Survey and statistical methods

There are a vast array of survey and statistical research tools.

Bayesian methods

Allowing a unified approach to inference, forecasting and decision making.

Causal inference

Quantifying the relationship between a particular exposure (the ‘cause’) and an outcome (the ‘effect’).

Confirmatory factor analysis

Specifying the number of factors which underlie a set of observed variables.

Cost benefit and cost effectiveness analysis

Describing methods of economic evaluation with underlying economic principles and value judgements.

Event history analysis

Examining the determinants or factors behind the occurrence of events over time.

Fixed effects vs multilevel models

Illustrating the advantages and disadvantages of structured and unvariable data.

Generalized method of moments

Providing a computationally convenient method for estimating the parameters of statistical models.

Health trajectories

Creating estimated descriptions of how a person’s health changes as they get older.

Item response theory

Comprising a theory of measurement and a family of statistical models that aim to provide justification and evidence for the reliability and validity of multivariate data.

Latent class analysis

Underlying Latent Class Analysis (LCA) is the idea that there are unobserved subgroups of cases in the data.

Latent structure analysis

Introducing the concept behind flexible, generalized latent variable models.

Multilevel modelling

Describing a flexible framework for testing sophisticated social, or other, theories.

Path analysis

Introducing an advanced statistical technique in simpler terms for non-statisticians.

Risk scores

Aiding decision making in conditions of uncertainty through construction, classification and prediction.

Social network analysis

Focusing on the network of relations consisting of a set of actors and edges.

Structural equation models

Allowing researchers to take seriously the problems of modelling hypothetical constructs.

Survey weights

Introducing survey weights and their use in research.

Time series analysis

Covering a wide range of statistical and econometric techniques designed to capture patterns observed over time.

Power calculations

Examining power and sample size calculations, and the compromises involved in their use.