Quantifying the user experience practical statistics for user research
Quantifying the User Experience: Practical Statistics for User Research, Second Edition, provides practitioners and researchers with the information they need to confidently quantify, qualify, and justify their data. The book presents a practical guide on how to use statistics to solve common quanti...
| Otros Autores: | , |
|---|---|
| Formato: | Libro electrónico |
| Idioma: | Inglés |
| Publicado: |
Cambridge, MA :
Elsevier/Morgan Kaufmann
2016.
|
| Edición: | 2nd edition |
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009630244606719 |
Tabla de Contenidos:
- Cover
- Title Page
- Copyright Page
- Dedication
- Contents
- Biographies
- Foreword
- Preface to the Second Edition
- Acknowledgments
- Chapter 1 - Introduction and how to use this book
- Introduction
- The organization of this book
- How to use this book
- What test should I use?
- What sample size do I need?
- You don't have to do the computations by hand
- Key points
- Chapter review questions
- Answers to chapter review questions
- References
- Chapter 2 - Quantifying user research
- What is user research?
- Data from user research
- Usability testing
- Sample sizes
- Representativeness and randomness
- Three types of studies for user research
- Data collection
- Completion rates
- Usability problems (UI problems)
- Task Time
- Errors
- Satisfaction ratings
- Combined scores
- A/B testing
- Clicks, page views, and conversion rates
- Survey data
- Rating scales
- Net Promoter Scores
- Comments and open-ended data
- Requirements gathering
- Key points
- References
- Chapter 3 - How precise are our estimates? Confidence intervals
- Introduction
- Confidence interval = twice the margin of error
- Confidence intervals provide precision and location
- Three components of a confidence interval
- Confidence level
- Variability
- Sample size
- Confidence interval for a completion rate
- Confidence interval history
- Wald interval: terribly inaccurate for small samples
- Exact confidence interval
- Adjusted-Wald: add two successes and two failures
- Best point estimates for a completion rate
- Guidelines on reporting the best completion rate estimate
- How accurate are point estimates from small samples?
- Confidence interval for a problem occurrence
- Confidence interval for rating scales and other continuous data
- Confidence interval for task-time data
- Mean or median task time?.
- Variability
- Bias
- Geometric mean
- Computing the geometric mean
- Log transforming confidence intervals for task-time data
- Confidence interval for large sample task times
- Confidence interval around a median
- Key points
- Chapter review questions
- Answers to chapter review questions
- References
- Chapter 4 - Did we meet or exceed our goal?
- Introduction
- One-tailed and two-tailed tests
- Comparing a completion rate to a benchmark
- Small sample test
- Mid-probability
- Large sample test
- Comparing a satisfaction score to a benchmark
- Do at least 75% agree? converting continuous ratings to discrete
- Disadvantages to converting continuous ratings to discrete
- Net Promoter Score
- Comparing a task time to a benchmark
- Key points
- Chapter review questions
- Answers to chapter review questions
- References
- Chapter 5 - Is there a statistical difference between designs?
- Introduction
- Comparing two means (rating scales and task times)
- Within-subjects comparison (paired t-test)
- Confidence interval around the difference
- Practical significance
- Comparing task times
- Normality assumption of the paired t-test
- Between-subjects comparison (two-sample t-test)
- Confidence interval around the difference
- Assumptions of the t-tests
- Normality
- Equality of variances
- Don't worry too much about violating assumptions (except representativeness)
- Comparing completion rates, conversion rates, and A/B testing
- Between-subjects
- Chi-square test of independence
- Small sample sizes
- Two-proportion test
- Fisher exact test
- Yates correction
- N−1 Chi-square test
- N−1 Two-proportion test
- Confidence interval for the difference between proportions
- Within-subjects
- McNemar exact test
- Concordant pairs
- Discordant pairs
- Alternate approaches
- Chi-square statistic.
- Yates correction to the chi-square statistic
- Confidence interval around the difference for matched pairs
- Key points
- Chapter review questions
- Answers to chapter review questions
- References
- Chapter 6 - What sample sizes do we need? Part 1: summative studies
- Introduction
- Why do we care?
- The type of usability study matters
- Basic principles of summative sample size estimation
- Estimating values
- Comparing values
- What can I do to control variability?
- Sample size estimation for binomial confidence intervals
- Binomial sample size estimation for large samples
- Binomial sample size estimation for small samples
- Sample size for comparison with a benchmark proportion
- Sample size estimation for chi-squared tests (independent proportions)
- Sample size estimation for McNemar Exact Tests (matched proportions)
- Key points
- Chapter review questions
- Answers to chapter review questions
- References
- Chapter 7 - What sample sizes do we need? Part 2: formative studies
- Introduction
- Using a probabilistic model of problem discovery to estimate sample sizes for formative user research
- The famous equation P(x ≥ 1) = 1 - (1 - p)n
- Deriving a sample size estimation equation from 1 - (1 - p)n
- Using the tables to plan sample sizes for formative user research
- Assumptions of the binomial probability model
- Additional applications of the model
- Estimating the composite value of p for multiple problems or other events
- Adjusting small-sample composite estimates of p
- Estimating the number of problems available for discovery and the number of undiscovered problems
- What affects the value of p?
- What is a reasonable problem discovery goal?
- Reconciling the "magic number five" with "eight is not enough"
- Some history-the 1980s
- Some more history-the 1990s.
- The derivation of the "Magic Number 5"
- Eight is not enough-a reconciliation
- More about the binomial probability formula and its small-sample adjustment
- The origin of the binomial probability formula
- How does the deflation adjustment work?
- Other statistical models for problem discovery
- Criticisms of the binomial model for problem discovery
- Expanded binomial models
- Capture-recapture models
- Why not use one of these other models when planning formative user research?
- Key points
- Chapter review questions
- Answers to chapter review questions
- References
- Chapter 8 - Standardized usability questionnaires
- Introduction
- What is a standardized questionnaire?
- Advantages of standardized usability questionnaires
- What standardized usability questionnaires are available?
- Assessing the quality of standardized questionnaires: reliability, validity, and sensitivity
- Other item characteristics
- Number of scale steps
- Availability of a neutral response
- Agreement versus bipolar scales
- Norms
- Post-study questionnaires
- QUIS (Questionnaire for User Interaction Satisfaction)
- Description of the QUIS
- Psychometric evaluation of the QUIS
- SUMI (Software Usability Measurement Inventory)
- Description of the SUMI
- Psychometric evaluation of the SUMI
- PSSUQ (Post-Study System Usability Questionnaire)
- Description of the PSSUQ
- Psychometric evaluation of the PSSUQ
- PSSUQ norms and interpretation of normative patterns
- SUS (System Usability Scale)
- Description of the SUS
- Psychometric evaluation of the SUS
- SUS norms
- Does it hurt to be positive? evidence from an alternate form of the SUS
- UMUX (Usability Metric for User Experience)
- Description of the UMUX
- Psychometric evaluation of the UMUX
- UMUX-LITE
- Description of the UMUX-LITE
- Psychometric evaluation of the UMUX-LITE.
- Experimental comparison of Post-Study usability questionnaires
- Post-task questionnaires
- ASQ (After-Scenario Questionnaire)
- Description of the ASQ
- Psychometric evaluation of the ASQ
- SEQ (Single Ease Question)
- Description of the SEQ
- Psychometric evaluation of the SEQ
- SMEQ (Subjective Mental Effort Question)
- Description of the SMEQ
- Psychometric evaluation of the SMEQ
- ER (Expectation Ratings)
- Description of expectation ratings
- Psychometric evaluation of expectation ratings
- UME (Usability Magnitude Estimation)
- Description of UME
- Psychometric evaluation of UME
- Experimental comparisons of POST-TASK questionnaires
- Questionnaires for assessing perceived usability of websites
- WAMMI (Website Analysis and Measurement Inventory)
- Description of the WAMMI
- Psychometric evaluation of the WAMMI
- SUPR-Q (Standardized User Experience Percentile Rank Questionnaire)
- Description of the SUPR-Q
- Psychometric evaluation of the SUPR-Q
- Other questionnaires for assessing websites
- Other questionnaires of interest
- CSUQ (Computer System Usability Questionnaire)
- USE (Usefulness, Satisfaction, and Ease-of-Use)
- HQ (hedonic quality)
- EMO (emotional metric outcomes)
- ACSI (American customer satisfaction index)
- NPS (Net Promoter Score)
- CxPi (Forrester customer experience index)
- TAM (technology acceptance model)
- Key points
- Chapter review questions
- Answers to chapter review questions
- References
- Chapter 9 - Six enduring controversies in measurement and statistics
- Introduction
- Is it OK to average data from multipoint scales?
- On one hand
- On the other hand
- Our recommendation
- Do you need to test at least 30 users?
- On one hand
- On the other hand
- Our recommendation
- Should you always conduct a two-tailed test?
- On one hand
- On the other hand.
- Our recommendation.
