Blog

Welcome to the blog! Here you’ll find discussions on statistical science, methodology, and applications of statistical methods in research and practice.

1 Browse by Topic

2 All Posts

Your Models Are Neither Useful Nor Approximate

statistics

A discussion about models and the assumptions that underlie them.

Sir Panda
11 min

Using Stata

A simple guide on how to produce consonance functions in Stata.

Sir Panda
29 min

Stan

Some sample scripts

Sir Panda
17 min

Your Models Are Neither Useful Nor Approximate

statistics

A discussion about models and the assumptions that underlie them.

Sir Panda
7 min

Stan

Some sample scripts

Sir Panda
85 min

Using Stata

A simple guide on how to produce consonance functions in Stata.

Sir Panda
14 min

Simulation of a Two-Group Parallel-Arm RCT with Interim Analyses

statistics

A simulation of a two-group parallel-arm randomized trial with interim analysis using the rpact package.

Feb 1, 2021
Zad Rafi
13 min

Simulation of a Two-Group Parallel-Arm RCT with Interim Analyses

statistics

A simulation of a two-group parallel-arm randomized trial with interim analysis using the rpact package.

Jan 31, 2021
Zad Rafi
54 min

Tables, Graphs, and Computations from Rafi & Greenland (2020)

This post goes through the R code and logic that was used to construct the figures and concepts in Rafi & Greenland (2020) BMC MRM.

Dec 12, 2020
Zad Rafi
36 min

Tables, Graphs, and Computations from Rafi & Greenland (2020)

This post goes through the R code and logic that was used to construct the figures and concepts in Rafi & Greenland (2020) BMC MRM.

Dec 11, 2020
Zad Rafi
45 min

Quality Control in Statistical Analyses

statistics

Experienced statisticians and data analysts are familiar with stories where a coding error has led to an entire conclusion changing, even leading to a retraction. It’s the sort of stuff that keeps people up at night.

Jun 13, 2020
Zad Rafi
44 min

Quality Control in Statistical Analyses

statistics

Experienced statisticians and data analysts are familiar with stories where a coding error has led to an entire conclusion changing, even leading to a retraction. It’s the sort of stuff that keeps people up at night.

Jun 12, 2020
Zad Rafi
45 min

Book Review: Regression and Other Stories by Gelman, Hill, and Vehtari

An early look at Gelman et als new book, Regression and Other Stories, which is an update to their seminal 2006 book, Data Analysis Using Regression and Multilevel Hierarchical Models.

Jun 11, 2019
Zad Rafi
3 min

Book Review: Regression and Other Stories by Gelman, Hill, and Vehtari

An early look at Gelman et als new book, Regression and Other Stories, which is an update to their seminal 2006 book, Data Analysis Using Regression and Multilevel Hierarchical Models.

Jun 10, 2019
Zad Rafi
5 min

Book Review: Fisher, Neyman, and the Creation of Classical Statistics

A review of Erich Lehmann’s last book, Fisher, Neyman, and the Creation of Classical Statistics.

Dec 30, 2018
Zad Rafi
25 min

Book Review: Fisher, Neyman, and the Creation of Classical Statistics

A review of Erich Lehmann’s last book, Fisher, Neyman, and the Creation of Classical Statistics.

Dec 29, 2018
Zad Rafi
25 min

P-values Are Tough And S-values Can Help

An extensive discussion about what P-values are, their properties, common interpretations, misinterpretations, and how a measure called an S-value may better help us interpret them.

Nov 11, 2018
Zad Rafi
28 min

P-values Are Tough And S-values Can Help

An extensive discussion about what P-values are, their properties, common interpretations, misinterpretations, and how a measure called an S-value may better help us interpret them.

Nov 10, 2018
Zad Rafi
36 min

We May Not Understand Control Groups

Discussions praising the efficiency of randomized trials are widespread, however, few of these discussions take a close look at some of the common assumptions that individuals hold regarding randomized trials. And unfortunately, these common assumptions may be based on outdated evidence and simplistic ideas.

Oct 28, 2018
Zad Rafi
11 min

Misplaced Confidence in Observed Power

Another misinterpretation of what statistical power is and how trial results should be reported in a popular journal.

Sep 30, 2018
Zad Rafi
2 min

The Bradford Hill Criteria Don’t Hold Up

The Bradford Hill viewpoints are commonly used as a checklist to argue for causality when randomized trials aren’t possible. However, the originator of these viewpoints never intended for them to be used this way. In this post, I examine the shortcomings of using these viewpoints as a checklist in the real world.

Sep 6, 2018
Zad Rafi
14 min

The Bradford Hill Criteria Don’t Hold Up

The Bradford Hill viewpoints are commonly used as a checklist to argue for causality when randomized trials aren’t possible. However, the originator of these viewpoints never intended for them to be used this way. In this post, I examine the shortcomings of using these viewpoints as a checklist in the real world.

Sep 5, 2018
Zad Rafi
14 min

Misuse of Standard Error in Clinical Trials

Analytic statistics are commonly used to make inferences from the data. However, they are often misused because of misconceptions about what they do. In this post, I discuss how standard error is commonly misused in clinical trials.

Aug 7, 2018
Zad Rafi
5 min

Misuse of Standard Error in Clinical Trials

Analytic statistics are commonly used to make inferences from the data. However, they are often misused because of misconceptions about what they do. In this post, I discuss how standard error is commonly misused in clinical trials.

Aug 6, 2018
Zad Rafi
5 min

Vitamin E, Mortality, and the Bayesian Gloss

A look at a time when Bayesian data analysis went off the rails.

Jun 20, 2018
Zad Rafi
8 min

Vitamin E, Mortality, and the Bayesian Gloss

A look at a time when Bayesian data analysis went off the rails.

Jun 19, 2018
Zad Rafi
8 min

Problems with the Number Needed to Treat

The number needed to treat is a popular statistic used in medicine, but it has several problems associated with the way it is used and in this blog post, I discuss some of those problems and possible solutions.

May 27, 2018
Zad Rafi
8 min

Problems with the Number Needed to Treat

The number needed to treat is a popular statistic used in medicine, but it has several problems associated with the way it is used and in this blog post, I discuss some of those problems and possible solutions.

May 26, 2018
Zad Rafi
8 min

Calculating Observed Power Is Just Transforming Noise

A discussion of events that transpired in the past year, where a group of surgical researchers promoted calculating post-hoc power using the observed effect size, despite warnings from several statisticians.

May 4, 2018
Zad Rafi
17 min

Calculating Observed Power Is Just Transforming Noise

A discussion of events that transpired in the past year, where a group of surgical researchers promoted calculating post-hoc power using the observed effect size, despite warnings from several statisticians.

May 3, 2018
Zad Rafi
28 min

Myth: Covariates Need to Be Balanced in RCTs

Many people believe that the purpose of randomization is to perfectly balance out both known and unknown covariates in order to reach causal inferences, however, this is simply not true and is a misunderstanding of the process of randomization.

Apr 10, 2018
Zad Rafi
4 min

Myth: Covariates Need to Be Balanced in RCTs

Many people believe that the purpose of randomization is to perfectly balance out both known and unknown covariates in order to reach causal inferences, however, this is simply not true and is a misunderstanding of the process of randomization.

Apr 9, 2018
Zad Rafi
4 min

Confidence, Posteriors, and the Bootstrap

statistics

This guide discusses the bootstrap resampling method and its close connection to the consonance distribution and how to use certain iterations of the bootstrap to construct a consonance distribution.

Jan 12, 1945
Sir Panda
9 min

Confidence, Posteriors, and the Bootstrap

statistics

This guide discusses the bootstrap resampling method and its close connection to the consonance distribution and how to use certain iterations of the bootstrap to construct a consonance distribution.

Jan 12, 1945
Sir Panda
9 min
No matching items