent Variable (X) Prediction Best Fit

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Regression Analysis
  • Define and explain Dependent Variable (Y)
  • Define and explain Independent Variable (X)
  • Define and explain Prediction
  • Define and explain Best Fit
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Regression analysis examines the relationship between variables to make predictions. Given data on advertising spending and sales, regression finds the equation that best predicts sales from spending. Unlike correlation (which measures strength of relationship), regression provides a specific predictive equation.

In this module, we will explore the fascinating world of Introduction to Regression. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Regression Analysis

What is Regression Analysis?

Definition: Statistical method for predicting one variable from another

When experts study regression analysis, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding regression analysis helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Regression Analysis is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Dependent Variable (Y)

What is Dependent Variable (Y)?

Definition: The outcome variable being predicted

The concept of dependent variable (y) has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about dependent variable (y), you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about dependent variable (y) every day.

Key Point: Dependent Variable (Y) is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Independent Variable (X)

What is Independent Variable (X)?

Definition: The predictor variable used for prediction

To fully appreciate independent variable (x), it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of independent variable (x) in different contexts around you.

Key Point: Independent Variable (X) is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Prediction

What is Prediction?

Definition: Estimating Y value for a given X

Understanding prediction helps us make sense of many processes that affect our daily lives. Experts use their knowledge of prediction to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Prediction is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Best Fit

What is Best Fit?

Definition: The line that minimizes prediction errors

The study of best fit reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Best Fit is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: Prediction vs. Explanation

Regression serves two purposes: prediction and explanation. Prediction: Use the model to forecast Y from new X values (predict next month's sales). Explanation: Understand how X affects Y (each $1000 in ads increases sales by $5000). The regression line minimizes the distance between predicted and actual values, giving the "best fit" through the data points.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? The term "regression" was coined by Francis Galton in 1886 studying heredity—tall parents had children who "regressed" toward average height!


Key Concepts at a Glance

Concept Definition
Regression Analysis Statistical method for predicting one variable from another
Dependent Variable (Y) The outcome variable being predicted
Independent Variable (X) The predictor variable used for prediction
Prediction Estimating Y value for a given X
Best Fit The line that minimizes prediction errors

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Regression Analysis means and give an example of why it is important.

  2. In your own words, explain what Dependent Variable (Y) means and give an example of why it is important.

  3. In your own words, explain what Independent Variable (X) means and give an example of why it is important.

  4. In your own words, explain what Prediction means and give an example of why it is important.

  5. In your own words, explain what Best Fit means and give an example of why it is important.

Summary

In this module, we explored Introduction to Regression. We learned about regression analysis, dependent variable (y), independent variable (x), prediction, best fit. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

2

The Simple Linear Regression Model

Understanding the equation of a straight line for prediction.

Key Concepts
Linear Regression Intercept (a) Slope (b) Regression Equation Prediction Equation

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Linear Regression
  • Define and explain Intercept (a)
  • Define and explain Slope (b)
  • Define and explain Regression Equation
  • Define and explain Prediction Equation
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Simple linear regression uses a straight line to model the relationship between one X and one Y. The equation is Y = a + bX, where a is the y-intercept (predicted Y when X=0) and b is the slope (change in Y for each unit change in X). The goal is to find the values of a and b that best fit the data.

In this module, we will explore the fascinating world of The Simple Linear Regression Model. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Linear Regression

What is Linear Regression?

Definition: Regression using a straight line model

When experts study linear regression, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding linear regression helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Linear Regression is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Intercept (a)

What is Intercept (a)?

Definition: Predicted Y when X equals zero

The concept of intercept (a) has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about intercept (a), you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about intercept (a) every day.

Key Point: Intercept (a) is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Slope (b)

What is Slope (b)?

Definition: Change in Y for each unit change in X

To fully appreciate slope (b), it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of slope (b) in different contexts around you.

Key Point: Slope (b) is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Regression Equation

What is Regression Equation?

Definition: The formula Y = a + bX

Understanding regression equation helps us make sense of many processes that affect our daily lives. Experts use their knowledge of regression equation to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Regression Equation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Prediction Equation

What is Prediction Equation?

Definition: Using the model to estimate Y values

The study of prediction equation reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Prediction Equation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: Interpreting the Equation

If the regression equation for predicting salary from years of experience is Salary = 30000 + 5000×Years, then: Intercept (a=30000): A person with 0 years experience is predicted to earn $30,000. Slope (b=5000): Each additional year of experience adds $5,000 to predicted salary. For someone with 10 years: Salary = 30000 + 5000(10) = $80,000.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? Linear regression is the foundation of machine learning. Most complex AI models can be thought of as sophisticated extensions of this basic concept!


Key Concepts at a Glance

Concept Definition
Linear Regression Regression using a straight line model
Intercept (a) Predicted Y when X equals zero
Slope (b) Change in Y for each unit change in X
Regression Equation The formula Y = a + bX
Prediction Equation Using the model to estimate Y values

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Linear Regression means and give an example of why it is important.

  2. In your own words, explain what Intercept (a) means and give an example of why it is important.

  3. In your own words, explain what Slope (b) means and give an example of why it is important.

  4. In your own words, explain what Regression Equation means and give an example of why it is important.

  5. In your own words, explain what Prediction Equation means and give an example of why it is important.

Summary

In this module, we explored The Simple Linear Regression Model. We learned about linear regression, intercept (a), slope (b), regression equation, prediction equation. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

3

Finding the Best Fit Line

Understanding how the regression line is calculated.

Key Concepts
Least Squares Residual Sum of Squared Errors Covariance Best Fit

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Least Squares
  • Define and explain Residual
  • Define and explain Sum of Squared Errors
  • Define and explain Covariance
  • Define and explain Best Fit
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

The "least squares" method finds the line that minimizes the sum of squared differences between actual Y values and predicted Y values (called residuals). This gives us the best possible straight line through the data points. The formulas for slope and intercept involve the means of X and Y, and the covariance and variance.

In this module, we will explore the fascinating world of Finding the Best Fit Line. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Least Squares

What is Least Squares?

Definition: Method minimizing sum of squared residuals

When experts study least squares, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding least squares helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Least Squares is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Residual

What is Residual?

Definition: Difference between actual and predicted Y

The concept of residual has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about residual, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about residual every day.

Key Point: Residual is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Sum of Squared Errors

What is Sum of Squared Errors?

Definition: Total of squared residuals: Σ(y - ŷ)²

To fully appreciate sum of squared errors, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of sum of squared errors in different contexts around you.

Key Point: Sum of Squared Errors is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Covariance

What is Covariance?

Definition: Measure of how X and Y vary together

Understanding covariance helps us make sense of many processes that affect our daily lives. Experts use their knowledge of covariance to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Covariance is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Best Fit

What is Best Fit?

Definition: The line that minimizes squared errors

The study of best fit reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Best Fit is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: The Least Squares Method

The slope formula is: b = Σ(x - x̄)(y - ȳ) / Σ(x - x̄)². This equals the correlation times the ratio of standard deviations: b = r × (sy/sx). The intercept is: a = ȳ - b×x̄. The regression line always passes through the point (x̄, ȳ). Why squared? Squaring errors prevents positive and negative errors from canceling, and penalizes large errors more heavily.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? The least squares method was invented independently by Legendre (1805) and Gauss (1809). Gauss used it to predict the orbit of the asteroid Ceres!


Key Concepts at a Glance

Concept Definition
Least Squares Method minimizing sum of squared residuals
Residual Difference between actual and predicted Y
Sum of Squared Errors Total of squared residuals: Σ(y - ŷ)²
Covariance Measure of how X and Y vary together
Best Fit The line that minimizes squared errors

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Least Squares means and give an example of why it is important.

  2. In your own words, explain what Residual means and give an example of why it is important.

  3. In your own words, explain what Sum of Squared Errors means and give an example of why it is important.

  4. In your own words, explain what Covariance means and give an example of why it is important.

  5. In your own words, explain what Best Fit means and give an example of why it is important.

Summary

In this module, we explored Finding the Best Fit Line. We learned about least squares, residual, sum of squared errors, covariance, best fit. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

4

R-Squared: Measuring Model Fit

Evaluating how well the regression line fits the data.

Key Concepts
R-Squared (R²) Coefficient of Determination Explained Variance Unexplained Variance Model Fit

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain R-Squared (R²)
  • Define and explain Coefficient of Determination
  • Define and explain Explained Variance
  • Define and explain Unexplained Variance
  • Define and explain Model Fit
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

R-squared (R²) measures the proportion of variance in Y that is explained by X. It ranges from 0 to 1. R² = 0.75 means 75% of the variation in Y is explained by the regression; 25% remains unexplained. R² is the square of the correlation coefficient r, hence the name.

In this module, we will explore the fascinating world of R-Squared: Measuring Model Fit. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


R-Squared (R²)

What is R-Squared (R²)?

Definition: Proportion of variance explained by the model

When experts study r-squared (r²), they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding r-squared (r²) helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: R-Squared (R²) is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Coefficient of Determination

What is Coefficient of Determination?

Definition: Another name for R²

The concept of coefficient of determination has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about coefficient of determination, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about coefficient of determination every day.

Key Point: Coefficient of Determination is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Explained Variance

What is Explained Variance?

Definition: Variation in Y accounted for by the model

To fully appreciate explained variance, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of explained variance in different contexts around you.

Key Point: Explained Variance is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Unexplained Variance

What is Unexplained Variance?

Definition: Variation due to factors not in the model

Understanding unexplained variance helps us make sense of many processes that affect our daily lives. Experts use their knowledge of unexplained variance to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Unexplained Variance is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Model Fit

What is Model Fit?

Definition: How well the model describes the data

The study of model fit reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Model Fit is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: Interpreting R-Squared

R² = 1 - (SSE / SST), where SSE is sum of squared errors (residuals) and SST is total sum of squares (variance in Y). High R² (close to 1) means the model explains most variation—predictions are accurate. Low R² (close to 0) means X doesn't explain Y well—other factors matter. Caution: R² can be high even for poor models if data has little variation, and adding variables always increases R² (adjusted R² corrects for this).

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? In social sciences, R² of 0.30 is often considered "good" because human behavior is complex. In physics, R² below 0.99 might indicate a problem!


Key Concepts at a Glance

Concept Definition
R-Squared (R²) Proportion of variance explained by the model
Coefficient of Determination Another name for R²
Explained Variance Variation in Y accounted for by the model
Unexplained Variance Variation due to factors not in the model
Model Fit How well the model describes the data

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what R-Squared (R²) means and give an example of why it is important.

  2. In your own words, explain what Coefficient of Determination means and give an example of why it is important.

  3. In your own words, explain what Explained Variance means and give an example of why it is important.

  4. In your own words, explain what Unexplained Variance means and give an example of why it is important.

  5. In your own words, explain what Model Fit means and give an example of why it is important.

Summary

In this module, we explored R-Squared: Measuring Model Fit. We learned about r-squared (r²), coefficient of determination, explained variance, unexplained variance, model fit. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

5

Residual Analysis

Using residuals to check if the regression model is appropriate.

Key Concepts
Residual Residual Plot Random Scatter Heteroscedasticity Outlier

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Residual
  • Define and explain Residual Plot
  • Define and explain Random Scatter
  • Define and explain Heteroscedasticity
  • Define and explain Outlier
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Residuals (errors) are the differences between actual and predicted Y values. Analyzing residuals helps check if the linear model is appropriate. Residuals should be randomly scattered around zero with no pattern. Patterns in residuals suggest the model is missing something—perhaps the relationship is not linear.

In this module, we will explore the fascinating world of Residual Analysis. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Residual

What is Residual?

Definition: Difference: actual Y minus predicted Y

When experts study residual, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding residual helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Residual is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Residual Plot

What is Residual Plot?

Definition: Graph of residuals against X or predicted values

The concept of residual plot has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about residual plot, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about residual plot every day.

Key Point: Residual Plot is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Random Scatter

What is Random Scatter?

Definition: No pattern in residuals—good model fit

To fully appreciate random scatter, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of random scatter in different contexts around you.

Key Point: Random Scatter is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Heteroscedasticity

What is Heteroscedasticity?

Definition: Non-constant variance of residuals

Understanding heteroscedasticity helps us make sense of many processes that affect our daily lives. Experts use their knowledge of heteroscedasticity to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Heteroscedasticity is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Outlier

What is Outlier?

Definition: Point far from the regression line

The study of outlier reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Outlier is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: What Residuals Reveal

Plot residuals against X or predicted values. Look for: Random scatter (good—assumptions met). Curved pattern (bad—relationship is not linear). Funnel shape (bad—variance is not constant). Outliers (investigate—influential points). If residuals show patterns, consider transforming variables (log, square root), adding polynomial terms (X²), or using non-linear regression.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? Residual plots are so important that statistician John Tukey said "The greatest value of a picture is when it forces us to notice what we never expected to see"!


Key Concepts at a Glance

Concept Definition
Residual Difference: actual Y minus predicted Y
Residual Plot Graph of residuals against X or predicted values
Random Scatter No pattern in residuals—good model fit
Heteroscedasticity Non-constant variance of residuals
Outlier Point far from the regression line

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Residual means and give an example of why it is important.

  2. In your own words, explain what Residual Plot means and give an example of why it is important.

  3. In your own words, explain what Random Scatter means and give an example of why it is important.

  4. In your own words, explain what Heteroscedasticity means and give an example of why it is important.

  5. In your own words, explain what Outlier means and give an example of why it is important.

Summary

In this module, we explored Residual Analysis. We learned about residual, residual plot, random scatter, heteroscedasticity, outlier. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

6

Making Predictions

Using the regression equation to predict new values.

Key Concepts
Prediction Interpolation Extrapolation Prediction Interval Uncertainty

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Prediction
  • Define and explain Interpolation
  • Define and explain Extrapolation
  • Define and explain Prediction Interval
  • Define and explain Uncertainty
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Once we have the regression equation, we can predict Y for any value of X by plugging X into the equation. These predictions have uncertainty—we can calculate prediction intervals that capture this uncertainty. Predictions are most reliable within the range of observed X values; extrapolating beyond the data is risky.

In this module, we will explore the fascinating world of Making Predictions. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Prediction

What is Prediction?

Definition: Using the model to estimate Y for given X

When experts study prediction, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding prediction helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Prediction is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Interpolation

What is Interpolation?

Definition: Predicting within the range of observed data

The concept of interpolation has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about interpolation, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about interpolation every day.

Key Point: Interpolation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Extrapolation

What is Extrapolation?

Definition: Predicting beyond the range of observed data

To fully appreciate extrapolation, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of extrapolation in different contexts around you.

Key Point: Extrapolation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Prediction Interval

What is Prediction Interval?

Definition: Range likely to contain the actual Y value

Understanding prediction interval helps us make sense of many processes that affect our daily lives. Experts use their knowledge of prediction interval to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Prediction Interval is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Uncertainty

What is Uncertainty?

Definition: Imprecision in predictions due to model limitations

The study of uncertainty reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Uncertainty is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: Interpolation vs. Extrapolation

Interpolation: predicting within the range of X data. If X in data ranges from 10 to 50, predicting for X=30 is interpolation. Extrapolation: predicting outside the data range (X=5 or X=70). Extrapolation is dangerous because the relationship might change beyond observed data. A model of height vs. age for children cannot safely predict adult heights—the relationship changes.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? The 2008 financial crisis was partly caused by extrapolating housing models beyond their valid range—assuming prices would keep rising forever!


Key Concepts at a Glance

Concept Definition
Prediction Using the model to estimate Y for given X
Interpolation Predicting within the range of observed data
Extrapolation Predicting beyond the range of observed data
Prediction Interval Range likely to contain the actual Y value
Uncertainty Imprecision in predictions due to model limitations

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Prediction means and give an example of why it is important.

  2. In your own words, explain what Interpolation means and give an example of why it is important.

  3. In your own words, explain what Extrapolation means and give an example of why it is important.

  4. In your own words, explain what Prediction Interval means and give an example of why it is important.

  5. In your own words, explain what Uncertainty means and give an example of why it is important.

Summary

In this module, we explored Making Predictions. We learned about prediction, interpolation, extrapolation, prediction interval, uncertainty. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

7

Assumptions of Linear Regression

Understanding the conditions required for valid regression analysis.

Key Concepts
Linearity Independence Homoscedasticity Normality Model Validity

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Linearity
  • Define and explain Independence
  • Define and explain Homoscedasticity
  • Define and explain Normality
  • Define and explain Model Validity
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Linear regression relies on several assumptions. When these are violated, results may be misleading. The main assumptions are: linearity (relationship is a straight line), independence (observations are independent), homoscedasticity (constant variance of residuals), and normality (residuals are normally distributed).

In this module, we will explore the fascinating world of Assumptions of Linear Regression. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Linearity

What is Linearity?

Definition: Assumption that relationship is straight-line

When experts study linearity, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding linearity helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Linearity is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Independence

What is Independence?

Definition: Assumption that observations are not related

The concept of independence has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about independence, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about independence every day.

Key Point: Independence is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Homoscedasticity

What is Homoscedasticity?

Definition: Assumption of constant variance in residuals

To fully appreciate homoscedasticity, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of homoscedasticity in different contexts around you.

Key Point: Homoscedasticity is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Normality

What is Normality?

Definition: Assumption that residuals are normally distributed

Understanding normality helps us make sense of many processes that affect our daily lives. Experts use their knowledge of normality to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Normality is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Model Validity

What is Model Validity?

Definition: Whether the model is appropriate for the data

The study of model validity reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Model Validity is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: The LINE Assumptions

L-Linearity: The true relationship is linear. Check with scatter plot and residual plot. I-Independence: Residuals are independent (no patterns over time). Violated with time series data without proper modeling. N-Normality: Residuals are normally distributed. Check with histogram or Q-Q plot of residuals. Needed for valid inference. E-Equal variance: Residuals have constant spread (homoscedasticity). Check residual plot for funnel shapes.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? George Box famously said "All models are wrong, but some are useful." Assumptions are never perfectly met—the question is whether violations seriously affect results!


Key Concepts at a Glance

Concept Definition
Linearity Assumption that relationship is straight-line
Independence Assumption that observations are not related
Homoscedasticity Assumption of constant variance in residuals
Normality Assumption that residuals are normally distributed
Model Validity Whether the model is appropriate for the data

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Linearity means and give an example of why it is important.

  2. In your own words, explain what Independence means and give an example of why it is important.

  3. In your own words, explain what Homoscedasticity means and give an example of why it is important.

  4. In your own words, explain what Normality means and give an example of why it is important.

  5. In your own words, explain what Model Validity means and give an example of why it is important.

Summary

In this module, we explored Assumptions of Linear Regression. We learned about linearity, independence, homoscedasticity, normality, model validity. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

8

Correlation vs. Causation

Understanding why regression does not prove cause and effect.

Key Concepts
Correlation Causation Confounding Variable Spurious Correlation Randomized Experiment

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Correlation
  • Define and explain Causation
  • Define and explain Confounding Variable
  • Define and explain Spurious Correlation
  • Define and explain Randomized Experiment
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Regression shows that X and Y are related, but it does not prove that X causes Y. Ice cream sales and drownings are correlated (both increase in summer), but ice cream does not cause drowning—summer is the common cause. Establishing causation requires controlled experiments or careful analysis of confounding variables.

In this module, we will explore the fascinating world of Correlation vs. Causation. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Correlation

What is Correlation?

Definition: Statistical relationship between variables

When experts study correlation, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding correlation helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Correlation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Causation

What is Causation?

Definition: One variable directly causing change in another

The concept of causation has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about causation, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about causation every day.

Key Point: Causation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Confounding Variable

What is Confounding Variable?

Definition: Third variable affecting both X and Y

To fully appreciate confounding variable, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of confounding variable in different contexts around you.

Key Point: Confounding Variable is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Spurious Correlation

What is Spurious Correlation?

Definition: Correlation without causal relationship

Understanding spurious correlation helps us make sense of many processes that affect our daily lives. Experts use their knowledge of spurious correlation to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Spurious Correlation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Randomized Experiment

What is Randomized Experiment?

Definition: Study design that can establish causation

The study of randomized experiment reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Randomized Experiment is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: Confounding Variables

A confounding variable affects both X and Y, creating a false appearance of causation. Shoe size correlates with reading ability in children—but shoe size does not cause reading skill. Age is the confounder: older children have larger feet AND read better. To establish causation: use randomized experiments, control for confounders, check temporal order (cause precedes effect), and rule out alternative explanations.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? A famous spurious correlation: per capita cheese consumption correlates 0.95 with deaths by bedsheet tangling. Obviously, cheese does not cause bedsheet accidents!


Key Concepts at a Glance

Concept Definition
Correlation Statistical relationship between variables
Causation One variable directly causing change in another
Confounding Variable Third variable affecting both X and Y
Spurious Correlation Correlation without causal relationship
Randomized Experiment Study design that can establish causation

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Correlation means and give an example of why it is important.

  2. In your own words, explain what Causation means and give an example of why it is important.

  3. In your own words, explain what Confounding Variable means and give an example of why it is important.

  4. In your own words, explain what Spurious Correlation means and give an example of why it is important.

  5. In your own words, explain what Randomized Experiment means and give an example of why it is important.

Summary

In this module, we explored Correlation vs. Causation. We learned about correlation, causation, confounding variable, spurious correlation, randomized experiment. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

9

Multiple Regression Introduction

Understanding regression with multiple predictor variables.

Key Concepts
Multiple Regression Controlling For Partial Effect Predictor Variables Adjusted R-Squared

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Multiple Regression
  • Define and explain Controlling For
  • Define and explain Partial Effect
  • Define and explain Predictor Variables
  • Define and explain Adjusted R-Squared
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Simple regression uses one X to predict Y. Multiple regression uses multiple X variables: Y = a + b₁X₁ + b₂X₂ + ... + bₙXₙ. This allows controlling for other factors and often provides better predictions. For example, predicting house price from both size AND location AND age.

In this module, we will explore the fascinating world of Multiple Regression Introduction. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Multiple Regression

What is Multiple Regression?

Definition: Regression with multiple predictor variables

When experts study multiple regression, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding multiple regression helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Multiple Regression is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Controlling For

What is Controlling For?

Definition: Holding other variables constant

The concept of controlling for has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about controlling for, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about controlling for every day.

Key Point: Controlling For is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Partial Effect

What is Partial Effect?

Definition: Effect of one variable with others held constant

To fully appreciate partial effect, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of partial effect in different contexts around you.

Key Point: Partial Effect is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Predictor Variables

What is Predictor Variables?

Definition: The X variables used for prediction

Understanding predictor variables helps us make sense of many processes that affect our daily lives. Experts use their knowledge of predictor variables to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Predictor Variables is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Adjusted R-Squared

What is Adjusted R-Squared?

Definition: R² adjusted for number of predictors

The study of adjusted r-squared reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Adjusted R-Squared is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: Interpreting Multiple Regression Coefficients

In multiple regression, each coefficient shows the effect of that variable while holding others constant. If Price = 100000 + 200×Size + 50000×Location + (-1000×Age), then: Each square foot adds $200 (holding location and age constant). Being in a good location (coded 1 vs 0) adds $50,000. Each year of age reduces price by $1,000. This "controlling for" other variables helps isolate individual effects.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? Netflix uses multiple regression with thousands of variables to predict which shows you will like based on your viewing history!


Key Concepts at a Glance

Concept Definition
Multiple Regression Regression with multiple predictor variables
Controlling For Holding other variables constant
Partial Effect Effect of one variable with others held constant
Predictor Variables The X variables used for prediction
Adjusted R-Squared R² adjusted for number of predictors

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Multiple Regression means and give an example of why it is important.

  2. In your own words, explain what Controlling For means and give an example of why it is important.

  3. In your own words, explain what Partial Effect means and give an example of why it is important.

  4. In your own words, explain what Predictor Variables means and give an example of why it is important.

  5. In your own words, explain what Adjusted R-Squared means and give an example of why it is important.

Summary

In this module, we explored Multiple Regression Introduction. We learned about multiple regression, controlling for, partial effect, predictor variables, adjusted r-squared. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

10

Practical Applications

Applying regression analysis to real-world problems.

Key Concepts
Model Validation Overfitting Domain Knowledge Uncertainty Quantification Best Practices

Learning Objectives

By the end of this module, you will be able to:

  • Define and explain Model Validation
  • Define and explain Overfitting
  • Define and explain Domain Knowledge
  • Define and explain Uncertainty Quantification
  • Define and explain Best Practices
  • Apply these concepts to real-world examples and scenarios
  • Analyze and compare the key concepts presented in this module

Introduction

Regression is used everywhere: predicting sales, housing prices, patient outcomes, stock returns, crop yields, and more. The key is understanding what regression can and cannot do, checking assumptions, and interpreting results in context. Good regression analysis combines statistical technique with domain knowledge.

In this module, we will explore the fascinating world of Practical Applications. You will discover key concepts that form the foundation of this subject. Each concept builds on the previous one, so pay close attention and take notes as you go. By the end, you'll have a solid understanding of this important topic.

This topic is essential for understanding how the subject works and how experts organize their knowledge. Let's dive in and discover what makes this subject so important!


Model Validation

What is Model Validation?

Definition: Checking if model works on new data

When experts study model validation, they discover fascinating details about how systems work. This concept connects to many aspects of the subject that researchers investigate every day. Understanding model validation helps us see the bigger picture. Think about everyday examples to deepen your understanding — you might be surprised how often you encounter this concept in the world around you.

Key Point: Model Validation is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Overfitting

What is Overfitting?

Definition: Model fits training data but not new data

The concept of overfitting has been studied for many decades, leading to groundbreaking discoveries. Research in this area continues to advance our understanding at every scale. By learning about overfitting, you are building a strong foundation that will support your studies in more advanced topics. Experts around the world work to uncover new insights about overfitting every day.

Key Point: Overfitting is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Domain Knowledge

What is Domain Knowledge?

Definition: Understanding of the subject matter

To fully appreciate domain knowledge, it helps to consider how it works in real-world applications. This universal nature is what makes it such a fundamental concept in this field. As you learn more, try to identify examples of domain knowledge in different contexts around you.

Key Point: Domain Knowledge is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Uncertainty Quantification

What is Uncertainty Quantification?

Definition: Reporting confidence in predictions

Understanding uncertainty quantification helps us make sense of many processes that affect our daily lives. Experts use their knowledge of uncertainty quantification to solve problems, develop new solutions, and improve outcomes. This concept has practical applications that go far beyond the classroom.

Key Point: Uncertainty Quantification is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


Best Practices

What is Best Practices?

Definition: Recommended approaches for reliable analysis

The study of best practices reveals the elegant complexity of how things work. Each new discovery opens doors to understanding other aspects and how knowledge in this field has evolved over time. As you explore this concept, try to connect it with what you already know — you'll find that everything is interconnected in beautiful and surprising ways.

Key Point: Best Practices is a fundamental concept that you will encounter throughout your studies. Make sure you can explain it in your own words!


🔬 Deep Dive: Best Practices

Start with visualization: scatter plots reveal the relationship and potential problems. Check assumptions: use residual plots to verify linearity, constant variance, and normality. Consider multiple predictors: rarely does one variable fully explain another. Beware of overfitting: complex models may fit training data but fail on new data. Report uncertainty: include R², confidence intervals, and limitations. Do not confuse correlation with causation.

This is an advanced topic that goes beyond the core material, but understanding it will give you a deeper appreciation of the subject. Researchers continue to study this area, and new discoveries are being made all the time.

Did You Know? The first regression-based weather forecasts were made in the 1920s. Today's weather models use regression on millions of data points from satellites and sensors!


Key Concepts at a Glance

Concept Definition
Model Validation Checking if model works on new data
Overfitting Model fits training data but not new data
Domain Knowledge Understanding of the subject matter
Uncertainty Quantification Reporting confidence in predictions
Best Practices Recommended approaches for reliable analysis

Comprehension Questions

Test your understanding by answering these questions:

  1. In your own words, explain what Model Validation means and give an example of why it is important.

  2. In your own words, explain what Overfitting means and give an example of why it is important.

  3. In your own words, explain what Domain Knowledge means and give an example of why it is important.

  4. In your own words, explain what Uncertainty Quantification means and give an example of why it is important.

  5. In your own words, explain what Best Practices means and give an example of why it is important.

Summary

In this module, we explored Practical Applications. We learned about model validation, overfitting, domain knowledge, uncertainty quantification, best practices. Each of these concepts plays a crucial role in understanding the broader topic. Remember that these ideas are building blocks — each module connects to the next, helping you build a complete picture. Keep reviewing these concepts and you'll be well prepared for what comes next!

Ready to master Regression Analysis?

Get personalized AI tutoring with flashcards, quizzes, and interactive exercises in the Eludo app

Personalized learning
Interactive exercises
Offline access

Related Topics