Modern Biostatistical Principles and Conduct: Study Analysis, interpretation and Application

Clinical medicine or surgery continues to make advances through evidence that is judged  to be objectively drawn from the care of individual patients. The natural observation of individuals remains the basis for our researchable questions’ formulation and the subsequent hypothesis testing.  Evidence-based medicine or surgery depends on how critical we are in evaluating evidence in order to inform our practice. These evaluations no matter how objective are never absolute but probabilistic, as we will never know with absolute certainty how to treat future patients who were not a part of our study. Despite the obstacles facing us today in an attempt to provide an objective evaluation of our patients, since all our decisions are based on a judgment of some evidence, we have progressed from expert opinion to the body of evidence from randomized controlled clinical trials, as well as cohort investigations, prospective and retrospective.   

 The conduct of clinical trials though termed the “gold standard”, which yields more reliable and valid evidence from the data relative to non-experimental or observational designs, depends on how well it is designed and conducted prior to outcomes data collection, analysis, results, interpretation, and dissemination. The designs and the techniques used to draw statistical inferences are often beyond the average clinician’s understanding. A text that brings hypothesis formulation, analysis, and how to interpret the results of the findings is long overdue and highly anticipated. Statistical modeling which is fundamentally a journey from sample to the application of findings is essential to evidence discovery.

 This text, Modern Biostatistics for Clinical, Biomedical and Population-Based Researchers has filled this gap, not only in the way complex modeling is explained but the simplification of statistical techniques in a way that had never been explained before. This text has been prepared intentionally at the rudimentary level to benefit clinicians without sophisticated mathematical backgrounds or previous advanced knowledge of biostatics as applied statistics in health and medicine. Also, biomedical researchers who may want to conduct clinical research, as well as consumers of research products may benefit from the sampling techniques, their relevance to scientific evidence discovery as well a simplified approach to statistical modeling of clinical and biomedical research data.  It is with this expectation and enthusiasm that we recommend this text to clinicians in all fields of clinical and biomedical research. One’s experience with biomedical research and how the findings in this arm are translated to the clinical environment signals the need for the application of biological, and clinical relevance of findings prior to statistical inference.  The examples provided by the author to simplify research methods are familiar to orthopedic surgeons as well as clinicians in other specialties of medicine and surgery.

 Whereas statistical inference is essential in our application of the research findings to clinical decision-making regarding the care of our patients, statistical inference without clinical relevance or importance can be very misleading, and meaningless. The authors have attempted to deemphasize the p-value in the interpretation of clinical and biomedical research findings, by stressing the importance of confidence intervals, which allow for the quantification of evidence. For example, a large study due to a large sample size that minimizes variability may show a statistically significant difference while in reality, the difference is too insignificant to warrant any clinical importance. In contrast, a small study as frequently seen in most clinical trials or surgical research may have a large effect size of clinical relevance but not statistically significant at (p > 0.05). Thus, without considering the magnitude of the effect size with the confidence interval, we tend to regard these studies as negative findings, which is erroneous, since the absence of evidence, simply on the basis of an arbitrary significance level of 5% does not necessarily mean evidence of absence.1   In effect, clinical research results,  cannot be adequately interpreted without first considering the biological and clinical significance of the data, before the statistical stability of the findings (p-value and 95% Confidence Interval), since the p-value as observed by the authors merely reflects the size of the study and not the measure of evidence.  

 In recommending this text, it is one’s inclination that this book will benefit clinicians, research fellows, clinical fellows, postdoctoral students in biomedical and clinical settings, nurses, clinical research coordinators, physical therapists, and all those involved in clinical research design, conduct, and analysis of research data for statistical and clinical relevance.  Convincingly, knowledge gained from this text will lead to our improvement of patient care through well-conceptualized research. Therefore, with the knowledge that no book is complete, no matter its content or volume, especially a book of this nature, which is prepared to guide clinicians on sampling, statistical modeling of data, and interpretation of findings, this book will benefit clinicians who are interested in applying appropriate statistical technique to scientific evidence discovery.

 Finally, we are optimistic that this book will bridge the gap in knowledge and practice of clinical and biomedical research, especially for clinicians in busy practice who are passionate about making a difference in their patient's care through scientific research initiatives.