Customer Reviews

Experimental and Quasi-Experimental Designs for Research

5 star:		(10)
4 star:		(3)
3 star:		(3)
2 star:		(0)
1 star:		(1)

 

 

Now I understand why this book is regarded as a classic. It's because the authors did such a great job of covering their subject (designs for research) when they wrote this book in the mid-1960s. But don't be put off by the fact that it's old. What they write is no less applicable to the 21st century reader than it was to readers of the 1960s. This is a great resource for anyone who's interested in designing an experiment - especially in the social sciences. Most of the examples that the authors use are drawn from the fields of education and psychology, but the reader will find their words readily applicable to other fields of inquiry.

This is a book written in the "old school" style. It's comprehensive AND relatively concise. I'm sure there are contemporary books written on this subject in more colloquial language, but I bet they are a pale imitation of this classic text.

The most important book on research designs to have, I use it weekly. It's brief, to the point, and 100% sound. I used it while in academics; now I find it particularly good for real-world (versus only laboratory) studies that need to be done quickly and on a budget. Though I've read it front to back, and have dog-earred lots of pages, it's value is that of a quick refresher and quick reference. A brief, inexpensive paperback.

Covers numerous true experimental designs along with inadequate designs. Based mostly in educational and social sciences research. A must have for the social sciences graduate student

Puts to rest the notion that simple case studies really "prove" anything, and helps students confront differences between trying to undermine one's cherished hypotheses and simply marshaling evidence on behalf of a point of view. This book is elegantly written, though a bit pricey. Still, I've yet to find a better quick overview -- though other authors have certainly tried. A classic.

While my copy is the 1963 version published by Rand McNally, it still sits on my bookshelf. It was a required text for a course in experimental design for my graduate program. Yes, it's expensive--and it was expensive when I bought it in 1974. But it's a one-stop source of quick, valuable information. It's especially useful when working with a twenty-something marketer who's trying to cut corners in a formative evaluation, or when working with an executive who's trying to fault a project on the wrong factors.

This famous and foundational discussion of research design belongs high on the shelf of every social science researcher. It presents twelve factors that threaten the internal and external validity of research studies and three common "pre-experimental" that do not adequately control for these threats. The authors then review three "true experimental designs" which offer high control and increased interpretability of results. Finally, the book reviews a number of "quasi-experimental" research designs commonly used in educational research. These designs control for most threats to validity and can be used with some additional care. Statistical procedures used to analyze data resulting from each design are also discussed.

This is a good reference book and a classic in the history of research. It is not necessarily the clearest or most thorough treatment of this topic, however. Readers looking for a readable introduction to experimental design in the context of other methods may benefit from John Cresswell's Research Design: Qualitative, Quantitative, and Mixed Methods Approaches. Those who would like a more extensive treatment of social science research designs should read Shadish, Cook and Campbell's Experimental and Quasi-Experimental Designs for Generalized Causal Inference. Put these two volumes a little lower on your shelf, where you can get at them.

Campbell & Stanley was a key resource when I was in graduate school. It was almost "Scripture" for those of us taking research methods courses. Even after all these years, I still consult this volume when I teach a course on research methods, to clarify questions about validity and so on.

This is a brief volume, with only 71 pages of text. But an awful lot of useful information is crammed into those pages!

The book considers three types of research designs--non-experiments (or, in the book's terms, "pre-experiments"), experiments, and quasi-experiments. They begin by defining the subject (Page 1): "By experiment we refer to that portion of research in which variables are manipulated and their effect upon other variables observed." A major issue is increasing "internal validity" and "external validity." The former? "Did in fact the experimental treatments make a difference in this specific experimental instance? Page 5)" The latter speaks to (Page 5): "To what populations, settings, treatment variables, and measurement variables can this effect be generalized?"

The emphasis in this volume is threats to internal and external validity and how we can address those threats.

Examples? Testing. If we test people at one point in time and retest them at a second point (using the same instrument), does the fact of having taken the test once affect the responses to the test later on? Or, instrumentation. If we use one test or measurement at one point in time and a different one later on, does that undermine our confidence in the results?

Even though this book came out in 1963, it is still a useful volume so many decades later. One can legitimately define this as a "classic" in the study of research methods.

A very concise book that gives an elegant treatment of experimental research. The text is from the 1960s, but the principles are timeless. The experiments might be in a wide range of fields; including anything in the social sciences.

The amount of statistics needed to follow the authors is minimal. Though in practise, with your actual experiments, you might need more statistical analysis. The book concentrates not on the mathematical details, but more on the overarching philosophy behind what you are trying to find or test. The intent is to design an experiment that is as simple as possible, and which can prove or disprove a focused hypothesis.

This survey originally appeared in N.L. Gage (Editor), Handbook of Research on Teaching, published by Rand McNally and Company in 1963 under the longer title "Experimental and Quasi-Experimental Designs for Research on Teaching." As a result, the introductory pages and many of the illustrations come from educational research. But as a study of the references will indicate, the survey draws from the social sciences in general, and the methodological recommendations are correspondingly broadly appropriate.

For the convenience of the user we have added a table of contents, a list of supplementary references, a name index and a subject index.
--- from book's Preface

The publisher should be hung for charging $60 for an 84 page book. Go to a university library and read it free.

As for content, the 20th Century produced 2 great works on the philosophy of science, this one and Kuhn's "Structure of Scientific Revolutions."

The only drawback is that the authors assume readers will understand what they read. Not so. After decades of applying the lessons of the book, I realized that few who read it understand its main points (some blame to authors for not pounding it home)-- 1] true experiments are not the gold standard of research, only the most efficient, and 2] identifying a quasi-experiment is just the start of the study design process, not the end.