Business Analytics

Methods, Models, and Decisions

James R. Evans i University of Cincinnati

GLOBAL EDITION

SECOND EDITION

PEARSON

Boston Columbus Indianapolis New York San Francisco

Amsterdam Cape Town Dubai London Madrid Milan Munich Paris Montreal Toronto
Delhi Mexico City Säo Paulo Sydney Hong Kong Seoul Singapore Taipei Tokyo
 Contents

Preface 17
About the Author 23
Credits 25

Part 1: Foundations of Business Analytics

Chapter 1: Introduction to Business Analytics 27
Learning Objectives 27
What Is Business Analytics? 30
Evolution of Business Analytics 31
Impacts and Challenges 34
Scope of Business Analytics 35
Software Support 38
Data for Business Analytics 39
Data Sets and Databases 40 • Big Data 41 • Metrics and Data
Classification 42 * Data Reliability and Validity 44
Models in Business Analytics 44
Decision Models 47 • Model Assumptions 50 • Uncertainty and Risk 52 •
Prescriptive Decision Models 52
Problem Solving with Analytics 53
Recognizing a Problem 54 • Defining the Problem 54 • Structuring the
Problem 54 • Analyzing the Problem 55 » Interpreting Results and Making
a Decision 55 • Implementing the Solution 55
Key Terms 56 • Fun with Analytics 57 • Problems and Exercises 57 *
Case: Drout Advertising Research Project 59 • Case: Performance Lawn
Equipment 60
Chapter 2: Analytics on Spreadsheets 63
Learning Objectives 63
Basic Excel Skills 65
Excel Formulas 66 • Copying Formulas 66 • Other Useful Excel Tips 67
Excel Functions 68
Basic Excel Functions 68 • Functions for Specific Applications 69 •
Insert Function 70 • Logical Functions 71
Using Excel Lookup Functions for Database Queries 73
Spreadsheet Add-Ins for Business Analytics 76
Key Terms 76 • Problems and Exercises 76 • Case: Performance Lawn
Equipment 78

7
B Contents

Part 2: Descriptive Analytics

Chapter 3: Visualizing and Exploring Data 79
Learning Objectives 79
Data Visualization 80
Dashboards 81 • Tools and Software for Data Visualization 81
Creating Charts in Microsoft Excel 82
Column and Bar Charts 83 • Data Labels and Data Tables Chart
Options 85 • Line Charts 85 • Pie Charts 85 • Area Charts 86 •
Scatter Chart 86 • Bubble Charts 88 * Miscellaneous
Excel Charts 89 • Geographie Data 89
Other Excel Data Visualization Tools 90
Data Bars, Color Scales, and Icon Sets 90 • Sparklines 91 • Excel Camera
Tool 92
Data Queries: Tables, Sorting, and Filtering 93
Sorting Data in Excel 94 • Pareto Analysis 94 • Filtering Data 96
Statistical Methods for Summarizing Data 98
Frequency Distributions for Categorical Data 99 • Relative Frequency
Distributions 100 • Frequency Distributions for Numerical Data 101 •
Excel Histogram Tool 101 • Cumulative Relative Frequency
Distributions 105 • Percentiles and Quartiles 106 • Cross-Tabulations 108
Exploring Data Using PivotTables 110
PivotCharts 112 • Slicers and PivotTable Dashboards 113
Key Terms 116 • Problems and Exercises 117 * Case: Drout Advertising Research
Project 119 • Case: Performance Lawn Equipment 120

Chapter 4: Descriptive Statistical Measures 121

Learning Objectives 121
Populations and Samples 122
Understanding Statistical Notation 122
Measures of Location 123
Arithmetic Mean 123 • Median 124 • Mode 125 • Midrange 125 •
Using Measures of Location in Business Decisions 126
Measures of Dispersion 127
Range 127 • Interquartile Range 127 • Variance 128 • Standard
Deviation 129 • Chebyshev's Theorem and the Empirical Rules 130 •
Standardized Values 133 • Coefficient of Variation 134
Measures of Shape 135
Excel Descriptive Statistics Tool 136
Descriptive Statistics for Grouped Data 138
Descriptive Statistics for Categorical Data: The Proportion 140
Statistics in PivotTables 140
Contents 9

Measures of Association 141

Covariance 142 • Correlation 143 • Excel Correlation Tool 145
Outliers 146
Statistical Thinking in Business Decisions 148
Variability in Samples 149
Key Terms 151 • Problems and Exercises 152 • Case: Drout Advertising Research
Project 155 • Case: Performance Lawn Equipment 155

Chapter 5: Probability Distributions and Data Modeling 157

Learning Objectives 157
Basic Concepts of Probability 158
Probability Rules and Formulas 160 • Joint and Marginal Probability 161 •
Conditional Probability 163
Random Variables and Probability Distributions 166
Discrete Probability Distributions 168
Expected Value of a Discrete Random Variable 169 • Using Expected Value in
Making Decisions 170 • Variance of a Discrete Random Variable 172 •
Bernoulli Distribution 173 • Binomial Distribution 173 "
Poisson Distribution 175
Continuous Probability Distributions 176
Properties of Probability Density Functions 177 • Uniform Distribution 178 •
Normal Distribution 180 * The NORM.INV Function 182 • Standard Normal
Distribution 182 • Using Standard Normal Distribution Tables 184 •
Exponential Distribution 184 • Other Useful Distributions 186 * Continuous
Distributions 186
Random Sampling from Probability Distributions 187
Sampling from Discrete Probability Distributions 188 • Sampling from Common
Probability Distributions 189 • Probability Distribution Functions in Analytic Solver
Platform 192
Data Modeling and Distribution Fitting 194
Goodness of Fit 196 • Distribution Fitting with Analytic Solver Platform 196
Key Terms 198 • Problems and Exercises 199 • Case: Performance Lawn
Equipment 205

Chapter 6: Sampling and Estimation 207

Learning Objectives 207
Statistical Sampling 208
Sampling Methods 208
Estimating Population Parameters 211
Unbiased Estimators 212 • Errors in Point Estimation 212
Sampling Error 213
Understanding Sampling Error 213
10 Contents

Sampling Distributions 215

Sampling Distribution of the Mean 215 * Applying the Sampling Distribution
oftheMean 216
Interval Estimates 216
Confidence Intervals 217
Confidence Interval for the Mean with Known Population Standard
Deviation 218 • The f-Distribution 219 • Confidence Interval for the
Mean with Unknown Population Standard Deviation 220 • Confidence Interval
for a Proportion 220 • Additional Types of Confidence Intervals 222
Using Confidence Intervals for Decision Making 222
Prediction Intervals 223
Confidence Intervals and Sample Size 224
Key Terms 226 • Problems and Exercises 226 • Case: Drout Advertising
Research Project 228 • Case: Performance Lawn Equipment 229

Chapter 7: Statistical Inference 231

Learning Objectives 231
Hypothesis Testing 232
Hypothesis-Testing Procedure 233
One-Sample Hypothesis Tests 233
Understanding Potential Errors in Hypothesis Testing 234 • Selecting the Test
Statistic 235 • Drawing a Conclusion 236
Two-Tailed Test of Hypothesis for the Mean 238
p-Values 238 • One-Sample Tests for Proportions 239 • Confidence Intervals
and Hypothesis Tests 240
Two-Sample Hypothesis Tests 241
Two-Sample Tests for Differences in Means 241 • Two-Sample Test for Means with
Paired Samples 244 • Test for Equality of Variances 245
Analysis of Variance (ANOVA) 247
Assumptions of ANOVA 249
Chi-Square Test for Independence 250
Cautions in Using the Chi-Square Test 252
Key Terms 253 * Problems and Exercises 254 • Case: Drout Advertising Research
Project 257 • Case: Performance Lawn Equipment 257

Part 3: Predictive Analytics

Chapter 8: Trendlines and Regression Analysis 259
Learning Objectives 259
Modeling Relationships and Trends in Data 260
Simple Linear Regression 264
Finding the Best-Fitting Regression Line 265 • Least-Squares Regression 267
Simple Linear Regression with Excel 269 • Regression as Analysis of
Variance 271 • Testing Hypotheses for Regression Coefficients 271 •
Confidence Intervals for Regression Coefficients 272
Contents 11

Residual Analysis and Regression Assumptions 272

Checking Assumptions 274
Multiple Linear Regression 275
Building Good Regression Models 280
Correlation and Multicollinearity 282 • Practical Issues in Trendline and Regression
Modeling 283
Regression with Categorical Independent Variables 284
Categorical Variables with More Than Two Levels 287
Regression Models with Nonlinear Terms 289
Advanced Techniques for Regression Modeling using XLMiner 291
Key Terms 294 • Problems and Exercises 294 • Case: Performance Lawn
Equipment 298

Chapter 9: Forecasting Techniques 299

Learning Objectives 299
Qualitative and Judgmental Forecasting 300
Historical Analogy 300 • The Delphi Method 301 • Indicators and Indexes 301
Statistical Forecasting Models 302
Forecasting Models for Stationary Time Series 304
Moving Average Models 304 • Error Metrics and Forecast Accuracy 308 •
Exponential Smoothing Models 310
Forecasting Models for Time Series with a Linear Trend 312
Double Exponential Smoothing 313 • Regression-Based Forecasting for Time Series
with a Linear Trend 314
Forecasting Time Series with Seasonality 316
Regression-Based Seasonal Forecasting Models 316 • Holt-Winters Forecasting for
Seasonal Time Series 318 • Holt-Winters Models for Forecasting Time Series with
Seasonality and Trend 318
Selecting Appropriate Time-Series-Based Forecasting Models 320
Regression Forecasting with Causal Variables 321
The Practice of Forecasting 322
Key Terms 324 * Problems and Exercises 324 • Case: Performance Lawn
Equipment 326

Chapter 10: introduction to Data Mining 327

Learning Objectives 327
The Scope of Data Mining 329
Data Exploration and Reduction 330
Sampling 330 • Data Visualization 332 • Dirty Data 334 • Cluster
Analysis 336
Classification 341
An Intuitive Explanation of Classification 342 • Measuring Classification
Performance 342 • Using Training and Validation Data 344 • Classifying
New Data 346
2 Contents

Classification Techniques 346

/fc-Nearest Neighbors (fc-NN) 347 • Discriminant Analysis 349 • Logistic
Regression 354 • Association Rule Mining 358
Cause-and-Effect Modeling 361
Key Terms 364 • Problems and Exercises 364 • Case: Performance Lawn
Equipment 366

Chapter 11: Spreadsheet Modeling and Analysis 367

Learning Objectives 367
Strategies for Predictive Decision Modeling 368
Building Models Using Simple Mathematics 368 • Building Models Using Influence
Diagrams 369
Implementing Models on Spreadsheets 370
Spreadsheet Design 370 • Spreadsheet Quality 372
Spreadsheet Applications in Business Analytics 375
Models Involving Multiple Time Periods 377 • Single-Period Purchase
Decisions 379 • Overbooking Decisions 380
Model Assumptions, Complexity, and Realism 382
Data and Models 382
Developing User-Friendly Excel Applications 385
Data Validation 385 • Range Names 385 • Form Controls 386
Analyzing Uncertainty and Model Assumptions 388
What-If Analysis 388 • Data Tables 390 • Scenario Manager 392 *
Goal Seck 393
Model Analysis Using Analytic Solver Platform 394
Parametric Sensitivity Analysis 394 • Tornado Charts 396
Key Terms 397 * Problems and Exercises 397 • Case: Performance Lawn
Equipment 402

Chapter 12: Monte Carlo Simulation and Risk Analysis 403

Learning Objectives 403
Spreadsheet Models with Random Variables 405
Monte Carlo Simulation 405
Monte Carlo Simulation Using Analytic Solver Platform 407
Defining Uncertain Model Inputs 407 • Defining Output Cells 410 •
Running a Simulation 410 • Viewing and Analyzing Results 412
New-Product Development Model 414
Confidence Interval for the Mean 417 • Sensitivity Chart 418 • Overlay
Charts 418 • Trend Charts 420 • Box-Whisker Charts 420 •
Simulation Reports 421
Newsvendor Model 421
The Flaw of Averages 421 • Monte Carlo Simulation Using Historical
Data 422 • Monte Carlo Simulation Using a Fitted Distribution 423
Overbooking Model 424
The Custom Distribution in Analytic Solver Platform 425
Contents

Cash Budget Model 426

Correlating Uncertain Variables 429
Key Terms 433 • Problems and Exercises 433 • Case: Performance Lawn
Equipment 440

Part 4: Prescriptive Analytics

Chapter 13: Linear Optimization 441
Learning Objectives 441
Building Linear Optimization Models 442
Identifying Elements for an Optimization Model 442 • Translating Model
Information into Mathematical Expressions 443 • More about
Constraints 445 • Characteristics of Linear Optimization Models 446
Implementing Linear Optimization Models on Spreadsheets 446
Excel Functions to Avoid in Linear Optimization 448
Solving Linear Optimization Models 448
Using the Standard Solver 449 • Using Premium Solver 451 • Solver
Answer Report 452
Graphical Interpretation of Linear Optimization 454
How Solver Works 459
How Solver Creates Names in Reports 461
Solver Outcomes and Solution Messages 461
Unique Optimal Solution 462 • Alternative (Multiple) Optimal
Solutions 462 • Unbounded Solution 463 • Infeasibility 464
Using Optimization Models for Prediction and Insight 465
Solver Sensitivity Report 467 • Using the Sensitivity Report 470 •
Parameter Analysis in Analytic Solver Platform 472
Key Terms 476 • Problems and Exercises 476 • Case: Performance Lawn
Equipment 481

Chapter 14: Applications of Linear Optimization 483

Learning Objectives 483
Types of Constraints in Optimization Models 485
Process Selection Models 486
Spreadsheet Design and Solver Reports 487
Solver Output and Data Visualization 489
Blending Models 493
Dealing with Infeasibility 494
Portfolio Investment Models 497
Evaluating Risk versus Reward 499 • Scaling Issues in Using Solver 500
Transportation Models 502
Formatting the Sensitivity Report 504 • Degeneracy 506
Multiperiod Production Flanning Models 506
Building Alternative Models 508
Multiperiod Financial Flanning Models 511
Contents

Models with Bounded Variables 515

Auxiliary Variables for Bound Constraints 519
A Production/Marketing Allocation Model 521
Using Sensitivity Information Correctly 523
Key Terms 525 ' Problems and Exercises 525 • Case: Performance Lawn
Equipment 537

Chapter 15: Integer Optimization 539

Learning Objectives 539
Solving Models with General Integer Variables 540
Workforce-Scheduling Models 544 • Alternative Optimal Solutions 545
Integer Optimization Models with Binary Variables 549
Project-Selection Models 550 • Using Binary Variables to Model Logical
Constraints 552 • Location Models 553 • Parameter Analysis 555 •
A Customer-Assignment Model for Supply Chain Optimization 556
Mixed-Integer Optimization Models 559
Plant Location and Distribution Models 559 * Binary Variables, IF Functions, and
Nonlinearities in Model Formulation 560 • Fixed-Cost Models 562
Key Terms 564 ' Problems and Exercises 564 • Case: Performance Lawn
Equipment 573

Chapter 16: Decision Analysis 579

Learning Objectives 579
Formulating Decision Problems 581
Decision Strategies without Outcome Probabilities 582
Decision Strategies for a Minimize Objective 582 • Decision Strategies for a
Maximize Objective 583 • Decisions with Conflicting Objectives 584
Decision Strategies with Outcome Probabilities 586
Average Payoff Strategy 586 • Expected Value Strategy 586 •
Evaluating Risk 587
Decision Trees 588
Decision Trees and Monte Carlo Simulation 592 • Decision Trees and
Risk 592 • Sensitivity Analysis in Decision Trees 594
The Value of Information 595
Decisions with Sample Information 596 • Bayes's Rule 596
Utility and Decision Making 598
Constructing a Utility Function 599 * Exponential Utility Functions 602
Key Terms 604 ' Problems and Exercises 604 • Case: Performance Lawn
Equipment 608
Contents 15

Supplementary Chapter A (online) Nonlinear and Non-Smooth Optimization

Supplementary Chapter B (online) Optimization Models with Uncertainty

Online chapters are available for download at www.pearsonglobaleditions.com/Evans.

Appendix A 611
Glossary 635
Index 643