Richard A. Berk – författare

Statistical Learning from a Regression Perspective considers statistical learning applications when interest centers on the conditional distribution of the response variable, given a set of predictors, and when it is important to characterize how the predictors are related to the response. As a first approximation, this is can be seen as an extension of nonparametric regression. Among the statistical learning procedures examined are bagging, random forests, boosting, and support vector machines. Response variables may be quantitative or categorical. Real applications are emphasized, especially those with practical implications. One important theme is the need to explicitly take into account asymmetric costs in the fitting process. For example, in some situations false positives may be far less costly than false negatives. Another important theme is to not automatically cede modeling decisions to a fitting algorithm. In many settings, subject-matter knowledge should trump formal fitting criteria. Yet another important theme is to appreciate the limitation of one’s data and not apply statistical learning procedures that require more than the data can provide. The material is written for graduate students in the social and life sciences and for researchers who want to apply statistical learning procedures to scientific and policy problems. Intuitive explanations and visual representations are prominent. All of the analyses included are done in R.

Statistical Learning from a Regression Perspective considers statistical learning applications when interest centers on the conditional distribution of the response variable, given a set of predictors, and when it is important to characterize how the predictors are related to the response. As a first approximation, this is can be seen as an extension of nonparametric regression. Among the statistical learning procedures examined are bagging, random forests, boosting, and support vector machines. Response variables may be quantitative or categorical.

Real applications are emphasized, especially those with practical implications. One important theme is the need to explicitly take into account asymmetric costs in the fitting process. For example, in some situations false positives may be far less costly than false negatives. Another important theme is to not automatically cede modeling decisions to a fitting algorithm. In many settings, subject-matter knowledge should trump formal fitting criteria. Yet another important theme is to appreciate the limitation of one’s data and not apply statistical learning procedures that require more than the data can provide.

The material is written for graduate students in the social and life sciences and for researchers who want to apply statistical learning procedures to scientific and policy problems. Intuitive explanations and visual representations are prominent. All of the analyses included are done in R.

From the first edition . . .

"There are a number of outstanding features to this book. First, introducing the key concepts in an easy-to-understand fashion. Second, using specific examples as concrete illustrations of the methods being utilized. Another positive feature is the in-depth appendix, which provides many additional sources of information on the subject of program evaluation. . . . This comprehensive resource presents a realistic look at the potential and the pitfalls of program evaluation. The authors' examination of the issues from various angles produces a document that can be a useful guide to program evaluation."

--The Journal of Applied Rehabilitation Counseling

"Extremely interesting and well written. . . . Key terms are clearly introduced and the reader is given an excellent introduction to the role program evaluation might play in programs at different stages of development. A wide variety of interesting examples drawn from disparate fields of practice are used to illustrate key points. An appendix is provided to guide the reader toward the literature on program evaluation, professional associations, and organizations engaged in evaluation research."

--Canadian Public Administration

"The book has all the potential of becoming to program evaluation what Strunk and White's (1976) Elements of Style became for writing. Read frequently and faithfully, it could help evaluators do a better job."

--James W. Trent in Adult Residential Care Journal

Have you been looking for an overview of evaluation that will provide you with the big picture rather than so many details that you lose sight of what evaluation research is? Through the use of specific examples to illustrate evaluation research goals and methods, this book provides readers with an overview of the science and politics of evaluation research with comprehensive topics but selective details.

New to this edition is coverage of meta-analysis, selection models, and instrumental variables. In addition, the authors have expanded the coverage of analysis of data, evaluation when the units of analysis are entire organizations of political jurisdictions, and comparisons between evaluation research and other related fields. The rich mix of examples has been expanded to include more illustrations from environmental evaluation, and the most recent studies on welfare reform, managed mental health care, and law enforcement.

From the first edition . . .

"There are a number of outstanding features to this book. First, introducing the key concepts in an easy-to-understand fashion. Second, using specific examples as concrete illustrations of the methods being utilized. Another positive feature is the in-depth appendix, which provides many additional sources of information on the subject of program evaluation. . . . This comprehensive resource presents a realistic look at the potential and the pitfalls of program evaluation. The authors' examination of the issues from various angles produces a document that can be a useful guide to program evaluation."

--The Journal of Applied Rehabilitation Counseling

"Extremely interesting and well written. . . . Key terms are clearly introduced and the reader is given an excellent introduction to the role program evaluation might play in programs at different stages of development. A wide variety of interesting examples drawn from disparate fields of practice are used to illustrate key points. An appendix is provided to guide the reader toward the literature on program evaluation, professional associations, and organizations engaged in evaluation research."

--Canadian Public Administration

"The book has all the potential of becoming to program evaluation what Strunk and White's (1976) Elements of Style became for writing. Read frequently and faithfully, it could help evaluators do a better job."

--James W. Trent in Adult Residential Care Journal

Have you been looking for an overview of evaluation that will provide you with the big picture rather than so many details that you lose sight of what evaluation research is? Through the use of specific examples to illustrate evaluation research goals and methods, this book provides readers with an overview of the science and politics of evaluation research with comprehensive topics but selective details.

New to this edition is coverage of meta-analysis, selection models, and instrumental variables. In addition, the authors have expanded the coverage of analysis of data, evaluation when the units of analysis are entire organizations of political jurisdictions, and comparisons between evaluation research and other related fields. The rich mix of examples has been expanded to include more illustrations from environmental evaluation, and the most recent studies on welfare reform, managed mental health care, and law enforcement.

Berk has incisively identified the various strains of regression abuse and suggests practical steps for researchers who desire to do good social science while avoiding such errors." --Peter H. Rossi, University of Massachusetts, Amherst

"I have been waiting for a book like this for some time. Practitioners, especially those doing applied work, will have much to gain from Berk's volume, regardless of their level of statistical sophistication. Graduate students in sociology, education, public policy, and any number of similar fields should also use it. It will also be a useful foil for conventional texts for the teaching of the regression model. I plan to use it for my students as a text, and hope others will do the same." --Herbert Smith, Professor of Demography & Sociology, University of Pennsylvania

Regression is often applied to questions for which it is ill equipped to answer. As a formal matter, conventional regression analysis does nothing more than produce from a data set a collection of conditional means and conditional variances. The problem, though, is that researchers typically want more: they want tests, confidence intervals and the ability to make causal claims. However, these capabilities require information external to that data themselves, and too often that information makes implausible demands on how nature is supposed to function. Convenience samples are treated as if they are random samples. Causal status is given to predictors that cannot be manipulated. Disturbance terms are assumed to behave not as nature might produce them, but as required by the model.

Regression Analysis: A Constructive Critique identifies a wide variety of problems with regression analysis as it is commonly used and then provides a number of ways in which practice could be improved. Regression is most useful for data reduction, leading to relatively simple but rich and precise descriptions of patterns in a data set. The emphasis on description provides readers with an insightful rethinking from the ground up of what regression analysis can do, so that readers can better match regression analysis with useful empirical questions and improved policy-related research.

"An interesting and lively text, rich in practical wisdom, written for people who do empirical work in the social sciences and their graduate students." --David A. Freedman, Professor of Statistics, University of California, Berkeley

Money, Work, and Crime: Experimental Evidence presents the complete details of the Department of Labor''s $3.4 million Transitional Aid Research Project (TARP), a large-scale field experiment which attempted to reduce recidivism on the part of ex-felons. Beginning in January 1976, some prisoners released from state institutions in Texas and Georgia were offered financial aid for periods of up to six months post-release. Payments were made in the form of Unemployment Insurance benefits. The ex-prisoners who were eligible for payments were compared with control groups released at the same time from the same institutions. The control groups were not eligible for benefits. The assumption that modest levels of financial help would ease the transition from prison life to civilian life was partially supported. Ex-prisoners who received financial aid under TARP had lower rearrest rates than their counterparts who did not receive benefits and worked comparable periods of time. Those receiving financial aid were also able to obtain better-paying jobs than the controls. However, ex-prisoners receiving benefits took longer to find jobs than those who did not receive benefits. The TARP experiment makes a strong contribution both to an important policy area—the reduction of crime through reducing recidivism—and to the further development of the field and experiment as a policy research instrument.

This textbook considers statistical learning applications when interest centers on the conditional distribution of a response variable, given a set of predictors, and in the absence of a credible model that can be specified before the data analysis begins. Consistent with modern data analytics, it emphasizes that a proper statistical learning data analysis depends in an integrated fashion on sound data collection, intelligent data management, appropriate statistical procedures, and an accessible interpretation of results. The unifying theme is that supervised learning properly can be seen as a form of regression analysis. Key concepts and procedures are illustrated with a large number of real applications and their associated code in R, with an eye toward practical implications. The growing integration of computer science and statistics is well represented including the occasional, but salient, tensions that result. Throughout, there are links to the big picture.The third edition considers significant advances in recent years, among which are:the development of overarching, conceptual frameworks for statistical learning;the impact of  “big data” on statistical learning;the nature and consequences of post-model selection statistical inference;deep learning in various forms;the special challenges to statistical inference posed by statistical learning;the fundamental connections between data collection and data analysis;interdisciplinary ethical and political issues surrounding the application of algorithmic methods in a wide variety of fields, each linked to concerns about transparency, fairness, and accuracy.This edition features new sections on accuracy, transparency, and fairness, as well as a new chapter on deep learning. Precursors to deep learning get an expanded treatment. The connections between fitting and forecasting are considered in greater depth. Discussion of the estimation targets for algorithmic methods is revised and expanded throughout to reflect the latest research. Resampling procedures are emphasized. The material is written for upper undergraduate and graduate students in the social, psychological and life sciences and for researchers who want to apply statistical learning procedures to scientific and policy problems.

This textbook considers statistical learning applications when interest centers on the conditional distribution of a response variable, given a set of predictors, and in the absence of a credible model that can be specified before the data analysis begins. Consistent with modern data analytics, it emphasizes that a proper statistical learning data analysis depends in an integrated fashion on sound data collection, intelligent data management, appropriate statistical procedures, and an accessible interpretation of results. The unifying theme is that supervised learning properly can be seen as a form of regression analysis. Key concepts and procedures are illustrated with a large number of real applications and their associated code in R, with an eye toward practical implications. The growing integration of computer science and statistics is well represented including the occasional, but salient, tensions that result. Throughout, there are links to the big picture.

The third edition considers significant advances in recent years, among which are:

the development of overarching, conceptual frameworks for statistical learning;the impact of  “big data” on statistical learning;the nature and consequences of post-model selection statistical inference;deep learning in various forms;the special challenges to statistical inference posed by statistical learning;the fundamental connections between data collection and data analysis;interdisciplinary ethical and political issues surrounding the application of algorithmic methods in a wide variety of fields, each linked to concerns about transparency, fairness, and accuracy.

This edition features new sections on accuracy, transparency, and fairness, as well as a new chapter on deep learning. Precursors to deep learning get an expanded treatment. The connections between fitting and forecasting are considered in greater depth. Discussion of the estimation targets for algorithmic methods is revised and expanded throughout to reflect the latest research. Resampling procedures are emphasized. The material is written for upper undergraduate and graduate students in the social, psychological and life sciences and for researchers who want to apply statistical learning procedures to scientific and policy problems.

This textbook considers statistical learning applications when interest centers on the conditional distribution of a response variable, given a set of predictors, and in the absence of a credible model that can be specified before the data analysis begins. Consistent with modern data analytics, it emphasizes that a proper statistical learning data analysis depends in an integrated fashion on sound data collection, intelligent data management, appropriate statistical procedures, and an accessible interpretation of results. The unifying theme is that supervised learning properly can be seen as a form of regression analysis. Key concepts and procedures are illustrated with a large number of real applications and their associated code in R, with an eye toward practical implications. The growing integration of computer science and statistics is well represented including the occasional, but salient, tensions that result. Throughout, there are links to the big picture.The third edition considers significant advances in recent years, among which are:the development of overarching, conceptual frameworks for statistical learning;the impact of  “big data” on statistical learning;the nature and consequences of post-model selection statistical inference;deep learning in various forms;the special challenges to statistical inference posed by statistical learning;the fundamental connections between data collection and data analysis;interdisciplinary ethical and political issues surrounding the application of algorithmic methods in a wide variety of fields, each linked to concerns about transparency, fairness, and accuracy.This edition features new sections on accuracy, transparency, and fairness, as well as a new chapter on deep learning. Precursors to deep learning get an expanded treatment. The connections between fitting and forecasting are considered in greater depth. Discussion of the estimation targets for algorithmic methods is revised and expanded throughout to reflect the latest research. Resampling procedures are emphasized. The material is written for upper undergraduate and graduate students in the social, psychological and life sciences and for researchers who want to apply statistical learning procedures to scientific and policy problems.

This textbook considers statistical learning applications when interest centers on the conditional distribution of the response variable, given a set of predictors, and when it is important to characterize how the predictors are related to the response. This fully revised new edition includes important developments over the past 8 years. Consistent with modern data analytics, it emphasizes that a proper statistical learning data analysis derives from sound data collection, intelligent data management, appropriate statistical procedures, and an accessible interpretation of results. As in the first edition, a unifying theme is supervised learning that can be treated as a form of regression analysis. Key concepts and procedures are illustrated with real applications, especially those with practical implications. The material is written for upper undergraduate level and graduate students in the social and life sciences and for researchers who want to apply statistical learning procedures to scientific and policy problems. The author uses this book in a course on modern regression for the social, behavioral, and biological sciences. All of the analyses included are done in R with code routinely provided.