Class Notes (837,484)
MGSC 372 (10)
Lecture 3

# MGSC 372 Lecture 3: Fall 2016 Semester Notes 3 Premium

8 Pages
31 Views

School
Department
Management Science
Course
MGSC 372
Professor
Brian Smith
Semester
Fall

Description
4.185 4.589 π β€ π π π \$65.69 β€ π β€π\$98.40 Simple Linear Regression Review Simple Linear Regression Simple linear regression analysis is used to analyze the nature of the relationship between two variables. The dependent (response) variable is designated by π and the independent (predictor) variable is designated by π. For a given independent variable, there may be many values of the dependent variable. The decision regarding which variable to designate π and which variable to designate π must be based upon theory, knowledge of the subject matter, and the objectives of the analysis. The relationship between the two variables is estimated and then used to make predictions for π. Scatter Diagram A scatter diagram is a graph showing the shape and direction of the underlying relationship between the independent variable π and the dependent variable π. Observations are plotted in pairs (π₯,π¦) with one variable plotted on each axis. Linear Relationships Between Two Variables Intercept and Slope The relationship between the two variables is described by a straight line mode in general form: True regression line: π = π½ 0 π½ π 1 π or πΈ π = π½ + π½ π0 1 Estimatedregression line: Μ Μ Μ π = π½ +0π½ π 1 Parameter Estimation π½0is a point estimation of π½0 Μ π½1is a point estimation of π½1 We note that π½ and π½ are variables while π½ and π½ are constants. 0 1 0 1 Simple Linear Regression Model Definitions of Terms π = the independent (predictor) variable π = the dependent (response) variable π½0= the true π-intercept π½ = the true slope 1 π = the error term Μ π½0= the estimated π-intercept π½ = the estimated slope 1 Simple Linear Regression Model Assumptions 1. In Simple Linear Regression, we have the assumption of linearity. 2. For each value of π the π values are normally distributed. 3. For each value of π the variance of the πvalues is the same (homoscedasticity). 4. Independence (independent sample of π are chosen for different values oπ i.e. error terms are not correlated). Intercept and Slope The π-intercept π½0is the point on the π-axis where the true regression line crosses and is the average value of π when π = 0. The slope of the true regression line1π½ represents the average change in π when π is increased by one unit. π½0and π½ 1re called the parameters of the regression line. Residual Error The difference between an observed value π and an estimated π is called a residual. SSE - Sum of Squares Error 2 2 πππΈ = βπ = π π¦ β π¦ π Μπ) SSE represents the sum of the squared deviations between the observed π-values in the data set and the π-values predicted by the estimated regression line. This is the amountof variation in π that is not explained by the regression line. Μ Μ Note: The Least Squares regression line is the line that has an intercep0 π½ and slope1π½ that will minimize SSE. Minimizing SSE To find the line that best fits the points in the scatter diagram, we minimize the quantity: πππΈ = β(π β π) = β(π β π½ β π½ π) Μ Μ 2 π π π 0 1 Μ Μ We note that πππΈ = π(π½ ,π½ 0. W1 obtain the two partial derivatives: πΏ(πππΈ) πΏ(πππΈ) πΏπ½Μ and πΏπ½ 0 1 And solve the equations: πΏ(πππΈ) = 0 and πΏ(πππΈ) = 0 πΏπ½Μ0 πΏπ½Μ1 Least Squares Estimates of Regression Parameters βπ₯π¦ β ππ₯Μπ¦ Μ π½1= βπ₯ β ππ₯Μ 2 π½0= π¦ Μ β π½ 1Μ Interpretation of Regression Coefficients The regression equation is: π = 7.905 + 0.715π π½1= 0.715 implies that, on average, a one unit increase in π will result in an increase of 0.715 in π, i.e. if advertising increases by \$1000 then profit will increase, on average, by \$715. π½ = 7.905 implies that the average profit in stores with no advertising budget will be \$7905. 0 Extrapolation The interpretation of π½ 0 7.905 is not reliable. The problem is that we are making a claim about a value of π for which we have no experimental evidence. All of our experimental data is for values of π in the range \$3000 to \$7000. Therefore we cannot make a reliable claim about the relationship between π and π when π = 0. This is called extrapolation. Point Estimates The regression equation can be used to predict a value of π based on a given value of π by substituting the π-value into the regression line. Example Estimate the profit of a store which spends \$3500 on advertising. Let π = 3.5 Then π = 7.905 + 0.715 3.5 = 10.4 (i.e. \$10400) Caution: Do not use the regression line to predict π with values of the independent variable significantly beyond the range of those represented in the sample. The nature of the relationship outside the range of π-values represented in the sample may not be linear and extrapolation may lead to false conclusions. Partitioning Total Deviation Μ Total deviation = π π π Unexplained deviation = π β π Μπ Explained deviation = π βππ Μ Μ Μ Μ Μ ππβ π = (π β π) + ππ β π)π Total deviation = Unexplained deviation + Explained deviation Sum of Squares We can compute sums of squares in regression analysis and construct an analysis of variance (ANOVA) table for the regression. Partitioning Sums of Squares It can be shown that:
More Less

Related notes for MGSC 372
Me

OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Just a few more details

So we can recommend you notes for your school.