Model« Back to Glossary Index
The term model is often used to describe statistical regression analyses involving more than one independent variable and one dependent variable. This is a multivariable or multiple regression (or multivariate analysis).
« Back to Glossary Index
Related Glossary Terms:
- Sensitivity AnalysisAny test of the stability of the conclusions of a health care evaluation over a range of probability estimates, value judgments, and assumptions about the structure of the decisions to be made. This may involve the repeated evaluation of a decision model in which one or more of the parameters of interest are varied.
- Fixed-Effects ModelsA model to generate a summary estimate of the magnitude of effect in a meta-analysis that restricts inferences to the set of studies included in the meta-analysis, and assumes that a single true value underlies all of the primary study results. The assumption is that if all studies were infinitely large, they would yield identical estimates of effect; thus, observed estimates of effect differ from each other only because of random error. This model only takes within-study variation into account and not between-study variation.
- Random-Effects ModelA model used to give a summary estimate of the magnitude of effect in a meta-analysis that assumes that the studies included are a random sample of a population of studies addressing the question posed in the meta-analysis. Each study estimates a different underlying true effect, and the distribution of these effects is assumed to be normal around a mean value. Because a random-effects model takes into account both within-study and between-study variability, the confidence interval around the point estimate is, when there is appreciable variability in results across studies, wider than it could be if a fixed-effects model were used.
- Degrees of FreedomA technical term in a statistical analysis that has to do with the power of the analysis. The more degrees of freedom, the more powerful the analysis. The degrees of freedom is typically the number of observations in a sample less the number of unknown parameters estimated for the model. It reflects a sort of adjusted sample size, with the adjustment based on the number of unknowns that need to be estimated in a model. For example, in a two-sample t-test the degrees of freedom is n1 + n2 – 1 – 1 since there are n1+n2 subjects altogether and 1 mean estimated in one group and one mean in another giving n1 + n2 – 2.
- Multivariate RegressionA type of regression that provides a mathematical model that attempts to explain or predict the dependent (outcome or target) variable by simultaneously considering 2 or more independent (or predictor) variables.