Statistics for Applied Behavior Analysis Practitioners and Researchers
Statistics for Applied Behavior Analysis Practitioners and Researchers provides practical and useful content for individuals who work directly with, or supervise those who work directly with, individuals with ASD. This book introduces core concepts and principles of modern statistical analysis that...
Saved in:
| Main Authors | , |
|---|---|
| Format | eBook |
| Language | English |
| Published |
Chantilly
Elsevier Science & Technology
2023
Academic Press |
| Edition | 1 |
| Series | Critical Specialties in Treating Autism and Other Behavioral Challenges |
| Subjects | |
| Online Access | Get full text |
| ISBN | 0323998852 9780323998857 |
| DOI | 10.1016/C2021-0-00438-7 |
Cover
Table of Contents:
- Classification models -- Brief primer on interpreting models -- How good is this model, exactly? -- How well does my regression model fit my data? -- Variance account for (r2) -- Mean absolute error -- Mean squared error -- Root mean squared error -- Metrics that penalize model complexity -- How well does my classification model fit my data? -- Accuracy -- Predictive value -- True rates -- F1 (Fβ) -- False rates -- Matthew's correlation coefficient -- Loss metric summary -- How influential is each independent variable on my dependent variable? -- Refresher on free parameters -- Interpreting linear regression parameters -- Interpreting nonlinear regression parameters -- Interpreting classification model parameters -- Interpreting relative influence in multivariable models -- Chapter summary -- References -- 7 How fast can I get to an answer? Sample size, power, and observing behavior -- Introduction -- Enough is enough -- Observations=responses -- Observations=sessions -- Observations=participants -- Is the intervention effect I'm seeing real? -- How do I know if I've accounted for the variables' multiply controlling behavior? -- When to decide when to stop: Variations on a theme -- Chapter summary -- References -- 8 Wait, you mean the clock is always ticking? The unique challenges time adds to statistically analyzing time series data -- Introduction -- Statistical analysis of time series data for single-case designs -- Structured criteria -- Benefits of structured criteria approaches -- Limitations that time imposes on structured criteria approaches -- (Non)Overlap statistics -- Benefits of (non)overlap statistics -- Limitations that time imposes on (non)overlap statistics -- Effect size measures -- Benefits of effect size measures -- Limitations that time imposes on effect size measures -- Regression and classification modeling
- Other types of means -- Median -- Mode -- Summary of measures of central tendency -- Examples of how reporting central tendency in applied behavior analysis can be fun -- Rate4 of responding -- Percentage -- Chapter summary -- References -- 4 Just how stable is responding? Estimating variability -- Introduction -- Describing the spread of your data -- Min and max values -- Range -- Interquartile range -- Standard deviation -- Benefits and drawbacks of each description of spread -- Describing how well you know your measure of central tendency -- Standard error -- Confidence intervals -- Other flavors for describing variability in your data -- Variation ratio -- Aggregate percentage difference from mode -- Consensus -- Choosing and using measures of variance in applied behavior analysis -- References -- Supplemental: Why square the difference, and square root the final measure? -- 5 Just how good is my intervention? Statistical significance, effect sizes, and social significance -- Introduction -- Statistical significance -- Common criticisms of null hypothesis significance testing -- Comparing two datasets -- Comparing three or more datasets -- Categorical dependent variables and independent variables -- Summary of statistical significance -- Effect sizes -- Risk estimates -- Group difference indices -- Strength of association indices -- But, how about single-case experimental designs?! -- Social significance -- Chapter summary -- References -- 6 Oh, shoot! I forgot about that! Estimating the influence of uncontrolled variables -- Introduction -- Situating this chapter in the broader analytic landscape -- What does it mean to control something? -- How might we control for nonempirically controlled variables? -- Summarizing our situation -- Models of behavior -- Regression models -- Beginning with the familiar -- Generalizing to a bigger picture
- Front Cover -- Statistics for Applied Behavior Analysis Practitioners and Researchers -- Copyright Page -- Contents -- About the series editor -- About the authors -- Series Foreword -- Purpose -- Preface -- What this book is (and isn't) -- Onward, Ho! -- 1 The requisite boring stuff part I: Defining a statistic and the benefit of numbers -- Introduction -- Defining a statistic -- The benefits of numbers -- Models and model building -- Common myths and misconceptions about statistics -- Myth #1: Statistics=group design research -- Myth #2: Statistics=deductive reasoning=bad -- "Us vs. them" is a false dichotomy -- Statistics in applied behavior analysis -- Chapter summary -- References -- 2 The requisite boring stuff part II: Data types and data distributions -- Introduction -- What haven't we considered so far? -- Data types -- Discrete data -- Nominal data -- Ordinal data -- Quantitative discrete data -- Continuous data -- Data type summary -- Data distributions -- Probability distributions -- Discrete data distributions -- Binomial distribution -- Geometric distribution -- Negative binomial distribution -- Continuous data distributions -- Normal distribution -- Lognormal -- Poisson distribution -- Exponential distribution -- Quick recap and resituating ourselves -- References -- Supplemental: Probability distribution equations -- Binomial probability distribution -- Geometric probability distribution -- Negative binomial probability distribution -- Normal probability distribution -- Lognormal probability distribution -- Poisson probability distribution -- Exponential probability distribution -- 3 How can we describe our data with numbers? Central tendency and point estimates -- Introduction -- What is next on the agenda? -- High-level overview of the why and the how -- Common descriptions of central tendency -- Arithmetic mean
- Benefits of modeling approaches -- Limitations that time imposes on modeling approaches -- Nested approaches to modeling -- Benefits of nested modeling approaches -- Limitations of nested modeling approaches -- Chapter summary -- References -- 9 This math and time thing is cool! Time series decomposition and forecasting behavior -- Introduction -- Time series analyses through a different lens -- Time series decomposition -- The main idea -- Variations on a theme -- How do the components combine? -- Variations in decomposing time series data -- Adding additional components -- Forecasting behavior -- Exponential smoothing -- Simple exponential smoothing -- Exponential forecasting with trends -- Autoregressive Integrated Moving Average models -- Differencing our data -- Autoregressive models -- Moving average models -- Chapter summary -- References -- 10 I suppose I should tell someone about the fun I've had: Chapter checklists for thinking, writing, and presenting statistics -- Introduction -- Checklist and questions to answer when writing/presenting about statistics -- Data provenance -- Descriptive statistics -- Inferential statistics -- Modeling -- Sample size -- Time series considerations -- General consideration for efficiency -- References -- 11 Through the looking glass: Probability theory, frequentist statistics, and Bayesian statistics -- Introduction -- It's assumptions, all the way down -- Probability theory -- What is it? -- Why is this useful? -- What exactly do these numbers mean? -- Frequentist approach -- Interesting examples: What does this have to do with me? -- Bayesian approach -- Interesting examples: What does this have to do with me? -- Chapter summary -- Closing thoughts -- References -- Index -- Back Cover