05_Chapter 05 - Click to edit Master subtitle style 5. M...

Info iconThis preview shows pages 1–15. Sign up to view the full content.

View Full Document Right Arrow Icon
Click to edit Master subtitle style Ch 1 5. M ultiple Discriminant Analysis 11
Background image of page 1

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

View Full DocumentRight Arrow Icon
Ch 1 Decision Process 1. Research Objective 2. Research Design 3. Assumption Test 4. Estimating the Discriminant Model and Assessing Overall Fit 5. Interpretation 6. Validation 22
Background image of page 2
Ch 1 1. Research Objective Purpose Identify variables that can discriminate between two or more groups Examine the effects of the independent variables in the discriminant variate 33
Background image of page 3

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

View Full DocumentRight Arrow Icon
Ch 1 1. Research Objective Regression vs. Discriminant Analysis Regression Y = b1X1 + b2X2 + …. . Y: metric variable X: metric variable b: relative impact (significant or insignificant) of the independent variables (Xs) in predicting dependent variable (Y) Discriminant analysis Y (0/1) = b1X1 + b2X2 + …. . Y: non-metric variable 0: non-user 1: user X: metric variable b: relative impact (significant or insignificant) of the 44
Background image of page 4
Ch 1 55
Background image of page 5

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

View Full DocumentRight Arrow Icon
Ch 1 66
Background image of page 6
Ch 1 77
Background image of page 7

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

View Full DocumentRight Arrow Icon
Ch 1 88
Background image of page 8
Ch 1 2. Research Design Measurement Dependent: non-metric Independent: metric Sample Size Overall sample size Minimum observation-to-independent variable ratio 5 : 1 99
Background image of page 9

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

View Full DocumentRight Arrow Icon
Ch 1 2. Research Design Sample Size Sample size per category At least 20 observations per category Division of the Sample Analysis subsample Develop the discriminant function Holdout subsample Validate the discriminant function 50-50 Split done at the beginning not the end of the analysis 10
Background image of page 10
Ch 1 2. Research Design Data: HBAT 800 Chapters 5 & 6.sav Dependent: X1 (1 = less than 1year, 2 = 1 to 5 years, 3 = more than 5 years) Independent: X6 to X18 Sample size Analysis subsample: 400 Observation-to-independent variable ratio l 400:13 Observation per category l 400 / 3 Holdout subsample: 400 11
Background image of page 11

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

View Full DocumentRight Arrow Icon
Ch 1 3. Assumption Test Linearity Partial regression plots Visual inspection 12 Not met
Background image of page 12
Ch 1 3. Assumption Test Normality Normal probability plot Visual inspection 13 Y ^ Y Not met
Background image of page 13

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

View Full DocumentRight Arrow Icon
Ch 1 4. Estimation & Overall Fit Discriminant function Generate a conceptual “line” that separates the categories in the dependent variable # of functions = # of categories – 1 Dependent: X1 (1 = less than 1year, 2 = 1 to 5 years, 3 = more than 5 years)
Background image of page 14
Image of page 15
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 55

05_Chapter 05 - Click to edit Master subtitle style 5. M...

This preview shows document pages 1 - 15. Sign up to view the full document.

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