Skip to main content Accessibility help
×
  1. Home
  2. Browse subjects
  3. Computer Science
  4. Computing: general interest
  5. Content listing

Refine search

Refine search

Access:
Content type:
Publication date:
Apply   From and To filters
Subject: Show more
Journals Show more
Publishers: Show more
Societies Show more
Series: Show more
Collections: Show more

Actions for selected content:

Select all | Deselect all
  • View selected items
  • Export citations
  • Download PDF (zip)
  • Save to Kindle
  • Save to Dropbox
  • Save to Google Drive

Save Search

You can save your searches here and later view and run them again in "My saved searches".

Please provide a title, maximum of 40 characters.
Cancel
×

1669 results in Computing: general interest

Page 18 of 84

  • Chapter 4 - Effects: What Tests Test

  • from Part I - Why We Use Statistics
  • Paul Cairns, University of York
  • Book:
    Doing Better Statistics in Human-Computer Interaction
    Published online:
    26 January 2019
    Print publication:
    07 February 2019, pp 53-68

  • Summary

    Effects and the size of effects are proposed as a key way to overcome the limitations of significance testing in modern statistics. However, traditionally, effects are usually added on to the statistical testing procedure. This chapter proposes instead thinking first about what effects to look for in the context of the research and its maturity within the discipline of HCI. The main types of effect, changes in location, stochastic dominance and (co)variation, are described. Consideration of which of these effects that current best knowledge can predict leads to choosing the test most suitable to find those effects.

  • 9 - Power and Two Types of Error

  • from Part II - How to Use Statistics
  • Paul Cairns, University of York
  • Book:
    Doing Better Statistics in Human-Computer Interaction
    Published online:
    26 January 2019
    Print publication:
    07 February 2019, pp 104-113

  • Summary

    The focus of statistical testing on significance can lead to the two types of error discussed in this chapter: finding a significant result when there is no underlying real effect; failing to get significance when there is in fact an underlying real effect. Though a blinkered approach to significance can be problematic for good data analysis, consideration of the two types of error is useful first to help think about sample sizes in studies but, second, it is a good way to assess the quality and robustness of statistical tests.

  • 16 - The Meaning of Factors

  • from Part II - How to Use Statistics
  • Paul Cairns, University of York
  • Book:
    Doing Better Statistics in Human-Computer Interaction
    Published online:
    26 January 2019
    Print publication:
    07 February 2019, pp 186-203

  • Summary

    Factor analysis is quite regularly seen in HCI to validate questionnaires, particularly those used to measure user experience. This chapter describes and illustrates the process of developing a questionnaire to measure a particular concept, starting from item generation through to factor analysis and interpretation. It introduces bifactor analysis as a more recent development in factor analysis that could help the interpretation of questionnaires made up of multiple factors.

  • 6 - A Cautionary Tail: Why You Should Not Do a One-Tailed Test

  • from Part II - How to Use Statistics
  • Paul Cairns, University of York
  • Book:
    Doing Better Statistics in Human-Computer Interaction
    Published online:
    26 January 2019
    Print publication:
    07 February 2019, pp 80-85

  • Summary

    A directional hypothesis predicts the specific way in which data are affected by an experimental manipulation. This, therefore, fits well with severe testing by making a concrete, explicit prediction. However, one-tailed testing associated with directional hypotheses regularly receives criticism because it can look like a way to make it easy to achieve statistical significance. This chapter describes why this is a problem and makes the case that despite the fit with severe testing, two-tailed testing is still the better way to do statistical analysis.

Doing Better Statistics in Human-Computer Interaction
  • Paul Cairns
  • Published online:
    26 January 2019
    Print publication:
    07 February 2019
  • Each chapter of this book covers specific topics in statistical analysis, such as robust alternatives to t-tests or how to develop a questionnaire. They also address particular questions on these topics, which are commonly asked by human-computer interaction (HCI) researchers when planning or completing the analysis of their data. The book presents the current best practice in statistics, drawing on the state-of-the-art literature that is rarely presented in HCI. This is achieved by providing strong arguments that support good statistical analysis without relying on mathematical explanations. It additionally offers some philosophical underpinnings for statistics, so that readers can see how statistics fit with experimental design and the fundamental goal of discovering new HCI knowledge.

Page 18 of 84