Analyzing Multivariate Data (with CD-ROM)

by Lattin, James; Carroll, Douglas; Green, Paul

• ISBN13: 9780534349745
• ISBN10: 0534349749
• Format: Hardcover
• Copyright: 2002-12-03
• Publisher: Cengage Learning

Summary

Part One: OVERVIEW. 1. Introduction. The Nature of Multivariate Data. Overview of Multivariate Methods. Format of Succeeding Chapters. 2. Vectors and Matrixes. Introduction. Definitions. Geometric Interpretation of Operations. Matrix Properties. Learning Summary. Exercises. Part Two: ANALYSIS OF INTERDEPENDENCE. 3. Regression Analysis. Introduction. Regression Analysis: How it Works. Sample Problem: Leslie Salt Property. Learning Summary. Exercises. 4. Principal Components Analysis. Introduction. Principal Components: How it Works. Sample Problem: Gross State Production. Questions Regarding the Application of Principal Components. Learning Summary. Exercises. 5. Exploratory Factor Analysis. Introduction. Exploratory Factor Analysis: How it Works. Sample Problem: Perceptions of Ready-to-Eat Cereals. Questions Regarding the Application of Factor Analysis. Learning Summary. Exercises. 6. Confirmatory Factor Analysis. Introduction. Confirmatory Factor Analysis: How Does it Work? Sample Problems. Questions Regarding the Application of Confirmatory Factor Analysis. Learning Summary. Exercises. 7. Multidimensional Scaling. Introduction. Metric MDS: How Does it Work? Non-Metric MDS: How Does it Work? Individual Differences Scaling: How Does It Work? Centroid Scaling: How Does it Work? A Note on Model Validation. Learning Summary. Exercises. 8. Clustering. Introduction. Objectives of Cluster Analysis. Measures of Distance, Dissimilarity, and Density. Agglomerative Clustering: How IT Works. Partitioning: How it Works. Sample Problem: Preference Segmentation. Questions Regarding the Application of Cluster Analysis. Learning Summary. Exercises. Part Three: ANALYSIS OF DEPENDENCE. 9. Canonical Correlation. Introduction. Canonical Correlation: How Does it Work? Sample Problem. Questions Regarding the Application of Canonical Correlation. Learning Summary. Exercises. 10. Structural Equation Models with Latent Variables. Introduction. Structural Equations with Latent Variables: How Does it Work? Sample Problem: Modeling the Adoption of Innovation. Questions Regarding the Application of Structural Equations with Latent Variables. Learning Summary. Exercises. 11. Analysis of Variance. Introduction. ANOLVA and ANCOVA: How Does it Work? Sample Problem: Test Marketing a New Product. Multiple Analysis of Variance (MANOVA): How Does it Work. Sample Problem: Testing Advertising Message Strategy. Questions Regarding the Application of MANOVA and MANCOVA. Learning Summary. Exercises. 12. Discriminant Analysis. Introduction. Two-Group Discriminant Analysis: How Does it Work? Sample Problem: Book Club Data. Questions Regarding the Application of Two-Group Discriminant Analysis. Multiple Discriminant Analysis: How Does it Work? Sample Problem: Real Estate. Questions Regarding the Application of Multiple Discriminant Analysis. Learning Summary. Exercises. 13. Logit Choice Models. Introduction. Binary Logit Model: How Does it Work? Sample Problem: Books Direct. Multinomial Logit Model: How Does it Work? Sample Problem: Brand Choice. Questions Regarding the Application of Logit Choice Models. Learning Summary. Exercises.

Table of Contents

Preface	xix
PART I Overview	1	(80)
Introduction	3	(16)
The Nature of Multivariate Data	4	(5)
Some Definitions	4	(1)
Observations and Data	4	(1)
Levels of Measurement	5	(4)
Overview of Multivariate Methods	9	(8)
Principal Components	9	(2)
Factor Analysis	11	(1)
Multidimensional Scaling	11	(1)
Clustering	12	(1)
Canonical Correlation	13	(1)
Structural Equation Models with Latent Variables	14	(1)
Analysis of Variance	15	(1)
Discriminant Analysis	16	(1)
Logit Choice Models	16	(1)
Format of Succeeding Chapters	17	(2)
Selected Readings	18	(1)
General	18	(1)
Data and Measurement	18	(1)
Vectors and Matrices	19	(19)
Introduction	19	(1)
Definitions	20	(5)
Vectors	20	(1)
Matrices	20	(1)
Coordinate Systems	21	(4)
Geometric Interpretation of Operations	25	(7)
Scalar Multiplication: Scaling	25	(1)
Vector Multiplication: Projection	26	(2)
Matrix Multiplication	28	(4)
Matrix Properties	32	(3)
Singular Value Decomposition	32	(1)
Cross-Product Matrix	32	(3)
Learning Summary	35	(3)
Selected Readings	36	(1)
General	36	(1)
Exercises	36	(2)
Regression Analysis	38	(43)
Introduction	38	(1)
Regression Analysis: How It Works	39	(8)
Intuition	39	(7)
Mechanics	46	(1)
Sample Problem: Leslie Salt Property	47	(3)
Questions Regarding the Application of Regression Analysis	50	(25)
How Good Is the Fit?	53	(1)
Is It Significant?	54	(2)
Detecting Problems with the Model	56	(9)
Comparing Models	65	(3)
Forecasting	68	(3)
Model Validation	71	(4)
Learning Summary	75	(6)
Selected Readings	77	(1)
General	77	(1)
Outliers and Regression Diagnostics	77	(1)
Resampling and Model Validation	78	(1)
Exercises	78	(3)
PART II Analysis of Interdependence	81	(230)
Principal Components Analysis	83	(44)
Introduction	83	(8)
Potential Applications	84	(7)
Principal Components: How It Works	91	(10)
Intuition	91	(6)
Mechanics	97	(4)
Sample Problem: Gross State Product	101	(8)
Data	101	(4)
Results	105	(4)
Questions Regarding the Application of Principal Components	109	(17)
When Is It Appropriate to Use Principal Components?	109	(2)
How Should the Data Be Scaled?	111	(1)
How Many Components Should Be Retained?	112	(5)
How to Assess the Validity of the Solution?	117	(9)
Learning Summary	126	(1)
Selected Readings	123	(1)
General	123	(1)
How Many Components?	123	(1)
Jackknife and Bootstrapping	123	(1)
Exercises	123	(4)
Exploratory Factor Analysis	127	(44)
Introduction	127	(4)
Potential Applications	128	(3)
Exploratory Factor Analysis: How It Works	131	(16)
Intuition	131	(10)
Mechanics	141	(6)
Sample Problem: Perceptions of Ready-to-Eat Cereals	147	(6)
Data	147	(1)
Results	148	(5)
Questions Regarding the Application of Factor Analysis	153	(10)
Can I Obtain a Solution with Correlated Factors?	153	(3)
How Can I Use the Results in Subsequent Analyses?	156	(3)
How Can I Assess the Validity of the Factor Structure?	159	(4)
Learning Summary	163	(8)
Selected Readings	165	(1)
General	165	(1)
Rotation	166	(1)
Exercises	166	(5)
Confirmatory Factor Analysis	171	(35)
Introduction	171	(4)
Potential Applications	172	(3)
Confirmatory Factor Analysis: How It Works	175	(12)
Intuition	175	(9)
Mechanics	184	(3)
Sample Problems	187	(1)
Questions Regarding the Application of Confirmatory Factor Analysis	187	(12)
How Do I Assess the Reliability of an Index?	187	(3)
How Do I Compare Alternative Models?	190	(3)
Going Beyond Simple Factor Structure	193	(5)
Note on Model Validation	198	(1)
Learning Summary	199	(7)
Selected Readings	201	(1)
General	201	(1)
Reliability	201	(1)
Multitrait-Multimethod Models	202	(1)
Exercises	202	(4)
Multidimensional Scaling	206	(58)
Introduction	206	(5)
Potential Applications	208	(3)
Classical Metric MDS: How It Works	211	(7)
Intuition	212	(1)
Mechanics	213	(3)
Sample Problem: Mapping Cities from Intercity Distances	216	(2)
Nonmetric MDS: How It Works	218	(17)
Intuition	219	(6)
Mechanics	225	(1)
Sample Problem: Perceptual Map of Automobiles	225	(2)
Questions Regarding the Application of Nonmetric MDS	227	(8)
The INDSCAL Model and Method for Individual Differences Scaling: How It Works	235	(9)
Intuition	235	(3)
Mechanics	238	(1)
Sample Problem: Perceptions of Breakfast Foods	239	(5)
Multidimensional Analysis of Preference: How It Works	244	(8)
Intuition	245	(2)
Mechanics	247	(1)
Sample Problem: Movie Critic Data	247	(5)
Learning Summary	252	(3)
Selected Readings	255	(9)
General	255	(1)
Metric MDS	255	(1)
Nonmetric MDS	255	(1)
Individual Differences Scaling	256	(1)
Unfolding	256	(1)
Multidimensional Analysis of Preference	256	(1)
Exercises	256	(8)
Cluster Analysis	264	(47)
Introduction	264	(7)
Potential Applications	266	(5)
Objectives of Cluster Analysis	271	(2)
Measures of Distance, Dissimilarity, and Density	273	(6)
Distance Measures	273	(6)
Agglomerative Clustering: How It Works	279	(9)
Intuition	279	(5)
Example	284	(4)
Partitioning: How It Works	288	(6)
Intuition	288	(5)
Example	293	(1)
Sample Problem: Preference Segmentation	294	(3)
Questions Regarding the Application of Cluster Analysis	297	(6)
How Should the Data Be Scaled?	297	(1)
Validation	298	(4)
A Further Note on the Number of Clusters	302	(1)
Learning Summary	303	(8)
Selected Readings	305	(1)
General	305	(1)
Single, Complete, Average Linkage	306	(1)
Ward's Method	306	(1)
Kth-Nearest Neighbor	306	(1)
K-Means	306	(1)
Assessment and Validation	306	(1)
Exercises	306	(5)
PART III Analysis of Dependence	311	(215)
Canonical Correlation	313	(39)
Introduction	313	(4)
Potential Applications	315	(2)
Canonical Correlation: How It Works	317	(10)
Intuition	317	(5)
Mechanics	322	(5)
Sample Problem	327	(5)
Questions Regarding the Application of Canonical Correlation	332	(10)
Is the Relationship between the X's and the Y's Significant?	332	(3)
How Many Pairs of Canonical Variates Are Significant?	335	(2)
How Do I Assess the Validity of the Results from a Canonical Correlation Analysis?	337	(5)
Learning Summary	342	(10)
Selected Readings	344	(1)
General	344	(1)
Statistical Tests	345	(1)
Redundancy	345	(1)
Exercises	345	(7)
Structural Equation Models with Latent Variables	352	(34)
Introduction	352	(3)
Potential Applications	353	(2)
Structural Equation Models with Latent Variables: How It Works	355	(10)
Intuition	355	(9)
Mechanics	364	(1)
Sample Problem: Modeling the Adoption of Innovation	365	(5)
Data	365	(3)
Results	368	(2)
Questions Regarding the Application of Structural Equations with Latent Variables	370	(11)
Model Diagnostics	370	(3)
Testing for Interactions	373	(7)
Model Validation	380	(1)
Learning Summary	381	(5)
Selected Readings	382	(1)
General	382	(1)
MIMIC Models/Relationship to Canonical Correlation	383	(1)
Interaction Effects	383	(1)
Exercises	383	(3)
Analysis of Variance	386	(40)
Introduction	386	(3)
Potential Applications	387	(2)
Anova/Ancova: How It Works	389	(16)
Intuition: Anova	389	(7)
Intuition: Ancova	396	(5)
Mechanics	401	(4)
Sample Problem: Test Marketing a New Product	405	(4)
Testing the Effects of Price and Advertising (Anova)	405	(2)
Controlling for Store Volume (Ancova)	407	(2)
Multiple Analysis of Variance (Manova): How It Works	409	(3)
Intuition	409	(3)
Sample Problem: Testing Advertising Message Strategy	412	(3)
Questions Regarding the Application of Anova	415	(5)
Testing Specific Contrasts in Anova	415	(1)
Testing for Equal Within-Group Slopes in Ancova	416	(1)
Using Manova for Repeated Measures Designs	417	(3)
Learning Summary	420	(6)
Selected Readings	422	(1)
General	422	(1)
Ancova	422	(1)
Test Statistics	422	(1)
Exercises	422	(4)
Discriminant Analysis	426	(48)
Introduction	426	(2)
Potential Applications	427	(1)
Two-Group Discriminant Analysis: How It Works	428	(11)
Intuition	428	(6)
Mechanics	434	(5)
Sample Problem: Books by Mail	439	(3)
Data	439	(1)
Results	439	(3)
Questions Regarding the Application of Two-Group Discriminant Analysis	442	(14)
Test for Equality of Covariance Matrices	442	(4)
How Do I Test for a Significant Difference between the Two-Group Centroids?	446	(1)
How Do I Assess the Goodness of Fit of the Discriminant Function?	447	(5)
How Do I Use the Discriminant Function for Prediction?	452	(4)
Multiple Discriminant Analysis: How It Works	456	(5)
Intuition	456	(3)
Mechanics	459	(2)
Sample Problem: Real Estate	461	(4)
Data	461	(1)
Results	461	(4)
Questions Regarding the Application of Multiple Discriminant Analysis	465	(1)
How Do I Test for a Significant Difference across Group Means?	465	(1)
How Do I Determine the Number of Discriminant Functions that Are Significant?	466	(1)
Learning Summary	466	(8)
Selected Readings	469	(1)
General	469	(1)
Tests	469	(1)
Goodness of Fit/Validation	469	(1)
Exercises	469	(5)
Logit Choice Models	474	(52)
Introduction	474	(3)
Potential Applications	475	(2)
Binary Logit Model: How It Works	477	(10)
Intuition	477	(7)
Properties of the Logit Model	484	(3)
Sample Problem: Books by Mail	487	(3)
Multinomial Logit Model: How It Works	490	(5)
Intuition	490	(4)
Properties of the Model	494	(1)
Sample Problem: Brand Choice	495	(3)
Questions Regarding the Application of Logit Choice Models	498	(19)
Accounting for Heterogeneity in Cross-Sectional Models	498	(11)
Circumventing IIA: The Nested Logit Model	509	(8)
Model Validation	517	(1)
Learning Summary	517	(9)
Selected Readings	519	(1)
General	519	(1)
Accounting for Heterogeneity	520	(1)
IIA/Nested Logit	520	(1)
Exercises	520	(6)
Statistical Tables	526	(8)
Bibliography	534	(11)
Index	545