Biostatistics: a fundamental discipline at the core of modern health data science

Every year, Australia's National Health and Medical Research Council (NHMRC) spends around $800 million on medical and public health research,1 much of which depends critically on the correct analysis and interpretation of data. We argue here that the value of our health research investment, in terms of improved health and lives saved, is at risk unless serious attention is paid to fostering the core scientific discipline of biostatistics. This risk is heightened by the expansion of research possibilities offered by the era of big data, which is rapidly enhancing the availability and scale of new information, necessitating ever deeper understanding of statistical issues and computational tools. Concerns surrounding the inadequate foundations of biostatistics in Australia were raised in a statement emanating from the International Society for Clinical Biostatistics conference held in Melbourne in August 2018 (in conjunction with the Australian Statistical Conference), the largest gathering of research biostatisticians that has ever occurred in Australia.

[1]  David Spiegelhalter,et al.  The Art of Statistics: Learning from Data , 2019 .

[2]  John Hsu,et al.  A Second Chance to Get Causal Inference Right: A Classification of Data Science Tasks , 2018, CHANCE.

[3]  J. Lipman,et al.  The Statistical Curriculum Within Randomized Controlled Trials in Critical Illness* , 2018, Critical care medicine.

[4]  Philip B. Stark,et al.  Cargo‐cult statistics and scientific crisis , 2018, Significance.

[5]  M. Bogdan,et al.  Lessons learned from IDeAl — 33 recommendations from the IDeAl-net about design and analysis of small population clinical trials , 2018, Orphanet Journal of Rare Diseases.

[6]  D. Donoho 50 Years of Data Science , 2017 .

[7]  Timothy L Lash,et al.  The Harm Done to Reproducibility by the Culture of Null Hypothesis Significance Testing. , 2017, American journal of epidemiology.

[8]  David A Chambers,et al.  Big Data and Large Sample Size: A Cautionary Note on the Potential for Bias , 2014, Clinical and Translational Science.

[9]  R. Tibshirani,et al.  Increasing value and reducing waste in research design, conduct, and analysis , 2014, The Lancet.

[10]  James M. Robins,et al.  Observational Studies Analyzed Like Randomized Experiments: An Application to Postmenopausal Hormone Therapy and Coronary Heart Disease , 2008, Epidemiology.

[11]  Thomas A Louis,et al.  Training of the next generation of biostatisticians: a call to action in the U.S. , 2006, Statistics in medicine.

[12]  J. Robins,et al.  Effect of highly active antiretroviral therapy on time to acquired immunodeficiency syndrome or death using marginal structural models. , 2003, American journal of epidemiology.

[13]  Mary Cushman,et al.  Estrogen plus progestin and the risk of coronary heart disease. , 2003, The New England journal of medicine.

[14]  D G Altman,et al.  The scandal of poor medical research , 1994, BMJ.

[15]  J. Naisbitt Megatrends: Ten New Directions Transforming Our Lives , 1982 .