Linda S. Fidell’s research while affiliated with California State University, East Bay and other places

Assessment of aircraft noise-induced sleep disturbance is problematic for several reasons. Current assessment methods are based on sparse evidence and limited understandings; predictions of awakening prevalence rates based on indoor absolute sound exposure levels (SELs) fail to account for appreciable amounts of variance in dosage-response relationships and are not freely generalizable from airport to airport; and predicted awakening rates do not differ significantly from zero over a wide range of SELs. Even in conjunction with additional predictors, such as time of night and assumed individual differences in "sensitivity to awakening," nominally SEL-based predictions of awakening rates remain of limited utility and are easily misapplied and misinterpreted. Probabilities of awakening are more closely related to SELs scaled in units of standard deviates of local distributions of aircraft SELs, than to absolute sound levels. Self-selection of residential populations for tolerance of nighttime noise and habituation to airport noise environments offer more parsimonious and useful explanations for differences in awakening rates at disparate airports than assumed individual differences in sensitivity to awakening.

Awakenings attributable to transportation noise intrusions into residential sleeping quarters are surprisingly rare events. Current methods for estimating such awakenings from indoor sound exposure levels are problematic for several reasons. They are based on sparse evidence and limited understandings; they fail to account for appreciable amounts of variance in dosage-response relationships; they are not freely generalizable from airport to airport; and predicted awakening rates do not differ significantly from zero over a wide range of sound exposure levels. Even in conjunction with additional predictors, such as time of night and assumed individual differences in "sensitivity to awakening," nominally SEL-based predictions of awakening rates remain of limited utility, and are easily mis-applied and mis-interpreted. Probabilities of awakening are more closely related to SELs scaled in units of standard deviates of local distributions of aircraft SELs, than to absolute sound levels. Self-selection of residential populations for tolerance of nighttime noise and habituation to airport noise environments offer more parsimonious and useful explanations for differences in awakening rates at disparate airports than assumed individual differences in sensitivity to awakening.

A recent social survey of the annoyance of low amplitude sonic booms included both prompt and delayed-response questions about the annoyance of sonic booms heard by respondents in the home over the course of two weeks. Interviews were conducted via smartphone with 49 voluntary test participants. Most of the prompt annoyance judgments were made within about a minute of notice of a sonic boom. The delayed response judgments were solicited in the evening, at a time of the respondent's choosing. Prior analyses showed that dosage-response relationships between the prevalence of high annoyance and sonic boom amplitude were well predicted by CTL analysis. The current analyses investigated how individual, within-day, prompt annoyance judgments were related to end-of-day judgments of the annoyance of sonic booms. Preliminary analyses suggest that end-of-day annoyance judgments are not simply a linear sum or averaging of the annoyances of individual sonic booms.

ANOVA (analysis of variance) tests whether mean differences among groups on a single DV (dependent variable) are likely to have occurred by chance. MANOVA (multivariate analysis of variance) tests whether mean differences among groups on a combination of DVs are likely to have occurred by chance. For example, suppose a researcher is interested in the effect of different types of treatment (the IV; say, desensitization, relaxation training, and a waiting-list control) on anxiety. In ANOVA, the researcher chooses one measure of anxiety from among many. With MANOVA, the researcher can assess several types of anxiety (say, test anxiety, anxiety in reaction to minor life stresses, and so-called free-floating anxiety). After random assignment of participants to one of the three treatments and a subsequent period of treatment, participants are measured for test anxiety, stress anxiety, and free-floating anxiety. Scores on all three measures for each participant serve as DVs. MANOVA is used to ...

Preparatory data analyses (data screening) are conducted before a main analysis to assess the fit between the data and the assumptions of that main analysis. Different main analyses have different assumptions that vary in importance; violation of some assumptions can lead to the wrong inferential conclusion (and a potential failure of replication) while violation of others yields an analysis that is correct as far as it goes, but misses certain additional relationships in the data. Assumptions that are often relevant for continuous variables are normality of sampling distributions, pairwise linearity, absence of outliers and collinearity, independence of errors, and homoscedasticity; these are evaluated by both graphical and statistical methods. When violation is detected, variables are often transformed or an alternative analytic strategy is employed. Relevant issues in the choice of when and how to screen are the level of measurement of the variables, whether the design produces grouped or ungrouped data, whether cases provide a single response or more than one response, and whether the variables themselves or the residuals of analysis are screened. Keywords: assumptions; collinearity; distributions; errors; homoscedasticity; outliers; residuals; screening; transformation