Statistical Questions

Philip Sedgwick, a medical statisitican at St Georges, has written many short Statistical question articles in the BMJ, These take to form of a summary of the statistical methodology in pubished paper, follow by a question about which of four statements are correct or incorrect. This is then followed by an explanation of the correct and incorrect answers. A list of these articles is given below, many of them are relevant for undergraduate students.

Absence of evidence is not evidence of absence
Absolute and relative risks
Allocation concealment
Allocation concealment
Analysing case-control studies: adjusting for confounding
Analysis by intention to treat
Analysis by per protocol
Analysis of longitudinal studies
Analysis of outcome measures within treatment groups
Bias in clinical trials
Block randomisation
Case-control studies: measures of risk
Cluster randomised controlled trials
Cluster randomised controlled trials: sample size calculations
Cohen's coefficient Kappa
Cohort studies
Cohort studies: sources of bias
Confidence intervals and statistical significance
Confidence intervals and statistical significance: rules of thumb
Confidence intervals: predicting uncertainty
Confounding in case-control studies
Confounding in case-control studies II
Confounding in clinical trials
Confounding in randomised controlled trials
Control groups
Control treatments
Correlation versus linear regression
Cox proportional hazards regression
Cross sectional studies
Crossover trials
Derivation of hazard ratios
Describing the spread of data I
Describing the spread of data II
Double dummy trials
Double dummy trials incorporating factorial designs
The ecological fallacy
Effect sizes
Equivalence trials
Errors when statistical hypothesis testing
Estimating the population at risk
External and internal validity in clinical trials
Factorial trials
Generalisation and extrapolation
Generalisation and extrapolation of study results
Hazard ratios
Hazards and hazard ratios
The healthy entrant effect
How to read a forest plot
Incidence rate ratio
Incidence rates
Independent samples t test
Internal and external validity
Intraclass correlation coefficient
Kaplan-Meier survival analysis: types of censored observations
Limits of agreement (Bland-Altman method)
The log rank test
Log transformation of data
Logistic regression
Measurement of data
Meta-analyses I
Meta-analyses II
Meta-analyses III
Meta-analyses IV
Meta-analyses V
Meta-analyses VI
Meta-analyses VII
Meta-analyses: heterogeneity and subgroup analysis
Meta-analyses: how to read a funnel plot
Meta-analyses: tests of heterogeneity
Multiple regression
Multiple significance tests
Multiple significance tests: the Bonferroni correction
n of 1 trials
Nested case-control studies
Non-inferiority trials
Non-parametric statistical tests for independent groups: numerical data
Non-parametric statistical tests for two related groups: numerical data
The Normal distribution
The normal distribution
Normal ranges
Number needed to harm
Number needed to treat
Number needed to treat I
Number needed to treat II
Numbers needed to treat and harm
Observational study design
Observational Study Design I
Observational study design II
Observational study designs
Odds and odds ratios
Odds ratios
Odds ratios and adjusting for confounding
Odds ratios II
One sided and two sided hypothesis tests
One way analysis of variance
Open clinical trials
Open label crossover trials
Open label trials
P values
P values or confidence intervals?
Parametric statistical tests for independent groups: numerical data
Parametric v non-parametric statistical tests
Patient preference trials
Pearson's correlation coefficient
Per protocol analysis
The placebo effect
Placebo run in periods
Populations and samples
Prevalence and incidence
Primary and secondary outcome measures
Proportional quota sampling
The purpose of control groups
Questionnaire surveys
Questionnaire surveys: sources of bias
Random allocation III
Random sampling versus random allocation
Randomised controlled trials with full factorial designs
Receiver operating characteristic curves
Receiver operating characteristic curves
Reference and normal ranges
Relative risks
Relative risks and confidence intervals
Relative risks and statistical significance
Restricted randomisation
Sample size calculations I
Sample size calculations II
Sample size: how many participants are needed in a trial?
Sampling I
Sampling II
Sampling III
Sampling methods I
Sampling methods II
Sampling methods III
Screening tests: indices of performance
Screening tests: likelihood ratios
Selection bias versus allocation bias
Sequential trials
Simple linear regression
Skewed distributions
Skewed distributions
Skewed distributions II
Sources of bias in randomised controlled trials
Sources of bias in randomised controlled trials II
Standard deviation versus standard error
Standard error of the mean
Standardisation of outcome measures (z scores)
Statistical hypothesis testing
Statistical tests for independent groups: categorical data
Statistical tests for independent groups: time to event data
Statistical tests: matched pairs categorical data
Stratified random allocation
Study design
Study design
Superiority trials
Survival (time to event) data I
Survival (time to event) data II
Survival (time to event) data: censored observations
Survival (time to event) data: median survival times
T scores and z scores
Units of analysis
Variables and parameters
Variables sample estimates and population parameters
What are odds?
What is a P value?
What is a superiority trial?
What is intention to treat analysis?
What is number needed to harm (NNH)?
What is number needed to treat (NNT)?
What is per protocol analysis?
What is recall bias?
What Is Risk?
What is sampling error?
What is the standard error of the mean?
Why match in case-control studies?
Why randomise in clinical trials?
z scores
Zelen's design

List updated on 29 October 2013

Please Report any issues to Dr Trevor Bryant