BIOSTATISTICS FOR DUMMIES is a 390 page book on biostatistics where the emphasis is on clinical trials. From my own experience as a medical writer, I know that Clinical Study Protocols, Clinical Study Reports, Investigator's Brochures, and so on, make frequent use of statistical concepts and formulas such as, alpha value, type I error, type II error, Kaplan-Meier plots, Z statistic, t statistic, P value, confidence interval, standard deviation, and others. Most of these formulas are described in this book. This book takes care to explain concepts that might be overlooked in other statistics textbooks, such as the fact that the determination of a P value, "is arbitrary, it depends on how much of a risk you're willing to take of being fooled by random fluctuations, that is, of making a Type I error. Over the years, the value of 0.05 has become accepted as a reasonable criterion for declaring significance" (page 43). This type of description provides a good background for the medical writer. For example, this morning I was reading a Clinical Study Protocol, which had been submitted with a SPA, where the P value for interim analysis was 0.002 and where the P value for analysis when the clinical trial was completed was 0.04. The book fails to provide guidance on how to solve any formulas in biostatistics. The book fails to include any problem sets, and it certainly does not include any answers. This book will not enable any novice to understand any statistical formulas. On the other hand, if you already understand biostatistics and know how to work the formulas by hand, then this book will be useful for tying all of the formulas together, and for providing a "big picture" of biostatistics. The book takes the same tactic as that taken by actor Robert Preston in THE MUSIC MAN. This tactic is as follows: If you just "think" about the task at hand, without receiving any training and without engaging in any hard work or practice, then you will somehow (magically) acquire skill in performing the task. Unfortunately, Robert Preston's advocated technique will never succeed in the real-world situation. In the same way, BIOSTATISTICS FOR DUMMIES cannot succeed.
BIOSTATISTICS FOR DUMMIES has a 12 page table of contents, which might be considered excessive for a book that is only 390 pages. At any rate, this is only a comment on style. One theme of this book, is statements about mathematics being frightening. These statements occur, e.g., on pages 9, 15, 17, 18, 20, 28, 31, 45, 51, 154, and 369. For example, the book states that the summation symbol "strikes terror into the hearts of so many people" (page 28). On page 51, the book states that, "there's just no good reason to put yourself through the misery of mind-numbing calculations and waste your precious time." On page 154, we read about, "a dizzying collection of tests with exotic-sounding names . . . enough to make your head spin." It is the case that this book avoids all calculations in order to avoid frightening the readers.
At any rate, many of the common formulas in biostatistics involve only high school arithmatic (adding, subtracting, multiplying, and dividing) and can easily be solved with a pencil and paper. I respectfully disagree with the notion that biostatistics can be learned or can be understood by any "teaching method" that refrains from actually working through the formulas. BIOSTATISTICS FOR DUMMIES does not contain a single worked formula. There are no working examples. There are no problem sets. Although many of the formulas are presented, the reader is not given any data for plugging into these formulas. There are no examples of solved problems. In my opinion, this book is better suited for people already with a practical working knowledge in biostatistics, who are interested in account of the "big picture," and who are interested in learning if there are any formulas or concepts that have been missed.
WHAT TO DO. I recommend the following books. I have not found any biostatistics book that provides working examples for all of the common equations, however, if you buy three or four of the following books, then your will be on your way to grasping the statistical concepts that are needed for medical writing for FDA submissions. The following compares some of the books that I have used, and from this account, you can choose the books that teach the indicated formulas.
KAPLAN-MEIER PLOTS (survival plots). This is about Medical Statistics 2nd ed. by Kirkwood and Sterne. Kirkwood (pages 272-286) discloses survival plots. Pharmaceutical Statistics by David S. Jones fails to disclose Kaplan-Meier curves. For this topic, I refer the reader to the excellent discussion in Dawson & Turner. But Lange (pages 221-244) is by far the best for this topic.
SAMPLE SIZE AND POWER CALCULATIONS. Kirkwood (pages 417-418) is the best of the books for sample size calculations, as Kirkwood provides a straightforward formula. The book by David S. Jones discloses sample size and power calculations on pages 172-179. The Jones narrative seems to come to a dead end on page 175, where delta is revealed as equaling 2.5 mL. But according to my calculations, delta should be 1.2 mL (50-48.8=1.2 mL). Lange (page 127) seems to lead to a dead end (since Lange fails to explain where the number -0.84 comes from).
FORMULA for CONFIDENCE INTERVAL FOR LARGE SAMPLES. Pages 60-63 of Kirkwood covers this topic, while pages 135-141 of Jones covers this topic. For two different treatments (study drug group and placebo group), Kirkwood's coverage is on page 67-70, and Jones' coverage is on pages 141-144.
FORMULA for CONFIDENCE INTERVAL FOR SMALL SAMPLES. Kirkwood's pages 53-55 is equivalent to pages 151-154 of Jones, for this simple formula. But Kirkwood's presentation of general information on Confidence Intervals (pages 50-53 of Kirkwood) is far superior to any presentation in Jones on this particular topic. Hence, I would recommend readers consult both Jones and Kirkwood for this formula.
FORMULA for HYPOTHESIS TESTING FOR LARGE SAMPLES. Kirkwood's treatment is on page 46-49, and 69, while Jones's treatment is on pages 87-125. Kirkwood has only two examples, but Jones has seven examples. In this respect, Jones is much better than Kirkwood. Both books teach us that once we have calculated the Z statistic, there are two things we can do with it. First, we can plug it into a table of STANDARD NORMAL DISTRIBUTION and get the P value (a probability). Second, we can compare it with a standard number, e.g., "1.96" for use in hypothesis testing, that is, for getting a yes/no answer (page 157-159 of Jones, page 244 of Rosner). To write this commentary, I needed to piece together information from several books. None of the books provides an organized stand-alone account of this formula.
FORMULA for HYPOTHESIS TESTING FOR SMALL SAMPLES. Kirkwood's treatment is on page 66, while Jones' treatment is on pages 168-178. These books teach that once we have the t statistic, there are two things we can do with it. First, we can plug it into a table (Table A4 of Kirkwood) to obtain a P value, and get a probability. Second, we can compare it to the "critical value of the t distribution" for hypothesis testing, and get a yes/no answer (Lange, page 101, 107). To write this commentary, I needed to piece together information from several books. None of the books provides an organized stand-alone account of this formula.
Lange provides a DECISION TREE for determining which statistics formula to use. This DECISION TREE is located on the inside front cover, but it does not come with any written commentary. Lange has the right idea, as far as efficacy in statistics teaching is concerned. But Lange does not go far enough.
I found a statistics book with this kind of decision tree. The book is: Daniel WW (2009) Biostatistics, 9th ed., John Wiley & Sons, Inc., Hoboken, NJ, p. 176. Another fine book is as follows. Norman GR, Streiner DL (2008) Biostatistics 3rd ed. B.C. Decker, Inc., Hamlton, Ontario, p. 35. Norman and Streiner know how to teach, and they warn students of the various ambiguities and inconsistencies found in other statistics books. The Daniel book, and the Norman & Streiner book, fill in the gaps where other statistics book are just plain confusing. I am still puzzled as to why many statistics books use such strikingly different approaches to using the Z statistic, and different approaches for plugging the Z statistic into a table to get the P value. Norman and Streiner is unique among all statistics books, in actually recognizing this inconsistency in the table that must be used, for plugging in the Z value.