M670_9 (Simple Regression)

M670_9 (Simple Regression) - SimpleLinearRegression k MGMT...

Info iconThis preview shows pages 1–16. Sign up to view the full content.

View Full Document Right Arrow Icon
  1 Simple Linear Regression k   MGMT 670: Business Analytics Krannert Graduate School of Management Purdue University
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
  2 § Describe the causal relationship between a  response  (or  dependent) variable and at least one  explanatory  (or  independent) variable. § Used for prediction e.g., sales vs. promotion activities § Correlation analysis  Measures the association between numerical  variables Not used for prediction e.g., German mark and Japanese yen Regression Models
Background image of page 2
  3 1. Define problem or question 2. Specify model 3. Collect data 4. Do descriptive data analysis 5. Estimate unknown parameters 6. Evaluate model 7. Implementation: Prediction,    Regression Modeling Steps
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
  4 Step 1: Define Problem § Most critical step § What are the objectives of building the model? § Who will use the model? § Are resources available (data etc.)? § How will the results be implemented? Example:   Develop a model to explain the variations in sales by advertising and promotional activities.
Background image of page 4
  5 Advertising Sales Advertising Sales Advertising Sales Advertising Sales Step 2:  Specify Model: What is more logical?
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
  6 Simple Linear Regression Models § Widely used for Trend Analysis § One dependent (response) variable § One independent (explanatory) variable Y Y   = b 0 + 1 X X b1 = Slope b0 = Y-intercept
Background image of page 6
  7 Visualizing the Linear Regression Model  … ε 1 β 0 β 0
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
  8 Estimated model does not match the true model …  House price versus # of Bathrooms 0 50000 100000 150000 200000 250000 300000 350000 400000 0 1 2 3 4 5 # of Bathrooms House price Actual Data Best Model Fit True Model
Background image of page 8
  9 Example: Pharmex Drugs § Collected data from 50 randomly selected regions Promote : Pharmex’s promotional expenditures as a percentage of  those of the leading competitor Sales : Pharmex’s sales as a percentage of those of the leading  competitor Region Promote Sales 1 77 85 2 110 103 3 110 102 4 93 109 5 90 85 6 95 103 7 100 110 8 85 86 9 96 92 10 83 87 11 88 99 12 94 101 13 104 109 14 89 81
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
  10 § Descriptive statistics § Correlation Coefficient § Scatter Plot Step 4  Descriptive Data Analysis
Background image of page 10
  11 Descriptive Statistics Descriptive Statistics: Promote, Sales   Variable N N* Mean SE Mean StDev Minimum Q1 Median Q3 Promote 50 0 97.88 1.24 8.74 77.00 92.75 96.50 103.00 Sales 50 0 99.74 1.40 9.89 81.00 92.00 101.00 108.00 Variable Maximum Promote 117.00 Sales 119.00 Correlations: Promote, Sales   Pearson correlation of Promote and Sales = 0.673 P-Value = 0.000
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
  12 Y X r = 0 Y X r = 0 Correlation Coefficients § Linear association between two variables Y X r = -1 Y X r = 1
Background image of page 12
  13 Example: Pharmex Drugs -Scatter Diagram
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
  14 Step 5  Estimate Unknown Parameters § Least Squares Method Minimize the sum of squared errors i = 1 n ( ) y i - y ^ i 2   Observed value x Y e 1 e 2 e 3 e 4 e 5 Predicted value Prediction Equation
Background image of page 14
Y X Why Squares? i
Background image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 16
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/17/2011 for the course MGMT 670 taught by Professor Tawarmalani during the Spring '11 term at Purdue University-West Lafayette.

Page1 / 81

M670_9 (Simple Regression) - SimpleLinearRegression k MGMT...

This preview shows document pages 1 - 16. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online