Statistics How To

Probability > A Nash Equilibrium in game theory is a collection of strategies, one for each player in a social game, where there is no benefit for any player to switch strategies. In this situation, all players the game are satisfied with their game choices at the same time, so the game remains at equilibrium. … Read more

Markov Chain Monte Carlo > Slice sampling (Neal, 2003) is a Markov Chain Monte Carlo (MCMC) method for sampling from a probability distribution. The basic idea behind a slice sample is that any distribution can be sampled from by selecting uniformly spaced points under a probability distribution curve using a MCMC algorithm; multivariate distributions can … Read more

Hypothesis Testing > REGWF Test What is the Ryan-Einot-Gabriel-Welsh F(REGWF) Procedure? The REGWF procedure– a modification of the Student-Newman-Keuls (SNK) procedure — is a step-down pairwise comparison procedure for One-Way Anova. It is a way to control the familywise error rate in multi-stage tests. It is a conservative test, which means that the familywise error … Read more

Measures of Spread > Semi Interquartile Range / Quartile Deviation What is the Semi Interquartile Range? The semi interquartile range (SIR) (also called the quartile deviation) is a measure of spread. It tells you something about how data is dispersed around a central point (usually the mean). The SIR is half of the interquartile range. … Read more

Randomized Clinical Trials > Number Needed to Treat What is Number Needed to Treat? The Number Needed to Treat (NNT) is a count of how many people need to be treated in order for one person to benefit. More effective treatments have lower NNTs. The ideal NNT is 1, which equals everyone benefiting from the … Read more

Randomized Clinical Trials > Number Needed to Harm What is Number Needed to Harm? Number Needed to Harm (NNH) is a measure of how many people need to be treated (or exposed to a risk factor) in order for one person to have a particular adverse effect. For example, March et. al showed that the … Read more

Randomized Clinical Trials > Binary Endpoints What are Binary Endpoints? A binary endpoint is a conclusion with two clear choices. For example, if a clinical trial is trying to find out if a drug cures a disease, the endpoints might be: “Cure” and “no cure”, “Remission” or “No remission”, “Symptom relief” or “no symptom relief”. … Read more

Randomized Clinical Trials > What is an Active Control? “Active control” (or “Active Comparator”) means that a known, effective treatment (as opposed to a placebo) is compared to an experimental treatment. In other words, every person in an active control clinical trial is given a treatment that works (or potentially works), instead of some receiving … Read more

Statistics Definitions > Statistical Process Control Contents: What is Statistical Process Control? Control Charts/Stewhart Charts What is Statistical Process Control? Statistical Process Control (SPC) is a way to figure out how a process or system should behave. A model for “normal” system behavior is created with set limits. This allows variations from the norm to … Read more

Randomized Clinical Trials > Primary Endpoint Contents: Primary Endpoint Surrogate Endpoint Other Types of Endpoint (Secondary, Binary, Hard/Soft) What is a Primary Endpoint? A primary endpoint is the main measurement a trial is trying to assess. It answers the most important question in the trial. For example: In a weight loss study: What is the … Read more