E-raamat: Modern Statistical Methods for HCI

Thisbook critically reflects on current statistical methods used in Human-ComputerInteraction (HCI) and introduces a number of novel methods to the reader.Coveringmany techniques and approaches for exploratory data analysis including effectand power calculations, experimental design, event history analysis,non-parametric testing and Bayesian inference; the research contained in thisbook discusses how to communicate statistical results fairly, as well aspresenting a general set of recommendations for authors and reviewers toimprove the quality of statistical analysis in HCI. Each chapter presents [ R]code for running analyses on HCI examples and explains how the results can beinterpreted.ModernStatistical Methods for HCI is aimed at researchers and graduate students who have someknowledge of "traditional" null hypothesis significance testing, but who wishto improve their practice by using techniques which have recently emerged fromstatistics and related fields. This

book critically evaluates current practiceswithin the field and supports a less rigid, procedural view of statistics infavour of fair statistical communication.

Preface.- An Introduction to Modern Statistical Methods for HCI.- PartI: Getting Started With Data Analysis.- Getting started with [ R]: A Brief Introduction.-Descriptive Statistics, Graphs, and Visualization.- Handling Missing Data.-Part II: Classical Null Hypothesis Significance Testing Done Properly.- Effectsizes and Power in HCI.- Using R for Repeated and Time-Series Observations.- Non-ParametricStatistics in Human-Computer Interaction.- Part III : Bayesian Inference.- BayesianInference.- Bayesian Testing of Constrained Hypothesis.- Part IV: Advanced Modelingin HCI.- Latent Variable Models.- Using Generalized Linear (Mixed) Models inHCI.- Mixture Models: Latent Profile and Latent Class Analysis.- Part V:Improving Statistical Practice in HCI.- Fair Statistical Communication in HCI.-Improving Statistical Practice in HCI.