Here are some of my favorite statistics books, in no particular order. If you have a favorite book, e-mail it to us along with a brief statement about why you've found it useful, and we'll add it to the list.
Rowntree, Derek. (1981) Statistics without tears: A primer for non-mathematicians. New York: Scribners.
--with a title like that, what can I add?? This is a concise, user-friendly introduction to the basic foundations of all social statistics. Highly recommended for beginners and as a refresher for everyone.
Tabachnick, Barbara G., & Fidell, Linda S. (1996). Using multivariate statistics (3rd Ed.). New York: Harper Collins. [may be out in a more current revision already]
--this is the most user-friendly and comprehensive multivariate text I know of. It's very thorough, but very readable. Very little matrix algebra is used, the writing is clear, and the figures are very helpful.
Grimm, Laurence G., & Yarnold, Paul R. (199 ). Reading and understanding multivariate statistics. Washington, DC: American Psychological Association.
Grimm, Laurence G., & Yarnold, Paul R. (2000.) Reading and understanding MORE multivariate statistics. Washington, DC: American Psychological Association.
--this pair of books surveys the most commonly used multivariate techniques. Each chapter (one per technique) is clearly written and focuses on when and why you would use the approach. Discussion is clear and non-mathematical.
Cohen, J., Cohen, P., West, S.G., & Aiken, L.S. (2003). Applied multiple regression / correlation analysis for the behavioral sciences (3rd Ed.). Mahwah, NJ: Erlbaum.
--I will always have a soft spot in my heart for this book, because the first edition helped me get through my dissertation (1977). It provides a very comprehensive yet readable treatment of multiple regression. It's more mathematical than the books listed above, but if you work through it patiently, you will be greatly rewarded.
"How people have been accepted and treated within the context of a given society or culture has a direct impact on how they perform in that society. The "racial" worldview was invented to assign some groups to perpetual low status, while others were permitted access to privilege, power, and wealth. The tragedy in the United States has been that the policies and practices stemming from this worldview succeeded all too well in constructing unequal populations among Europeans, Native Americans, and peoples of African descent."
Excerpted from the American Anthropological Association's Statement on Race
Study of quantitative research methods includes the study of race and ethnicity. There are a wealth of resources available to family researchers. A few are listed below--I hope others will suggest more.
A History of Race Relations Research: First Generation Recollections, winner of the Gustavus Myers Center Outstanding Book Award, by John Stanfield.
Race and Ethnicity in Research Methods (quantitative and qualitative) edited by Dennis and Stanfield, This book includes 13 articles, one of which is by Samuel L. Myers, a noted University of Minnesota scholar.
For a current perspective on the role of race and ethnicity in U.S. society listen to NPR podcasts on race.
Do available quantitative methods help us advance family research based on systems theories? Which methods are particularly useful when theory suggests systems and subsystems are mutually influencing? If cultural, economic, and social systems, as well as family interaction patterns, are mutually influencing, what do we take as our unit of analysis?
Resources on system theory:
Rosenblatt, P.C. Metaphors of Family Systems Theory, 1994
Sameroff, A. J. Developmental Systems: Contexts and Evolution, Handbook on Child Development, Theoretical Models of Human Development, 4th edition.
Principia Cybernetica Web
Or, for a brief definition of systems theory see more...
Systems theories often involve interdisciplinary approaches that seek to understand elements in relation. They emphasize self-organizing properties of elements and subsystems in hierarchical systems. They are based on many different metaphors. A few key assumptions may include:
1. Wholeness or the sum is more than the parts. In order to understand a system it is necessary to look at relationships between parts. Systems thinkers might say, "properties emerge at the systems level."
2. Systems are self-regulating. Systems maintain and/or adapt to internal or environmental stimuli. A system requires some stability to exist.
3. System hierarchy: systems with sufficient stability often develop more complex hierarchies, potentially increasing their stability.
Systemic metaphors can jolt us out of our every day thinking about families and relationships. Every theory contains linguistic metaphor. Language and culture are inextricably linked and when we explore a new system metaphor we also explore how theory is rooted in culture. System theory can help us understand how we organize our thinking and how we might reorganize our thinking to gain insight.
“Social psychologists should treat interdependence not as a statistical nuisance that should be controlled, but rather as an important social psychological phenomenon that should be studied” Kashey & Kenny, 2002
Family researchers like this quote as much as social psychologists do because Kashey and Kenny are urging us to explore methods that allow us to study families--not to treat family data as though they were individual data.
Why is interdependence considered a nuisance? Even when families are selected for studies using random sampling, the data collected from multiple members of a family will be dependent. (Partners or married persons in a couple, for example, are more likely to be similar to each other than two randomly selected individuals are likely to be similar.) Regression models typically assume independence, along with linearity, normality, and homogeneity of variance of errors.
Researchers might be tempted to work around interdependence by studying individuals or by aggregating data or by assigning the same values to each member of a group. The latter two solutions can be statistically problematic and the former, well, we are back to the point of this entry: much can be gained by understanding the ways in which family members are and are not interdependent.
There are statistical methods, such as SEM or HLM, that accommodate--or take advantage of interdependence, depending on your point of view. These methods and others require a firm grasp of regression so it is best to start there. Here are two links to David A. Kenny's web site if you want to explore issues on this topic in more depth: dyadic analysis and unit of analysis.