Search Results

In this chapter a number of methods that make use of both graphical procedures and statistical methods are described and illustrated. Methods such as trend lines, median lines, and graphical representations of background variability are described and illustrated. Also described is a method especially designed for use by practitioners. Some of these methods make use of procedures adopted from statistical process control methodology. A recommended analysis procedure is described that makes use of both median-based and trend-line based methods for representing background variability.

This chapter provides a brief introduction to some of the epidemiologic and statistical methods for and challenges to gathering and analyzing the data that underlie the research presented in this volume and in the field of public mental health as a whole. It focuses on some of the data and methodological complexities particularly common in public mental health research. It explores three fundamental types of questions relevant to public mental health: estimating rates of disorders in a population across people, place, and time; examining risk and protective factors associated with particular disorders; and exploring interventions to prevent disorders or to treat them once they emerge.

This chapter begins by describing vitalism and materialism. The name “vitalism” is often given to those doctrines which have used the hypothesis that the phenomena of living organisms are due to some process which is essentially identical in its nature with the process exemplified by people's conscious voluntary activities. On the other hand, some things and events in the natural world—such as the recurrent movements of the heavenly bodies and the processes which attend the workings of machines—seem to be in many respects essentially different from the processes which result from people's plans, choices, and voluntary deeds. What is called a “mechanical theory of nature” or “materialism” undertakes to account for the vital processes, for the activities of organisms. The chapter then considers the three classifications of scientific methods: the historical, the mechanical, and the statistical.

Many organisms have undergone genome-wide or local chromosome duplication events during their evolution. As a result, many genes are represented as several paralogs in the genome with related but distinct functions (gene families). Since gene duplication is thought to have provided the raw materials for functional innovations, it is desirable to identify amino acid sites that are responsible for functional divergence from the sequence analysis of a gene family. A series of statistical models has been developed, based on the principle that functional divergence between duplicate genes is highly correlated with the change of evolutionary rate after the gene duplication. This chapter discusses these statistical and computational methods. These include the Poisson-gamma model for protein sequence evolution, the Markov chain model for type-I functional divergence, and statistical methods for type-II functional divergence.

This chapter describes statistical methods for inferring and quantifying social transmission in groups of animals in the wild, or in “captive” groups of animals in naturalistic social environments. In particular, it considers techniques for analyzing time-structured data on the occurrence of a particular behavior pattern, or behavioral trait, in one or more groups. For the most part, the focus is on cases where a novel trait spreads through one or more groups. Following standard terminology in the field of social learning, the spread of a trait through a group is referred to as a diffusion, and the resulting data as diffusion data. The methods include diffusion curve analysis and network-based diffusion analysis. For the latter, inclusion of individual-level variables is taken into account, along with model selection and inference, modeling of multiple diffusions, choosing a social network, and “untransmitted” social effects. The chapter also examines the spatial spread of a behavioral trait.

This chapter examines how the qualitative and quantitative research traditions empirically assess theories about mechanisms when making causal inferences. In the qualitative paradigm, researchers carry out this assessment by attempting to observe causal mechanisms through process tracing and through the analysis of causal-process observations. In the qualitative paradigm, the within-case analysis of specific cases is combined with the effort to observe mechanisms. By contrast, statistical methods are not designed to observe mechanisms within particular cases. The chapter considers the importance of mechanisms in causal inference as well as the use of process tracing in multimethod vs. qualitative research. It shows that multimethod research, which integrates regression and case study analysis, is increasingly regarded as a best practice.

This book explores social learning concepts and methods as well as new developments in the field. These methods include: experimental and statistical methods that allow researchers to categorize cases of social learning according to their underlying psychological processes and learning mechanisms; neuroscientific methods for identifying the brain structures, neural circuitry, and physiological processes underlying both social learning and social influences on decision making; and mathematical methods for predicting the pattern of diffusion of novel learned innovations, and for modeling cultural evolution and gene-culture coevolution. This introductory chapter presents some definitions such as “social learning,” “imitation,” “innovation,” and “social transmission” and explains why social learning is an important field of study. It also provides an overview of the chapters that follow.

Because social science research has a low utilitarian value, little attention is given to such research and social scientists are probably receiving a lot less respect than they deserve. Higher standards for reliability should then be set for social science research so that more respect would be given to the researchers and the findings would have more value for society. This chapter presents some research tactics that will hopefully improve the results of social science research or at least filter unnecessary noise. The chapter encourages researchers to challenge their own thinking to be able to demonstrate the validity of their knowledge through observation and displacing situations from equilibria. Also, the chapter introduces statistical methods that would yield the production of reliable knowledge. Lastly, researchers should be able to create consensus about what they know.

This chapter is divided into two parts. The first part discusses systematic reviews and the role of meta-analysis. The second part presents the most widely used statistical methods for meta-analysis and related issues such as exploring differences between studies. Self-test questions are provided at the end of the chapter.

This chapter describes statistical methods for taking account of unequal attrition, that is, different follow-up times across exposed and unexposed groups in a cohort study. It considers methods for analyzing time to an event as an outcome in its own right. The chapter defines the outcome as the time until disease onset. From this perspective, a nondiseased subject in the study is not a control as in a case-control study, but someone who has not yet developed the disease. To analyze disease incidence data from this perspective, methods that come under the interchangeable headings of survival analysis, time-to-event analysis, or failure-time analysis are used.

This chapter focuses on social learning strategies—functional rules specifying what, when, and who to copy. There are many plausible social learning strategies. Individuals might disproportionately copy when asocial learning would be difficult or costly, when they are uncertain of what to do, when the environment changes, when established behavior proves unproductive, and so forth. Likewise, animals might preferentially copy the dominant individual, the most successful individual, or a close relative. This chapter presents evidence for some of the better-studied learning heuristics and describes statistical procedures for identifying which social learning strategies are being deployed in a data set. It examines “who” strategies, which cover frequency-dependent biases, success biases, and kin and age biases, as well as “what” strategies, random copying, and statistical methods for detecting social learning strategies. Finally, it evaluates meta-strategies, best strategies, and hierarchical control.

This chapter explores how missionaries, starting in the mid-nineteenth century, developed a method for assessing the degree of faith of Christians in communities in Manchuria. Far from being a passing experiment, missionaries’ use of statistical methods and quantitative language to measure the religiosity of local converts became a central concern of the Church, as important as translating texts to and from Latin, French, and Chinese. In creating this method, missionaries calculated the impact of their efforts and defined what it meant to be a “good” Christian.

This chapter discusses the history of epidemiological methods. It provides a personal account of how the three authors view the evolution of study designs, statistical methodology, and the development of epidemiological computer software that aided progress in the field. Whenever appropriate, emphasis is given to the view from the Americas. However, in the interest of providing a seamless historical perspective, key scientific developments from other continents are also included.

Intergenerational data necessarily reflect the time and place that the different generations of participants were living in. This chapter aims first to introduce simple concepts to provide an understanding of the founding assumptions and principles, before moving on to more complex analytic methods. As the objectives of analyses may vary substantially across intergenerational studies, there is no easy guideline for analyses, except perhaps that some a priori clarity on the main associations of interest is crucial. Since parents and their offspring are genetically related, intergenerational studies are to some extent genetically informative even if no genotyping was performed. Much of the analyses are concerned with identifying or unravelling the relationship between outcomes and genetic and environmental factors. Ways of handling missing data as well as approaches to deal with non-paternity are also discussed. Illustrative examples are drawn from the two cohort studies.