You are previewing Improving the User Experience through Practical Data Analytics.
O'Reilly logo
Improving the User Experience through Practical Data Analytics

Book Description

Improving the User Experience through Practical Data Analytics shows you how to make UX design decisions based on data—not hunches. Authors Fritz and Berger help the UX professional recognize the enormous potential of user data that is collected as a natural by-product of routine UX research methods, including moderated usability tests, unmoderated usability tests, surveys, and contextual inquiries. Then, step-by-step, they explain how to utilize both descriptive and predictive statistical techniques to gain meaningful insight with that data. By mastering the use of these techniques, you’ll delight your users, increase your bottom line and gain a powerful competitive advantage for your company—and yourself.

Key features include:

  • Practical advise on choosing the right data analysis technique for each project.
  • A step-by-step methodology for applying each technique, including examples and scenarios drawn from the UX field.
  • Detailed screen shots and instructions for performing the techniques using Excel (both for PC and Mac) and SPSS.
  • Clear and concise guidance on interpreting the data output.
  • Exercises to practice the techniques, along with access to sample data on the companion website.


  • Practical guidance on choosing the right data analysis technique for each project.
  • Real-world examples to build a theoretical and practical understanding of key concepts from consumer and financial verticals.
  • A step-by-step methodology for applying each predictive technique, including detailed examples.
  • A detailed guide to interpreting the data output and examples of how to effectively present the findings in a report.
  • Exercises to learn the techniques, along with access to sample data on the companion website.

Table of Contents

  1. Cover image
  2. Title page
  3. Table of Contents
  4. Advance Praise for Improving the User Experience through Practical Data Analytics
  5. Copyright
  6. Dedication
  7. Preface
  8. About the Authors
  9. Acknowledgments
  10. Chapter 1. Introduction to a variety of useful statistical ideas and techniques
    1. 1.1. Introduction
    2. 1.2. The Great Normal Curve in the Sky
    3. 1.3. Confidence Intervals
    4. 1.4. Hypothesis Testing
    5. 1.5. Summary
    6. 1.6. Addendum: activating “Data Analysis”
  11. Chapter 2. Comparing two designs (or anything else!) using independent sample T-tests
    1. 2.1. Introduction
    2. 2.2. Case Study: Comparing Designs at Mademoiselle La La
    3. 2.3. Comparing Two Means
    4. 2.4. Independent Samples
    5. 2.5. Mademoiselle La La Redux
    6. 2.6. But What if We Conclude that the Means Aren’t Different?
    7. 2.7. Final Outcome at Mademoiselle La La
    8. 2.8. Addendum: Confidence Intervals
    9. 2.9. Summary
    10. 2.10. Exercise
  12. Chapter 3. Comparing two designs (or anything else!) using paired sample T-tests
    1. 3.1. Introduction
    2. 3.2. Vignette: How Fast Can You Post a Job at Behemoth.com?
    3. 3.3. Introduction to Paired Samples
    4. 3.4. Example of Paired (Two-Sample) t-test
    5. 3.5. Behemoth.com Revisited
    6. 3.6. Addendum: A Mini-Discussion Why the Independent and Paired Tests Need to Be Different
    7. 3.7. Summary
    8. 3.8. Exercise
  13. Chapter 4. Pass or fail? Binomial-related hypothesis testing and confidence intervals using independent samples
    1. 4.1. Introduction
    2. 4.2. Case Study: Is Our Expensive New Search Engine At Behemoth.Com Better Than What We Already Have?
    3. 4.3. Hypothesis Testing Using the Chi-Square Test of Independence or Fisher’s Exact Test
    4. 4.4. Meanwhile, Back At Behemoth.Com
    5. 4.5. Binomial Confidence Intervals and the Adjusted Wald Method
    6. 4.6. Summary
    7. 4.7. Addendum 1: How to Run the Chi-Square Test for Different Sample Sizes
    8. 4.8. Addendum 2: Comparing More than Two Treatments
    9. 4.9. Appendix: Confidence Intervals for all Possible Sample-Proportion Outcomes From N = 1 to N = 15, in Table A.1
    10. 4.10. Exercises
  14. Chapter 5. Pass or fail? Binomial-related hypothesis testing and confidence intervals using paired samples
    1. 5.1. Introduction
    2. 5.2. Case Study: Can I Register for a Course at Backboard.com?
    3. 5.3. Hypothesis testing using the cochran Q test
    4. 5.4. Meanwhile, back at backboard…
    5. 5.5. Summary
    6. 5.6. Exercise
  15. Chapter 6. Comparing more than two means: one factor ANOVA with independent samples. Multiple comparison testing with the Newman-Keuls test
    1. 6.1. Introduction
    2. 6.2. Case Study: Sophisticated for Whom?
    3. 6.3. Independent Samples: One-Factor ANOVA
    4. 6.4. The Analyses
    5. 6.5. Multiple Comparison Testing
    6. 6.6. Illustration of the S-N-K Test
    7. 6.7. Application of the S-N-K to This Result
    8. 6.8. Discussion of the Result
    9. 6.9. Meanwhile, Back at Mademoiselle La La…
    10. 6.10. Summary
    11. 6.11. Exercises
  16. Chapter 7. Comparing more than two means: one factor ANOVA with a within-subject design
    1. 7.1. Introduction
    2. 7.2. Case Study: Comparing Multiple Ease-of-Use Ratings at Mademoiselle La La
    3. 7.3. Comparing Several Means with a Within-Subjects Design
    4. 7.4. Hypotheses for Comparing Several Means
    5. 7.5. SPSS Analysis
    6. 7.6. Newman-Keuls Analysis
    7. 7.7. Excel Analysis
    8. 7.8. Mademoiselle La La: Let’s Fix the Checkout Asap!
    9. 7.9. Summary
    10. 7.10. Exercise
  17. Chapter 8. Comparing more than two means: two factor ANOVA with independent samples; the important role of interaction
    1. 8.1. Introduction
    2. 8.2. Case Study: Comparing Age and Gender at Mademoiselle La La
    3. 8.3. Interaction
    4. 8.4. Working the example in SPSS
    5. 8.5. Meanwhile, back at Mademoiselle La La…
    6. 8.6. Summary
    7. 8.7. Exercise
  18. Chapter 9. Can you relate? Correlation and simple linear regression
    1. 9.1. Introduction
    2. 9.2. Case Study: Do Recruiters Really Care about Boolean at Behemoth.Com?
    3. 9.3. The Correlation Coefficient
    4. 9.4. Linear Regression
    5. 9.5. Linear Regression Analysis of Behemoth.com Data
    6. 9.6. Meanwhile, Back at Behemoth
    7. 9.7. Summary
    8. 9.8. Addendum: A Quick Discussion of Some Assumptions Implicit in Interpreting the Results
    9. 9.9. Exercise
  19. Chapter 10. Can you relate in multiple ways? Multiple linear regression and stepwise regression
    1. 10.1. Introduction
    2. 10.2. Case Study: Determining the Ideal Search Engine at Behemoth.Com
    3. 10.3. Multiple Regression
    4. 10.4. A Confidence Interval for the Prediction
    5. 10.5. Back to Behemoth.Com
    6. 10.6. Stepwise Regression
    7. 10.7. Meanwhile, Back at Behemoth.com
    8. 10.8. Summary
    9. 10.9. Exercise
  20. Chapter 11. Will anybody buy? Logistic regression
    1. 11.1. Introduction
    2. 11.2. Case study: will anybody buy at the <span xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops" class="italic">Charleston Globe</span>??
    3. 11.3. Logistic regression
    4. 11.4. Logistic regression using SPSS
    5. 11.5. CharlestonGlobe.com survey data and its analysis
    6. 11.6. Implications of the survey-data analysis results—Back to CharlestonGlobe.com
    7. 11.7. Summary
    8. 11.8. Exercise
  21. Addendum: For Mac Excel Users
  22. Index