Bootstrap

After giving a short course on resampling just a few days ago I had a chance to look through this book a little more carefully. I did not realize how many practical simulations studies the authors have summarized. The research they summarize is not available in any other book (with the exception of classification error rate estimation which is covered in my book and in McLachlan's). Their discussion at the end of each chapter is helpful. I still think that most practitioners will have difficulty with the theory but the simulation results can be used to provide guidelines for many important problems. Also they develop the theory to many of the more complicated problems. This is something I had not realized earlier.

This is another one of several recent books on bootstrap. The authors provide a systematic and theoretical treatment of the jackknife and the bootstrap in a variety of contexts including confidence intervals, survey sampling, linear and non-linear models, multivariate and nonparametric settings and time series and other dependent situations. The book is comprehensive, well-written and contains an extensive list of references. It is advanced and presupposes a fair amount of knowledge of mathematical statistics. It is a very useful reference for statistician, particularly ressearch statisticians. The authors state that their primary aims are "(1) to provide a systematic introduction to the theory of the jackknife, the bootstrap, and other resampling methods developed in the last twenty years; (2) to provide a guide for applied statisticians; practitioners often use (or misuse) the resampling methods in situations where no theoretical confirmation has been made; and (3) to stimulate the use of the jackknife and bootstrap and further developments of the resampling methods." The authors certainly achieve (1) and (3) but I think the book is at too high a level to reach most applied statisticians and so although they sometimes provide good practical advice based on the theory, most applied statisticians will not have the patience to wade through the theory to get to the advice.

I do not necessarily consider use of resampling methods in situations where there is no theoretical confirmation as misuse. Often applications come ahead of theory and it is worthwhile to try out new techniques even when good theory is lacking. Often, the usefulness of a method can be confirmed by simulation even when asymptotic theory is not available. Also asymptotic theory may be of no value (or could even be misleading) in practical small sample size situations.

This monograph is a treatise based on a series of lectures that Professor Beran gave at the Centre de Recherches Mathematiques (CRM) in Montreal Canada in 1989 (the monograph was published in 1991). It is an advanced theoretical text designed for graduate students and statistical researchers. It provides an introduction to the theory and contrasts it with other classical methods for second order corrections. Covers confidence regions and hypothesis tests and particularly the research contributions of Beran and his colleagues. More detailed treatment at the same level can be found in Hall (1992) The Bootstrap and Edgeworth Expansion and Shao and Tu (1995) The Jackknife and Bootstrap. Well written but very mathematical and difficult to get. It was published by the CRM and may now be out of print. I got my copy by ordering directly to the CRM. It may be possible to get it through companies like Amazon.com who have contacts at the major used book stores.

I wrote a book on bootstrap methods at the same time that Peter Hall was writing his. He kindly sent me an advance copy of the manuscript. This enabled me to incorporate some very useful information in my book. The material is advanced and rigorous. However the asymptotic results for Edgeworth and Cornish-Fisher expansions provide important insight into the advantages of bootstrap and the special modifications such as bootstrap iteration and various other bootstrap variants for confidence intervals including Efron's BCa method. It is well written but requires a good mathematical background and knowledge of advanced probability would be helpful. It is not easy reading even for Ph.D students and postdoctoral researchers but is certainly worth the effort.

This monograph is typical of the short monographs in the SAGE series. It provides a gentle (light on mathematics) introduction to the topic with social scientists in mind. Some applications are presented and it provides a good list of references. It was written prior to the now popular book by Efron and Tibshirani and others that followed. At times it is overly simplistic in order to provide concepts without much mathematics. However, most of the descriptions are accurate. It provides an intuitive understanding of bootstrap, presents some applications, exposes the wide variety of potential applications, puts things in an appropriate historical prospective and briefly describes situations where the bootstrap fails. My book "Bootstrap Methods" published by Wiley in 1999 has many of the same objectives and features of this monograph. For a thorough and more recent account of the literature and more detailed examples see my book. Other books including Efron and Tibshirani (1993), Davison and Hinkley (1997), Hall (1992), Shao and Tu (1995) and Manly (1997) provide more detail, theory and mathematics. This book is good though, as a place to get that first quick and gentle introduction to the subject.

Author Anna Lee Robe-Terry is a distant cousin of mine, who has written not just a book of recipes, but an evocation of the atmosphere of our northern West Virginia roots. Disabled by a chronic disease, she lost home, job and possessions until she moved onto the old Robe homestead in Marion County determined to survive. "If life gives you wild grapes, then make jelly" is her philosophy. She began investigating the wild plants that she had grown up with and educating herself in botany and the ways of the old settlers. Her recipes are wonderful just to read. I have tried the Snapping Turtle soup recipe myself and can recommend it as a definite change of pace from clam chowder. She also has a recipe for skunk (!) that resulted from a hilarious end to a hunting trip. I would recommend this book not only to people in the area, but those interested in its pioneer culture and folklore.

Raoul LePage and Lynn Billard have edited a collection of papers from a conference they organized on bootstrap methods in Ann Arbor Michigan in 1990 in conjunction with the annual Interface meetings connecting computer science and statistics. LePage also contributed to the collection of articles. Some very novel applications of bootstrap methods are included. Brad Efron who started the research explosion on bootstrap contributes with both introductory remarks and a thought-provoking article that raises 6 questions that came to him from his reseaarch on the bootstrap.

Subsampling is a form of data reuse similar to the bootstrap. However the idea of subsampling preceded the bootstrap. The original work is due to Hartigan in the 1970s and was motivation for some of Efron's ideas on bootstrap. The authors begin with a treatment of bootstrap theory. They then introduce subsampling under the assumption that the data are independent and identically distributed (i.i.d). They then provide the theoretical development of subsampling for i.i.d. data, stationary time series, non-stationary time series, random fields and marked point processes. The material is thorough and includes some of the authors' own original research. It is a highly advanced text that presupposes a first year graduate course in theoretical statistics.

In his 1982 monograph, Brad Efron describes the ordinary bootstrap resampling procedure which samples with replacement from the original data. The ordinary bootstrap resamples n times where n is the number of observations in the original sample and each observation is given equal probability of occurrence 1/n. He also suggests a generalization that is now referred to as the weighted or generalized bootstrap where the individual weights do not have to be equal. In this advanced monograph, Barbe and Bertail provide a summary of know asymptotic results for the weighted bootstrap based on work of Dudley, Gine and Zinn, Mason and Newton as well as some of their own.

Of particular interest to bootstrap researchers is Chapter 2 on "How to choose the weights" and Chapter 3 "Special forms of the bootstrap". Most notably, in Chapter 3, in cases where the equal weight (also called the ordinary or naive) bootstrap is inconsistent, they provide weights that lead to a consistent weighted bootstrap. This work, although sometimes cited in bootstrap texts(e.g. Chernick (1999) and Davison and Hinkley (1997)), is not given enough attention and is not mentioned in Hall (1992), Efron and Tibshirani (1993) or Shao and Tu (1997). In some cases it is because the texts predated this publication.

This monograph could be used as part of an advanced topics course on the bootstrap. Some proofs have been relegated to appendices which seems to me to detract from the presentation rather than improve it.

This title of this book does not accurately reflect the content. It is extremely vague, completely lacking in any technical detail regarding crop production, expected yield per acerage used, costs involved, marketing/selling etc. I can sum this book up in one sentence "I grew some flowers and sold them in my local shop and I dont know how or why I was successful at this practice." This really is a worthless book...the author has a very homely style which reinforces the impression that she is a complete amateur at this business. She runs out of anything useful to say after a couple of chapters and sets off to tell the life-story of her flower-growing acquaintances without paying much notice to the technical and scientific detail of their various ventures. If you are hoping to get some serious insights into growing flowers and developing marketing strategies for selling those flowers, forget it....do not buy this book.

great information. she interviewed growers and marketers of all types of florals, dried and fresh. her advice about growing, cutting, conditioning and marketing will be invaluable. written so that the layman understands. i like the many interview with people actually doing this (not a bunch of academic morons with no life experience just spouting rhetoric.).

If you are thinking about selling cut-flowers this book is straight talk from one who has 'been there'. Nothing important has been overlooked. The chapters on harvesting,conditioning,pricing and marketing are outstanding. Personality profiles of individual flowers lets the beginner choose with confidence.

This political biography of Teodoro Moscoso, the brain behind Operation Bootstrap, straddles between epical and history. Moscoso is presented as a hero who singlehandedly transformed Puerto Rican history. Moscoso's failures as U.S. ambassador to Venezuela and Director of the Alliance for Progress are presented as fatefull events out of his control.

Well written but too bent on presenting Moscoso as a hero, rather than as an actor of history, the book becomes a one sided apology rather than a balanced political biography.

Luis Negrón Hernandez: El por muchos años periodista de El Mundo y The San Juan Star, Alex W. Maldonado, aporta a nuestra historiografía: Teodoro Moscoso and Puerto Rico's Operation Bootstrap. Moscoso, a cargo de la promoción industrial de Puerto Rico a partir de la década del 1940, junto a otros extraordinarios tecnócratas, contribuyó como pocos al desarrollo y futuro de Puerto Rico. Lea cómo lo hicieron.

Maldonado opened with his book one of Puerto Rican history important moments, operation boostrap. To my generation Operation Bootstrap (Manos a la Obra) seems as something so far in time, but in reading Maldonados book I understand how this economic changes shape the lives of my family and therefore in the longrun me. Maldonado achieve to expose all the different aspect of the operation and all the problems it confroted. Maldonado proves is objectivity by recognizing the mistakes that were made and how they have influenced outcome events. I really recommended this book.