m

Business Analytics

Methods, Models, and Decisions

James R. Evans University of Cincinnati

THIRD EDITION

fl Pearson
Contents

Preface xvii
About the Author xxv
Credits xxvii

Part 1: Foundations of Business Analytics

Chapter 1: Introduction to Business Analytics 1
Learning Objectives 1
What is Business Analytics? 3
Using Business Analytics 4 • Impacts and Challenges 5
Evolution of Business Analytics 6
Analytic Foundations 6 • Modern Business Analytics 7 • Software Support
and Spreadsheet Technology 9
Analytics in Practice: Social Media Analytics 10
Descriptive, Predictive, and Prescriptive Analytics 11
Analytics in Practice: Analytics in the Home Lending and Mortgage Industry 13
Data for Business Analytics 14
Big Data 16 • Data Reliability and Validity 16
Models in Business Analytics 17
Descriptive Models 19 • Predictive Models 21 • Prescriptive Models 22 •
Model Assumptions 23 • Uncertainty and Risk 25
Problem Solving with Analytics 26
Recognizing a Problem 26 • Defining the Problem 26 • Structuring the
Problem 27 • Analyzing the Problem 27 • Interpreting Results and Making a
Decision 27 • Implementing the Solution 27
Analytics in Practice: Developing Effective Analytical Tools at Hewlett-Packard 28
Key Terms 29 * Chapter 1 Technology Help 29 • Problems and Exercises 29 •
Case: Performance Lawn Equipment 31
Appendix A1: Basic Excel Skills 33
Excel Formulas and Addressing 34
Copying Formulas 35
Useful Excel Tips 35
Excel Functions 36
Basic Excel Functions 36 • Functions for Specific Applications 37 • Insert
Function 38 • Date and Time Functions 39
Miscellaneous Excel Functions and Tools 40
Range Names 40 • VALUE Function 43 • Paste
Special 43 • Concatenation 44 • Error Values 44
Problems and Exercises 45
vii
Chapter 2: Database Analytics 47
Learning Objectives 47
Data Sets and Databases 49
Using Range Names in Databases 50
Analytics in Practice: Using Big Data to Monitor Water Usage in Cary,
North Carolina 51
Data Queries: Tables, Sorting, and Filtering 51
Sorting Data in Excel 52 • Pareto Analysis 53 • Filtering Data 54 •
Database Functions 56
Logical Functions 59
Lookup Functions for Database Queries 61
Excel Template Design 64
Data Validation Tools 65 • Form Controls 67
PivotTables 70
PivotTable Customization 72 • Slicers 75
Key Terms 76 • Chapter 2 Technology Help 76 • Problems and Exercises 77 •
Case: People 's choice Bank 81 • Case: Drout Advertising Research Project 82
Part 2: Descriptive Analytics
Chapter 3: Data Visualization 85
Learning Objectives 85
The Value of Data Visualization 86
Tools and Software for Data Visualization 88
Analytics in Practice: Data Visualization for the New York City Police Depnrünent's
Domain Awareness System 88
Creating Charts in Microsoft Excel 88
Column and Bar Charts 89 • Data Label and Data Table Chart Options 90 •
Line Charts 91 • Pie Charts 92 • Area Charts 93 • Scatter Charts
and Orbit Charts 94 • Bubble Charts 95 • Combination Charts 96 •
Radar Charts 97 • Stock Charts 97 • Charts from PivotTables 97 •
Geographie Data 98
Other Excel Data Visualization Tools 98
Data Bars 98 • ColorScales 99 • Icon Sets 100 • Sparklines 101
Dashboards 103
Analytics in Practice: Driving Business Transformation with IBM Business
Analytics 104
Key Terms 105 • Chapter 3 Technology Help 105 • Problems and Exercises 106 •
Case: Performance Lawn Equipment 107
Appendix A3: Additional Tools for Data Visualization 108
Hierarchy Charts 108
PivotCharts 110
Tableau 111
Problems and Exercises 113
Chapter 4: Descriptive Statistics 115
Learning Objectives 115
Analytics in Practice: Applications of Statistics in Health care 117
 Contents ix

Metrics and Data Classification 118

Frequency Distributions and Histograms 120
Frequency Distributions for Categorical Data 120 • Relative Frequency
Distributions 121 • Frequency Distributions for Numerical Data 122 • Grouped
Frequency Distributions 123 • Cumulative Relative Frequency Distributions 126 •
Constructing Frequency Distributions Using PivotTables 127
Percentiles and Quartiles 129
Cross-Tabulations 130
Descriptive Statistical Measures 132
Populations and Samples 132 • Statistical Notation 133 • Measures of
Location: Mean, Median, Mode, and Midrange 133 • Using Measures of Location
in Business Decisions 135 • Measures of Dispersion: Range, Interquartile
Range, Variance, and Standard Deviation 137 • Chebyshev's Theorem and the
Empirical Rules 140 • Standardized Values (Z-Scores) 142 • Coefficient of
Variation 143 • Measures of Shape 144 • Excel Descriptive Statistics Tool 146
Computing Descriptive Statistics for Frequency Distributions 147
Descriptive Statistics for Categorical Data: The Proportion 149
Statistics in PivotTables 150
Measures of Association 151
Covariance 152 • Correlation 153 • Excel Correlation Tool 155
Outliers 156
Using Descriptive Statistics to Analyze Survey Data 158
Statistical Thinking in Business Decisions 159
Variability in Samples 160
Analytics in Practice: Applying Statistical Thinking to Detecting Financial Problems 162
Key Terms 163 • Chapter 4 Technology Help 164 • Problems and Exercises 165 *
Case: Drout Advertising Research Project 170 • Case: Performance Lawn Equipment 170
Appendix A4: Additional Charts for Descriptive Statistics in Excel for Windows 171

Chapter 5: Probability Distributions and Data Modeling 173

Learning Objectives 173
Basic Concepts of Probability 175
Experiments and Sample Spaces 175 • Combinations and Permutations 175 •
Probability Definitions 177 • Probability Rules and Formulas 179 • Joint and
Marginal Probability 180 • Conditional Probability 182
Random Variables and Probability Distributions 185
Discrete Probability Distributions 187
Expected Value of a Discrete Random Variable 188 • Using Expected Value in
Making Decisions 189 • Variance of a Discrete Random Variable 191 • Bemoulli
Distribution 191 • Binomial Distribution 192 • Poisson Distribution 193
Analytics in Practice: Using the Poisson Distribution for Modeling Bids on
Priceline 195
Continuous Probability Distributions 196
Properties of Probability Density Functions 196 • Uniform Distribution 197 •
Normal Distribution 199 • The NORM.INV Function 200 • Standard Normal
Distribution 201 • Using Standard Normal Distribution Tables 202 • Exponential
Distribution 203 • Triangulär Distribution 204
X Contents

Data Modeling and Distribution Eitting 205

Goodness of Fit: Testing for Normality of an Empirical Distribution 207 •
Chi-Square Goodness of Fit Test 208
Analytics in Practice: The value of Good Data Modeling in Advertising 209
Key Terms 210 * Chapter 5 Technology Help 210 • Problems and Exercises 211 *
Case: Performance Lawn Equipment 217
Chapter 6: Sampling and Estimation 219
Leaming Objectives 219
Statistical Sampling 220
Sampling Methods 221
Analytics in Practice: Using Sampling Techniques to lmprove Distribution 223
Estimating Population Parameters 224
Unbiased Estimators 224 • Errors in Point Estimation 225 • Understanding
Sampling Error 226
Sampling Distributions 228
Sampling Distribution of the Mean 228 • Applying the Sampling Distribution of the
Mean 229
Interval Estimates 229
Confidence Intervals 230 • Confidence Interval for the Mean with Known
Population Standard Deviation 231 • The (-Distribution 232 • Confidence
Interval for the Mean with Unknown Population Standard Deviation 233 •
Confidence Interval for a Proportion 233 • Additional Types of Confidence
Intervals 235
Using Confidence Intervals for Decision Making 235
Data Visualization for Confidence Interval Comparison 236
Prediction Intervals 237
Confidence Intervals and Sample Size 238
Key Terms 240 • Chapter 6 Technology Help 240 • Problems and Exercises 241 •
Case: Drout Advertising Research Project 244 • Case: Performance Lawn Equipment 244
Chapter 7: Statistical Inference 247
Leaming Objectives 247
Hypothesis Testing 248
Hypothesis-Testing Procedure 249
One-Sample Hypothesis Tests 249
Understanding Potential Errors in Hypothesis Testing 250 • Selecting the Test
Statistic 251 • Finding Critical Values and Drawing a Conclusion 252 • Two-
Tailed Test of Hypothesis for the Mean 254 • Summary of One-Sample
Hypothesis Tests for the Mean 255 • p- Values 256 • One-Sample Tests for
Proportions 257 • Confidence Intervals and Hypothesis Tests 258 • An Excel
Template for One-Sample Hypothesis Tests 258
Two-Sample Hypothesis Tests 259
Two-Sample Tests for Differences in Means 260 • Two-Sample Test for Means with
Paired Samples 262 • Two-Sample Test for Equality of Variances 264
Analysis of Variance (ANOVA) 266
Assumptions of ANOVA 268
 Contents xi

Chi-Square Test for Independence 269

Cautions in Using the Chi-Square Test 271 • Chi-Square Goodnessof Fit Test 272
Analytics in Practice: Using Hypothesis Tests and Business Analytics in a Help Desk
Service Improvement Project 273
Key Terms 274 • Chapter 7 Technology Help 274 • Problems and Exercises 276 •
Case: Drout Advertising Research Project 281 • Case: Performance Lawn Equipment 281
Part 3: Predictive Analytics
Chapter 8: Trendlines and Regression Analysis 283
Learning Objectives 283
Modeling Relationships and Trends in Data 285
Analytics in Practice: Using Predictive Trendline Models at Procter & Gamble 289
Simple Linear Regression 289
Finding the Best-Fitting Regression Line 291 • Using Regression Models for
Prediction 291 • Least-Squares Regression 292 • Simple Linear Regression with
Excel 294 • Regression as Analysis of Variance 296 • Testing Hypotheses for
Regression Coefficients 297 • Confidence Intervals for Regression Coefficients 297
Residual Analysis and Regression Assumptions 298
Checking Assumptions 299
Multiple Linear Regression 301
Analytics in Practice: Using Linear Regression and Interactive Risk Simulators to
Predict Performance at Aramark 304
Building Good Regression Models 306
Correlation and Multicollinearity 308 • Practical Issues in Trendline and Regression
Modeling 310
Regression with Categorical Independent Variables 310
Categorical Variables with More Than Two Levels 313
Regression Models with Nonlinear Terms 315
Key Terms 317 • Chapter 8 Technology Help 317 • Problems and Exercises 318 •
Case: Performance Lawn Equipment 322
Chapter 9: Forecasting Techniques 325
Learning Objectives 325
Analytics in Practice: Forecasting Call-Center Demand at EL. Bean 326
Qualitative and Judgmental Forecasting 327
Historical Analogy 327 • The Delphi Method 327 • Indicators and Indexes 328
Statistical Forecasting Models 329
Forecasting Models for Stationary Time Series 331
Moving Average Models 331 • Error Metrics and Forecast Accuracy 333 •
Exponential Smoothing Models 335
Forecasting Models for Time Series with a Linear Trend 338
Double Exponential Smoothing 338 • Regression-Based Forecasting for Time Series
with a Linear Trend 340
Forecasting Time Series with Seasonality 341
Regression-Based Seasonal Forecasting Models 341 • Holt-Winters Models for
Forecasting Time Series with Seasonality and No Trend 343 • Holt-Winters Models
for Forecasting Time Series with Seasonality and Trend 345 • Selecting Appropriate
Time-Series-Based Forecasting Models 348
Xii Contents

Regression Forecasting with Causal Variables 348

The Practice of Forecasting 349
Analytics in Practice: Forecasting at NBCUniversal 350
Key Terms 351 • Chapter 9 Technology Help 352 • Problems and Exercises 352 •
Gase: Performance Lawn Equipment 354
Chapter 10: Introduction to Data Mining 355
Leaming Objectives 355
The Scope of Data Mining 356
Cluster Analysis 358
Measuring Distance Between Objects 359 • Normalizing Distance
Measures 360 • Clustering Methods 360
Classification 362
An Intuitive Explanation of Classification 363 • Measuring Classification
Performance 364 • Classification Techniques 365
Association 370
Cause-and-Effect Modeling 372
Analytics In Practice: Successful Business Applications ofData Mining 374
Key Terms 374 • Chapter 10 Technology Help 375 • Problems and Exercises 375 •
Case: Performance Lawn Equipment 376
Chapter 11: Spreadsheet Modeling and Analysis 377
Leaming Objectives 377
Analytics in Practice: Using Spreadsheet Modeling and Analysis at Nestle 379
Model-Building Strategies 379
Building Models Using Logic and Business Principles 379 • Building Models Using
Influence Diagrams 380 • Building Models Using Historical Data 381 • Model
Assumptions, Complexity, and Realism 382
Implementing Models on Spreadsheets 382
Spreadsheet Design 383 • Spreadsheet Quality 384 • Data Validation 386
Analytics in Practice: Spreadsheet Engineering at Procter & Gamble 388
Descriptive Spreadsheet Models 388
Staffing Decisions 389 • Single-Period Purchase Decisions 390 • Overbooking
Decisions 392
Analytics in Practice: Using an Overbooking Model at a Student Health Clinic 393
Retail Markdown Decisions 393
Predictive Spreadsheet Models 395
New Product Development Model 395 • Cash Budgeting 397 • Retirement
Flanning 398 • Project Management 398
Prescriptive Spreadsheet Models 401
Portfolio Allocaüon 401 • Locating Central Facilities 402 • Job Sequencing 404
Analyzing Uncertainty and Model Assumptions 406
What-If Analysis 406 • Data Tables 406 • Scenario Manager 409 • Goal
Seck 410
Key Terms 412 • Chapter 11 Technology Help 413 • Problems and Exercises 414 •
Case: Performance Lawn Equipment 421
 Contents xiii

Chapter 12: Simulation and Risk Analysis 423

Learning Objectives 423
Monte Carlo Simulation 425
Random Sampling from Probability Distribution« 427
Generating Random Variates using Excel Functions 429
Discrete Probability Distribution« 429 • Uniform Distribution« 430 • Exponential
Distribution« 431 • Normal Distribution« 431 • Binomial Distribution« 433 •
Triangulär Distribution« 433
Monte Carlo Simulation in Excel 435
Profit Model Simulation 435 • New Product Development 438 • Retirement
Flanning 440 • Single-Period Purchase Decisions 441 • Overbooking
Decisions 444 • Project Management 445
Analytics in Practice: Implementing Large-Scale Monte Carlo Spreadsheet
Models 446
Dynamic Systems Simulation 447
Simulating Waiting Lines 449
Analytics in Practice: Using Systems Simulation for Agricultural Product
Development 452
Key Terms 453 • Chapter 12 Technology Help 453 • Problems and Exercises 453 •
Case: Performance Lawn Equipment 463
Part 4: Prescriptive Analytics
Chapter 13: Linear Optimization 465
Learning Objectives 465
Optimization Models 466
Analytics in Practice: Linear Optimization in Bank Financial Planning 468
Analytics in Practice: Using Optimization Models for Sales Planning at NBC 468
Developing Linear Optimization Models 469
Identifying Decision Variables, the Objective, and Constraints 470 • Developing a
Mathematical Model 471 • More About Constraints 472 • Implementing Linear
Optimization Models on Spreadsheets 474 • Excel Functions to Avoid in Linear
Optimization 475
Solving Linear Optimization Models 476
Solver Answer Report 478 • Graphical Interpretation of Linear Optimization with
Two Variables 479
How Solver Works 485
How Solver Creates Name« in Reports 486
Solver Outcomes and Solution Messages 487
Unique Optimal Solution 487 • Alternative (Multiple) Optimal Solutions 487 •
Unbounded Solution 487 • Infeasibility 489
Applications of Linear Optimization 491
Blending Models 491 • Dealing with Infeasibility 492 • Portfolio Investment
Models 493 • Scaling Issues in Using Solver 495 • Transportation
Models 498 • Multiperiod Production Planning Models 501 • Multiperiod
Financial Planning Models 505
 Analytics in Practice: Linear Optimization in Bank Financial Planning 508
Key Terms 509 • Chapter 13 Technology Help 29 • Problems and Exencises 510 •
Case: Performance Lawn Equipment 522
Chapter 14: Integer and Nonlinear Optimization 523
Learning Objectives 523
Integer Linear Optimization Models 524
Models with General Integer Variables 525 • Workforce-Scheduling Models 528 •
Alternative Optimal Solutions 531
Models with Binary Variables 533
Using Binary Variables to Model Logical Constraints 534 • Applications in Supply
Chain Optimization 535
Analytics in Practice: Supply Chain Optimization at Procter & Gamble 539
Nonlinear Optimization Models 539
A Nonlinear Pacing Decision Model 539 • Quadratic Optimization 543 • Practica!
Issues Using Solver for Nonlinear Optimization 544
Analytics in Practice: Applying Nonlinear Optimization at Prudential Securities 545
Non-Smooth Optimization 546
Evolutionary Solver 546 • Evolutionary Solver for Sequencing and Scheduling
Models 549 • The Traveling Salesperson Problem 551
Key Terms 553 • Chapter 14 Technology Help 553 • Problems and Exercises 554 '
Case: Performance Lawn Equipment 563
Chapter 15: Optimization Analytics 565
Learning Objectives 565
What-If Analysis for Optimization Models 566
Solver Sensitivity Report 567 • Using the Sensitivity Report 572 •
Degeneracy 573 • Interpreting Solver Reports for Nonlinear Optimization
Models 573
Models with Bounded Variables 575
Auxiliary Variables for Bound Constraints 578
What-If Analysis for Integer Optimization Models 581
Visualization of Solver Reports 583
Using Sensitivity Information Correctly 590
Key Terms 594 • Chapter 15 Technology Help 594 • Problems and Exercises 594 •
Case: Performance Lawn Equipment 601
Part 5: Making Decisions
Chapter 16: Decision Analysis 603
Learning Objectives 603
Formulating Decision Problems 605
Decision Strategies without Outcome Probabilities 606
Decision Strategies for a Minimize Objective 606 • Decision Strategies for a
Maximize Objective 608 • Decisions with Conflicting Objectives 608
Decision Strategies with Outcome Probabilities 610
Average Payoff Strategy 610 • Expected Value Strategy 610 • Evaluating
Risk 611
 Contents XV

Decision Trees 612

Decision Trees and Risk 614 • Sensitivity Analysis in Decision Trees 617
The Value of Information 618
Decisions with Sample Information 619
Bayes's Rule 620
Utility and Decision Making 621
Constructing a Utility Function 622 • Exponential Utility Functions 625
Analytics in Practice: Using Decision Analysis in Drug Development 626
Key Terms 627 • Chapter 16 Technology Help 627 • Problems and Exercises 628 •
Gase: Performance Lawn Equipment 632
Online Supplements: Information about how to access and use Analytic Solver Basic
are available for download at www.pearsonhighered.com/evans.
Gelting Started with Analytic Solver
Using Advanced Regression Techniques in Analytic Solver
Using Forecasting Techniques in Analytic Solver
Using Data Mining in Analytic Solver
Model Analysis in Analytic Solver
Using Monte Carlo Simulation in Analytic Solver
Using Linear Optimization in Analytic Solver
Using Integer and Nonlinear Optimization in Analytic Solver
Using Optimization Parameter Analysis in Analytic Solver
Using Decision Trees in Analytic Solver

Appendix A 633
Glossary 657
Index 665