Simple Linear Regression: Theory and Estimation

College Depth 82 in the knowledge graph I know this Set as goal
Unlocks 2 downstream topics
linear-regression

Core Idea

Fit Y=β₀+β₁X+ε by minimizing Σε². Least squares: β₁=Cov(X,Y)/Var(X)=r(s_Y/s_X), β₀=Ȳ−β₁X̄. Under normality, LS is MLE. R²=correlation² is proportion of Y variance explained. Residuals ê_i=y_i−ŷ_i should be random.

Explainer

You already know that covariance and correlation measure how two variables move together. Simple linear regression takes that relationship and converts it into a predictive machine: given X, what is our best guess for Y? The model posits a straight line Y = β₀ + β₁X + ε, where ε represents random noise. The question becomes: which line fits best?

Ordinary least squares (OLS) answers that by minimizing the sum of squared residuals — the vertical distances between each observed point and the proposed line. Squaring the errors penalizes large misses more than small ones, making the solution unique and analytically tractable. Taking derivatives and setting them to zero yields the formulas: β₁ = Cov(X,Y)/Var(X) and β₀ = Ȳ − β₁X̄. Notice the slope formula: it is covariance (how much X and Y move together) scaled by variance (how spread-out X is). If X and Y are unrelated, Cov = 0, so β₁ = 0 — a flat line that ignores X entirely.

The equivalent form β₁ = r(sY/sX) gives a second interpretation. The correlation r captures the direction and strength of the relationship; the ratio sY/sX rescales it from correlation units into the actual units of Y per unit of X. This is why two datasets can have the same correlation but very different slopes — the slopes also depend on the relative spread of the variables.

— the coefficient of determination — measures how much of Y's total variation the model explains. It equals r² = 1 − SSRes/SSTotal, ranging from 0 (the line explains nothing beyond the mean) to 1 (perfect fit). Since R² is the square of the correlation, all the intuition you built about correlation directly transfers. After fitting, always inspect the residuals ê_i = y_i − ŷ_i. If the model is correctly specified, residuals should look like random noise: no pattern, no fan shape, no curve. Any structure in the residuals signals a problem — the relationship may be nonlinear, or the variance may change with X — and points toward the regression diagnostics you will study next.

Practice Questions 5 questions

Prerequisite Chain

Counting to 10Counting to 20Understanding ZeroThe Number ZeroCounting to FiveOne-to-One CorrespondenceCombining Small Groups Within 5Addition Within 10Addition Within 20Two-Digit Addition Without RegroupingTwo-Digit Addition with RegroupingAddition Within 100Repeated Addition as MultiplicationMultiplication Facts Within 100Division as Equal SharingDivision as Grouping (Measurement Division)Division: Grouping (Repeated Subtraction) ModelDivision: Fair Sharing ModelDivision as Equal SharingDivision as GroupingBasic Division FactsDivision Facts Within 100Two-Digit by One-Digit DivisionDivision with RemaindersRemainders and Quotients in DivisionDivision Word ProblemsIntroduction to Long DivisionFactors and MultiplesPrime and Composite NumbersEquivalent FractionsRelating Fractions and DecimalsDecimal Place ValueReading and Writing DecimalsComparing and Ordering DecimalsAdding and Subtracting DecimalsMultiplying DecimalsDividing DecimalsDividing FractionsMixed Number ArithmeticOrder of OperationsInteger Order of OperationsVariable ExpressionsCombining Like TermsOne-Step EquationsTwo-Step EquationsSolving Multi-Step EquationsEquations with Variables on Both SidesAngle Pairs: Complementary, Supplementary, and VerticalParallel Lines and TransversalsCorresponding AnglesAlternate Interior AnglesTriangle Angle Sum TheoremExterior Angle TheoremTriangle Inequality TheoremSimilar Triangles: AA SimilaritySimilar Triangles: SSS and SAS SimilarityProportions in Similar TrianglesRight Triangle Trigonometry IntroductionTrigonometric Ratios ReviewRadian MeasureConverting Between Degrees and RadiansThe Unit CircleGraphing Sine and CosineGraphing Tangent and Reciprocal Trigonometric FunctionsDerivatives of Trigonometric FunctionsAntiderivativesIndefinite IntegralsBasic Integration RulesRiemann SumsDefinite Integral DefinitionProbability Density Functions and Continuous DistributionsCumulative Distribution FunctionsContinuous Random VariablesNormal DistributionCentral Limit TheoremConfidence Intervals for MeansZ-Tests and T-Tests for MeansOne-Sample Z-Test for MeansOne-Sample and Two-Sample T-TestsInference in Linear RegressionPrediction Intervals in RegressionLinear Regression BasicsSimple Linear Regression: Theory and Estimation

Longest path: 83 steps · 411 total prerequisite topics

Prerequisites (3)

Leads To (2)