Its luck was revealed in childhood; its power lies in knowing where unequal allocation helps, and where it cannot.

This blog shows how to reason quantitatively about FDA’s proposed policy change instead of defaulting to either alarm or celebration.

From crime fiction to sufficient statistics, why every layer of modeling necessarily blurs information rather than creating it.

What a few college football games reveal about weighing evidence, applying models, and making informed decisions — lessons that extend far beyond the field.

Statistics did not disappear; one of its creations has become powerful, and with that power comes responsibility we are currently failing to take seriously.

A guide to avoiding wasted potential in clinical trials by leveraging repeated measures and integrating pharmacology and biological insights into analysis.

Thanksgiving stories lead to a broader lesson: knowing all possibilities allows one to apply six critical levers for smarter study design.

Being a technically great statistician is not enough: before your skills can shine, you must open the door that allows you to establish credibility with each scientist you work with and then establish it.

This blog offers a framework for making responsible Proof-of-Concept decisions when budgets limit sample size, showing how adaptive thinking replaces rigid historical dogma.

A dog may follow commands without understanding why, but in science, blindly following ‘statistical’ rules without grasping the principles can lead to cherry picking, misinterpretation, and compromised integrity.

When diagnostic observations are presented as facts, the consequences ripple through public perception, funding, and the progress of science itself.

In last week's blog, I showed that the Frequentist/Bayesian divide is largely philosophical, with practical differences between approaches being limited. Even unique Bayesian methods can often be interpreted in a frequentist manner. Yet, adoption of these methods, dubbed Bayesian, even when appropriately applied, has been slow in drug development. This article explains why.

Despite the tribal divide, Bayesian and Frequentist methods produce nearly the same action in the preponderance of situations.

A reflection on how a childhood toy, civic pride, and a one-page impact statement taught me how to lead without breaking under pressure.

Although regulators fear overly optimistic results, the real consequences of pre-disclosure fall primarily on sponsors, increasing variability and risking missteps in trial conduct and decision making.

Systems meant to protect trial integrity sometimes devolve into ritual, adding bureaucracy without improving patient safety or science.

The best statistical solutions in drug development are not always conventional, but they are always grounded in the real scientific and operational question.

A personal tale of love, compromise, and curiosity that led to an unexpected but fulfilling career in statistics, and how you can find your own path too.

Using the example of estimating proportions from continuous data, this essay highlights a general lesson in statistics: the non-obvious choice is often the most effective, whether in analysis, research, or decision-making. This should not be a surprise, since the same is true in life.

Through stories of name confusion and statistical jargon, the post emphasizes the importance of precise communication in statistics.