Abramson, J.H. (1994). Making Sense of Data. 2nd Edition. NY: Oxford University Press. A good text for interactive learning courses. Brief explanations are given about major epidemiological concepts that are reinforced by exercises. Answers with explanations are given in following chapters. Really needs a good teacher to make the most of this text. Hard for those who (like me) likes to study concepts in a systematic way. However, does have a good section (at the end) on meta-analytic studies - how to conduct and critique them.
Ahlbom, A. (1993). Biostatistics for Epidemiologists. Boca Raton: Lewis Publishers. Good explanations of biostatistical procedures used by epidemiologists: p-value/confidence intervals; incidence/prevalence; crude/stratified analyses; multivariate models; exposure levels; meta-analysis. If you don't like mathematical formulas, skip it.
Bell, F.D. (1995). Basic Biostatistics, Concepts for the Health Sciences. The Almost No Math Stats Book. IA: Wm. C. Brown Publishers. THE BEST BIOSTATISTICS TEXTBOOK FOR THE NON-STATISTICIAN. If statistics is "sadistics" to you, read this book before you totally start counting the ways you hate math. The conceptual coverage will help you understand why you really do need to know biostatistics to make a case for your program, whether you are planning, implementing or evaluating it. Excellent explanations of standard errors and confidence intervals.
Baker, Stephen. (2008). The Numerati NY: First Mariner Books. Here is a book that I consider with an air of prescience in which mathematical algorithms are being used to the make decisions in every area of human endeavor. Here is a Brief Summary of the material he covers in his book.
It is somewhat scary about where we are heading in a world where so much information about us can be found on a variety of storage facilities. Imagine what can be done if someone and/or some machine can pull all these bits of information (data in math-speak) and use it to predict human behavior! Well, it is happening now, and Baker does his best in showing how mathematicians are mining the data that are being relentlessly gathered by a variety of entities. From financial to health information, there are tons of data all over the place.
They are beginning to refer to mountains of electronic data as Big Data, all there for the picking by those who know how. Imagine Big Data managers and analysts? Imagine being manipulated by those who have more information on you than you care to disclose? This is partially driven by young people today who think nothing of sharing everything online, sharing information about themselves indiscriminately. Basically, ethical questions should be asked regarding ownership of these data. If the data are about us, shouldn't we have a say about how the data can and cannot be used? Worth reading.
Brown, R.A., & Beck, J.S. (1990). Medical Statistics on Microcomputers. A guide to the appropriate use of statistical packages. London: British Medical Journal. Not as computer oriented as the title would lead you to believe, but actually an excellent biostatistical text that gets right to the point. How to handle, summarize and analyze data the right way. THE BEST TEXT FOR GIVING A CONCISE EXPLANATION OF THE MOST COMMON STATISTICAL PROCEDURES FOUND IN THE BIOMEDICAL LITERATURE.
Cryer, J.D., & Cobb, G.W. (1997) An Electronic Companion to Business Statistics. NY: Cognito Learning Media, Inc. A multi-media approach to statistics that should make this subject pleasing to the eye and brain.
Daniel, W.W. (1991). Biostatistics: A Foundation for Analysis in the Health Sciences. NY: John Wiley Publishers. Good explanation of hypothesis testing. Weak in non-parametric statistics.
Elston, R.C., & Johnson, W.D. (1994). Essentials of Biostatistics. Philadelphia: F.A. Davis. Chapters 1 (Descriptive Statistics) and 9 (Correlation and Regression) will give a good overview of these topics. Good summary explanations of specialized techniques (Chapter 11): MANOVA, MGLM, discriminate analysis, logistic regression, etc.
Gigerenzer, G. (2002). Calculated Risks. How To Know When Numbers Deceive You NY: Simon & Shuster MacMillan Co. An excellent book that introduces you to a better way of understanding statistics. Yes, it is possible to present statistical information in an easy-to-understand format that can be used for decision-making. The author's premise that presenting risk in natural frequencies is the right way to talk about risk is well-supported by examples and explanation. I think this book would be more useful if he also presented a curriculum with which schools and universities can incorporate his ideas into teaching math and statistics from elementary all the way into professional schools (i.e., medicine, law, etc.). Great promise for improving Public Health risk communication, too. Nothing is worst than people trying to fog you with statistics when they themselves don't even understand what they are saying!!! A must read.
Glaser, A.N. (1995). High-yield Biostatistics. PA: Williams & Wilkins, Inc. Written as a review text for medical students studying for the medical boards, Glaser covers all the basic biostatistical concepts needed to understand medical research and pass the medical board's biostatistical questions. The "Statistics in Epidemiology" chapter does a good job in explaining the common epi risk measurements found in the medical literature.
Gore, S.M. & Altman, D.G. (1992). Statistics in Practice. London: British Medical Association. A compilation of articles written by the authors dealing with the use of biostatistics in medical research published in the British Medical Journal. Altman manages to find the use of statistics in the medical literature to be as deplorable as the way I used grammar in my high school English compositions. You will learn what's "ludicrous" and "nonsense," as well as what he considers to be the unethical uses of statistics. Gore, a little more tolerant, takes a didactic approach. She shows the reader how to critically assess research design and statistical methods, and offers many useful pointers on how to conduct proper medical research. Excellent articles on confidence intervals, transforming data and data presentation.
Hanrahan, E.J., Madupu, G. (1994). Apelleton & Lange's Review of Epidemiology & Biostatistics for the USMLE. If 2x2 tables give you the chills, chill out with this review text. The 2x2 table is the standard epi tool for everything from evaluating screening tests, organizing data for risk factor studies and hypothesis testing. This text will clarify the table's various uses and is very good in explaining common epi risk measures as relative risk, odds ratio, absolute risk and attributable risk.
Hopkins, N., Mayne, J.W., & Hudson, J.R. (1992). Numbers for Everyday Life. WASH, DC: Visible Ink. A good review text about all the math you need to get by in life.
Kuzma, J.W.(1998). Basic Statistics for the Health Sciences. 3rd Edition CA: Mayfield Publishing Company. A good basic textbook of how statistics is used in conducting health-related research. Does provide some basic epidemiologic measures and public health application. Good organization and well-written.
Lang, T.A., & Secic, M. (1997). How to Report Statistics in Medicine. Annotated Guidelines for Authors, Editors, and Reviewers. PA:American College of Physicians. FINALLY, a guide on how medical research should be reported in the literature!! With this text in print, now there really is no reason for poorly written research reports to be in print, nor for any medical researcher not to know how to write up their research in an appropriate fashion. And for research consumers - this text will tell you what you should be looking for when you read the literature.
Le, C.T. & Boen, J.R. (1994). Health and Numbers. Basic Biostatistical Methods. NY: Wiley-Liss. Unfortunately, does not live up to its preface as a "friendly" biostatistical text. Warnings of what is not covered for being beyond the scope of the text makes the coverage spotty. Probably good course text if the teacher is willing to work on the problems with students in class. Greatest strength is in its analogy of hypothesis testing with trial by jury, and interpreting results from statistical procedures. Weakness lies in its lack of explanations for many of the formulas presented.
Morgan, S.E., Reichert, T., & Harrison, T.J. (2002). From Numbers to Words. Reporting Statistical Results for the Social Sciences. MA: Allyn & Bacon. A slim text of gentle reminders from three young academics on the proper way to report research statistics. As the authors put it, this is a supplemental text. It really does require a basic understanding of statistics. Perhaps, the saddest commentary is how poorly social science research is reported that the authors had to review some 5,000 research articles to come up with examples of the best that were STILL lacking in some way. Perhaps, the worst example can be found on pp. 24-25 in which I found 4 errors without much effort, in a three-sentence excerpt! And, these were just simple things like inconsistency between text and numbers and percentage totals! More comprehensive coverage for statistical reporting can be found in Lang & Sercic's 1997 excellent annotated guidelines.
Morton, R.F., Hebel, J.R., & McCarter, R.J. (1990). A Study Guide to Epidemiology and Biostatistics. Rockville, MD: Aspen Publications. Cram text. (Read Mausner & Bahn)
Motulsky, H. (1995). Intuitive Biostatistics. NY: Oxford University Press. A good textbook for explaining everything biostatistical to those who dread mathematical formulas. Motulsky makes a supreme effort in providing a rationale for the way biostatisticians think to the reasons why any particular statistical procedure is appropriate for hypothesis testing. Ideal for social science majors and those who love to read about biostatistics rather than look at formulas.
Pagano, M., & Gauvreau, K. (1993). Principles of Biostatistics. Belmont, CA: Duxbury Press. (THE BEST FOR SIMPLICITY IN UNDERSTANDING THE THEORY AND PRACTICE OF BIOSTATISTICS) Comes with a floppy of data sets to use with any computer statistical software.
Page, R.M., Cole, G.E. & Timmreck, T.E. (1995).Basic Epidemiological Methods and Biostatistics: A Practical Guide Book. Boston, MA: Jones and Bartlett Publishers. THE BEST EPIDEMIOLOGY / BIOSTATISTICS TEXTBOOK FOR LEARNING ALL THE BASICS. Besides providing the best history of Epidemiology I've seen in print, the authors take the reader through epidemiologic investigations, and give the best explanation of hypothesis testing that can be found in a biostatistics text.
Rosenthal, J.S. (2006). Struck by Lightning. The Curious World of Probabilities WASH DC: John Henry Press. Incredibly, an enjoyably readable book about probability! Rosenthal applies probability to the real world to explain whether events are truly coincidences or surprises, why casino always wins (even though you may have a lucky streak - that won't last), measuring social trends, research studies, margins of error, and junk e-mail. The most interesting point I learned was that spammers can afford to send out one million junk e-mails for a possible 15 responses, simply because paying so little to stuff our E-mail boxes pays off for them in the long run. Lesson - don't respond to junk E-mail, or make the !@#$% pay! Probability is probably the most hardest mathematical concept to grasp for the average person, but necessary to understand how inferential statistics work. This book will help you understand probability.
Rudas, T. (1998). Odds Ratios in the Analysis of Contingency Tables. (#119 of Quantitative Applications in the Social Sciences Series). CA: Sage Publications. Rudas makes a case for "variation independence." Unless if your life depended on explaining odds ratio, you can safely skip this one and study Hanrahan & Madupu's Apelleton & Lange's Review of Epidemiology & Biostatistics for the USMLE written for the statistically-challenged.
Selvin, S. (1991). Statistical Analysis of Epidemiologic Data. NY: Oxford University Press. Definitely not for anyone who considers themselves biostatistically-challenged. A real technical text that is quite comprehensive in covering statistical measures only principal investigators would be, or should be interested in. A great reference for understanding life tables, censored and truncated data, proportional hazards analyses and logistic modeling. Surprisingly, the earlier chapters on measures of risk, variation and bias were the hardest to get through.
Yates, K. (2020). The Math of Life & Death. 7 Mathematical Principles that Shape Our Lives. NY: Scribner. In 7 chapters, Kit Yates provides an interesting overview of how mathematics is very much a part of our daily lives. And, it doesn't all have to do with calculations. Because of our numerophobia, we tend to gloss over when numbers become a part of the conversation, which is why mathematics is misused and abused in all walks of life.
Because of mathematical errors, like the misplacement of a decimal point, wrong medication dosages can lead to death, as well as a mix-up in different measurements (liters vs. gallons) can result in running out of plane fuel while a country is switching over to the metric system. Yates shows how the misuse of statistics in the courtroom to sway the jury can result in wrongful imprisonment, and how the mistiming of warning alarms resulted in a bombing that could have been prevented.
Throughout the book, Yates offers real-world and interesting examples of how we really can't do with numbers at the same time offering historical gems on how we ended up with clocks having 24 hours, each hour with 60 minutes, and each minute with 60 seconds. His final chapter "Susceptible, Infective, Removed: How to Stop an Epidemic" was my favorite since it covered Public Health. It was too bad this book came out before the pandemic. I am sure Yates would have offered an enlightened look that how bad our record-keeping has been from underreporting cases and deaths to the lack of testing that should have been done to assess the prevalence of COVID-19. Maybe his next book can be devoted entirely to the topic.
Finally, Chapter 6 on the use of algorithms for everything offers a warning of overdependence on its use for everything. Sure, we want things automated, and we want it done in as orderly fashion as possible. Nevertheless, we should not forget that those who write the algorithms are humans, and humans make mistakes.
I have written enough computer programs to know that you really can tell a computer what to do. And, it will do it exactly the way your coding tells it to do. But, the interpretation still has to be done by humans, and they can always misinterpret the numbers. And, the programmer can introduce a bias in what data are to be included or excluded, which, of course, would result in possibly inaccurate data that could be misinterpreted, adding insult to injury.
It's like people today can plug in a set of numbers into a spreadsheet, and wah-la, a beautiful graph will show up that could be totally meaningless. And, "Even if some of the most complex mental tasks can be farmed out to an algorithm, matters of the heart can never be broken down into a simple set of rules. No code or equation will ever imitate the true complexities of the human condition." (p. 242).
I truly enjoyed this book that sought to explain mathematical concepts in a very understandable way. Yates does provide tables with numbers to illustrate his points, but no formulas that you would need to memorize like when you took it in school to understand what he is trying to say. You will come out with an appreciation of why we need numbers in our lives. After all, what would a birthday be without a number?
Zolman, J.F. (1993). Biostatistics. NY: Oxford University Press. Everything you ever wanted to know about ANOVA (analysis of variance), and how to design your research the right way. Contains 100 critiques of biological research projects that could have been done better if the researchers had only consulted J.F. Zolman first about proper research design.
Updated: 11/20/2022 R178
© Copyright 1999 - 2023 Betty C. Jung