Chapter 16 Exploring, Displaying, and Examining Data McGraw-Hill/Irwin Copyright © 2011 by The McGraw-Hill Companies, Inc. All Rights Reserved.
16-2 Learning Objectives Understand... That exploratory data analysis techniques provide insights and data diagnostics by emphasizing visual representations of the data. How cross-tabulation is used to examine relationships involving categorical variables, serves as a framework for later statistical testing, and makes an efficient tool for data visualization and later decision-making.
16-3 Research as Competitive Advantage “As data availability continues to increase, the importance of identifying/filtering and analyzing relevant data can be a powerful way to gain an information advantage over our competition.” Tom H.C. Anderson founder & managing partner Anderson Analytics, LLC
16-4 PulsePoint: Research Revelation 65 The percent boost in company revenue created by best practices in data quality.
16-5 Researcher Skill Improves Data Discovery DDW is a global player in research services. As this ad proclaims, you can “push data into a template and get the job done,” but you are unlikely to make discoveries using a template process.
16-6 Exploratory Data Analysis ConfirmatoryExploratory
16-7 Data Exploration, Examination, and Analysis in the Research Process
16-8 Research Values the Unexpected “It is precisely because the unexpected jolts us out of our preconceived notions, our assumptions, our certainties, that it is such a fertile source of innovation.” Peter Drucker, author Innovation and Entrepreneurship
16-9 Frequency of Ad Recall Value Label Value Frequency Percent Valid Cumulative Percent Percent
16-10 Bar Chart
16-11 Pie Chart
16-12 Frequency Table
16-13 Histogram
16-14 Stem-and-Leaf Display
16-15 Pareto Diagram
16-16 Boxplot Components
16-17 Diagnostics with Boxplots
16-18 Boxplot Comparison
16-19 Mapping
16-20 Geograph: Digital Camera Ownership
16-21 SPSS Cross-Tabulation
16-22 Percentages in Cross-Tabulation
16-23 Guidelines for Using Percentages Averaging percentages Use of too large percentages Using too small a base Percentage decreases can never exceed 100%
16-24 Cross-Tabulation with Control and Nested Variables
16-25 Automatic Interaction Detection (AID)
16-26 Exploratory Data Analysis This Booth Research Services ad suggests that the researcher’s role is to make sense of data displays. Great data exploration and analysis delivers insight from data.
16-27 Key Terms Automatic interaction detection (AID) Boxplot Cell Confirmatory data analysis Contingency table Control variable Cross-tabulation Exploratory data analysis (EDA) Five-number summary Frequency table Histogram Interquartile range (IQR) Marginals Nonresistant statistics Outliers Pareto diagram Resistant statistics Stem-and-leaf display
Working with Data Tables McGraw-Hill/Irwin Copyright © 2011 by The McGraw-Hill Companies, Inc. All Rights Reserved.
16-29 Original Data Table Our grateful appreciation to eMarketer for the use of their table.
16-30 Arranged by Spending
16-31 Arranged by No. of Purchases
16-32 Arranged by Avg. Transaction, Highest
16-33 Arranged by Avg. Transaction, Lowest