Lynn Shaffer's Research Essentials
The essentials for interpreting research and statistics
General concepts and discussions on statistics
Number Needed to Treat (NNT) The number needed to treat (NNT) is based on comparing one treatment, typically a new one, with another treatment (usually the standard treatment) or perhaps with nothing. That is, it is always relative to another situation. NNT says, “by treating this number of patients with the new treatment, one additional…
Situation: You have two populations (or groups) for whom you have calculated their risk of a particular outcome. A typical scenario is one group has been exposed to something that might cause a disease and the other one hasn’t. Or one group has received treatment A and another treatment B, and you want to see…
Situation: You have two populations (or groups) for whom you have calculated their risk of a particular outcome. A typical scenario is one group has been exposed to something that might cause a disease and the other one hasn’t. Or one group has received treatment A and another treatment B, and you want to see…
Situation: there is a defined population and each member of the population will be followed for a specific period of time to see if they experience an outcome of interest. Risk = the proportion of people in the population who experience the outcome within the specified time period Because it’s a proportion, risk ranges from…
What They Are Sensitivity and specificity are aspects of how well a test performs in determining whether a patient has a disease (or condition). When calculating sensitivity, you restrict your population (or denominator) to only the people who truly have the disease. For calculating specificity, you restrict your population (or denominator) to only the people…
Intention to treat (ITT) involves the statistical analysis of data from randomized clinical trials. At the beginning of their participation, patients are randomized to one of the trial interventions. Over the course of their participation, they may leave the group to which they were assigned – they may stop treatment altogether, start a treatment not…
What It Is In epidemiology, an intermediate outcome is an event that occurs within the series of steps of a proposed causal pathway that leads from an initiating exposure to an ultimate outcome of interest. In an (oversimplified) example, smoking tobacco increases activity of the sympathetic nervous system which leads to high blood pressure, which…
What It Is Type II error, also known as beta error, can occur with classical (frequentist) statistical testing. Before the statistical test is conducted, you select the value of the p-value that will determine whether you reject the null hypothesis (usually of no difference between groups). A customary p-value level for rejecting the null hypothesis…
What It Is Many clinical or observational research studies involve regression models. These models employ statistical methods to examine whether particular factors have an association with an outcome. If there are multiple factors of interest in the model, the statistical methods allow for determining whether they have a relationship with the outcome even after considering…
What It Is Type I error, also known as alpha error, can occur with classical (frequentist) statistical testing. Before the statistical test is conducted, you select the value of the p-value that will determine whether you reject the null hypothesis (usually of no difference between groups). A customary p-value level is 0.05. If your statistical…