It is often necessary for social scientists to study differences in groups, such as gender or race differences in attitudes, buying behaviour, or socioeconomic characteristics. When the researcher seeks to estimate group differences through the use of independent variables that are qualitative, dummy variables allow the researcher to represent information about group membership in quantitative terms without imposing unrealistic measurement assumptions on the categorical variables. Beginning with the simplest model, Hardy probes the use of dummy variable regression in increasingly complex specifications, exploring issues such as: interaction, heteroscedasticity, multiple comparisons and significance testing, the use of effects or contrast coding, testing for curvilinearity and estimating a piecewise linear regression.
To help researchers and students make the transition from the classroom and laboratory to research in the `real world', the authors reveal the pitfalls and suggest strategies to overcome problems in the design and planning of applied research. With a focus on how to refine research questions as real world events force deviations from the original research plan, they discuss how to study and monitor programme implementation and statistical power analysis. They also explore how to assess the human and material resources that will be needed at different times while conducting an applied research design to facilitate the management of data collection, analysis and interpretation.
Can the mentally ill be interviewed? What kind of reliability can be expected in their responses? What about the ethics of informed consent? Although standard social science methodologies have been used successfully to study mental health, researching issues with mentally ill individuals introduces unique theoretical and methodological issues. Focusing on the study of mentally ill adults at the individual level of analysis, this book explores such topics as: how theories of human behaviour that have been developed for a general population may have limited applicability to the population under study; how symptoms are defined and measured; ways to plan and implement research; uses of alternative data sources such as clinical charts; and the issues of research in multi-disciplinary settings.
Can the mentally ill be interviewed? What kind of reliability can be expected in their responses? What about the ethics of informed consent? Although standard social science methodologies have been used successfully to study mental health, researching issues with mentally ill individuals introduces unique theoretical and methodological issues. Focusing on the study of mentally ill adults at the individual level of analysis, this book explores such topics as: how theories of human behaviour that have been developed for a general population may have limited applicability to the population under study; how symptoms are defined and measured; ways to plan and implement research; uses of alternative data sources such as clinical charts; and the issues of research in multi-disciplinary settings.
This volume aims to help prospective educational researchers plan their research in schools more carefully. It focuses on such issues as: access and credibility in the school; traditional issues of designing research; questions that emerge as the design is imposed on the school culture and setting particularly with regard to school staff and student assessment; the length of interventions and whether or not to schedule follow-up studies; and how to interpret and communicate findings to schools and policy makers. Using personal experiences from their field research to illustrate key concepts, the authors have also included a research project to clarify the practical issues of school research.
This volume provides a basic framework for using visual data - namely still photographs - as a tool for social analysis. The authors determine the importance of theoretical assumptions in analyzing these data and provide advice on how to use photographs in cognitive, symbolist and structuralist research. The book is richly illustrated with examples ranging from Native American masks to perfume advertisements.
The goal for any social scientist doing a survey is to develop a rating on some attitude, value or opinion - a summated rating scale. Aimed at helping researchers construct more effective scales, Spector shows how to determine the number of items necessary, the appropriate amount of response categories and the most productive wording of items, how to sort good items from bad (including item-remainder coefficients and Cronbach's alpha) and how to validate a scale, including dimensional validity from factor analysis. Written in a user-friendly manner, the book concludes with a step-by-step account of how to develop a summated rating scale based on classical test theory.
This volume explores the doing of research - as a `journey' for those involved. It looks at the meanings of exemplary research practice. Authors' descriptions of the origins, experiences and outcomes of their own research are interwoven with commentaries on these by other major figures in the field. The book is an outstanding resource for all organizational researchers.
Income, employment, family composition, health and retirement - are all topics on which the Panel Study of Income Dynamics (PSID) has annually gathered information from more than 4,800 US households. Hill sets out to make this wealth of data more accessible to researchers by reviewing key analysis issues and identifying key variables for the user. Several detailed analysis examples show how to make use of the PSID to estimate earnings regressions, changes in women's income following divorce and the correlation between parents' income and a child's adult income, as well as to create a longitudinal poverty measure.
