Instrumental variables and heterogeneous treatment effects

22 March 2022 - A randomised clinical trial can be used to estimate the average treatment effect for a population.  ...

Read more →

Collider bias

14 March 2022 - Bias is a systematic, non-random error in the estimation of a treatment effect or the effect of ...

Read more →

Assessing unexpected circumstances that lead to modifications in clinical trial design, conduct, or analysis application of the CONSERVE Reporting Guideline

1 March 2022 - In the COVID-19 Dexamethasone (CoDEX) randomised clinical trial, which studied a sample of critically ill patients with ...

Read more →

Heterogeneity of treatment effect; estimating how the effects of interventions vary across individuals

14 December 2021 -  ...

Read more →

Use of confidence intervals in interpreting non-statistically significant results

23 November 2021 - The goal of much of medical research is to determine which of 2 or more therapeutic approaches ...

Read more →

Estimands, estimators and estimates

23 August 2021 - The primary goal of most randomised clinical trials is to draw conclusions about the effect of a ...

Read more →

Immortal time bias in observational studies

16 February 2021 - Observational studies are commonly used to evaluate the association between a risk factor or “exposure” and the ...

Read more →

Why proper understanding of confidence intervals and statistical significance is important

15 February 2021 - Guidelines for reporting results from randomised trials have long underscored the importance of confidence intervals. ...

Read more →

Is it time to stop using statistical significance?

1 February 2021 - The important first step in the critical appraisal of a randomised trial is not an evaluation ...

Read more →

Even before year end, 2020's new drug approvals match FDA's 2019 stats

7 December 2020 - The US FDA has kept its new drug approvals for 2020 on track to match or ...

Read more →

Worst-rank score methods—a non-parametric approach to informatively missing data

28 September 2020 - A previous JAMA Guide to Statistics and Methods article briefly reviewed non-parametric statistics.  ...

Read more →

Estimating risk ratios and risk differences: alternatives to odds ratios

15 September 2020 - The goal of many medical research studies is to estimate the direction and magnitude of the effect ...

Read more →

Regression discontinuity design

2 July 2020 - The method is used to study the outcomes related to an abrupt change when it is not ...

Read more →

Why test for proportional hazards?

13 March 2020 - The Cox proportional hazards model, introduced in 1972, has become the default approach for survival analysis in ...

Read more →

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

28 October 2019 - The value of our health and medical research investment is at risk unless we foster the discipline ...

Read more →