TY - CHAP
T1 - Dichotomous outcome variables
AU - Leppink, Jimmie
PY - 2019
Y1 - 2019
N2 - The main take home message from Part I of this book is that whether we deal with simple group comparisons (Chap. 2), measurement issues (Chap. 3) or missing data (Chap. 4), data-analytic choices ought to be driven by the questions that led us to do the experiment, by the features of the experimental design that resulted from our questions, and by the nature of the data acquired in the experiment (the QDA bridge from Chap. 1). In this second part of the book, this approach is applied to different types of outcome variables. In this first chapter of Part II, we focus on dichotomous outcome variables. Examples of dichotomous variables are pass/fail decisions in tests, recover/failure to recover distinctions in mental health-related contexts, and event occurrence/event absence. This chapter discusses different plots and statistics for experiments in which a dichotomous outcome variable is measured once in time as well as for experiments in which the outcome variable is a dichotomous variable in the form of event occurrence/absence in a particular time period. Although the latter is commonly associated with survival analysis in hospitals, (simulated) traffic research for example may focus on the occurrence or absence of accidents in different groups of participants studied.
AB - The main take home message from Part I of this book is that whether we deal with simple group comparisons (Chap. 2), measurement issues (Chap. 3) or missing data (Chap. 4), data-analytic choices ought to be driven by the questions that led us to do the experiment, by the features of the experimental design that resulted from our questions, and by the nature of the data acquired in the experiment (the QDA bridge from Chap. 1). In this second part of the book, this approach is applied to different types of outcome variables. In this first chapter of Part II, we focus on dichotomous outcome variables. Examples of dichotomous variables are pass/fail decisions in tests, recover/failure to recover distinctions in mental health-related contexts, and event occurrence/event absence. This chapter discusses different plots and statistics for experiments in which a dichotomous outcome variable is measured once in time as well as for experiments in which the outcome variable is a dichotomous variable in the form of event occurrence/absence in a particular time period. Although the latter is commonly associated with survival analysis in hospitals, (simulated) traffic research for example may focus on the occurrence or absence of accidents in different groups of participants studied.
U2 - 10.1007/978-3-030-21241-4_5
DO - 10.1007/978-3-030-21241-4_5
M3 - Chapter
SN - 978-3-030-21240-7
T3 - Springer Texts in Education
SP - 79
EP - 90
BT - Statistical methods for experimental research in education and psychology
PB - Springer
CY - Switzerland
ER -