MLwiN
Problems with our software?
A software package for fitting multilevel models
- Upgrade MLwiN to 2.27 (released 12-Mar-13)
-
Bug warnings:
- Newly-discovered MLwiN bug: issue for MCMC cross-classified models with a classification whose units start from 0 (13-Oct-11) More >>
- There is currently an issue with using sandwich standard errors in a one level model where the standard error is incorrectly estimated as zero. As a workaround you can specify the model as two level with nothing defined at the higher level.
- A bug has been discovered where if robust standard errors are chosen for a model estimated with RIGLS the estimates can be incorrect. This has been fixed in version 2.26.
- New features in MLwiN 2.18 including note about training materials
- MLwiN - free if you are a UK academic
- Buy MLwiN
- Bugs fixed, new features and known issues
- Teaching version (limited version available free to all to be used with our online training course- see topics covered)
- Starting out? Introduction to MLwiN
- Register/log into our online course - incuding multilevel modelling using MLwiN. Note - please register to use these materials. The course is free, we require you to register so that we can collect data to help us to conduct and publish research into the learning of multilevel methodology and applications.
- Try MLwiN for free (expires after 30 days)
- Manuals
- Using MLwiN - help using the software, eg getting results, using commands, and more
- Citing MLwiN
- MLwiN features and versions
- System requirements
A few of its features
- Names window (where you can see all the variables)
- Equations window (showing what model has been fitted and the parameter estimates). More >>
- Variance function window (to calculate the residual variance at any level)
- Predictions window (to calculate predicted values for each individual in the dataset, specifying what should be included in the prediction), and
- Graphs (here the user has selected the country line that seems to be different from the others and asked that points relating to this country be drawn in red in all graphs, to help in deciding whether this is an outlier; the country is the Netherlands, as the user would have seen when they clicked on the line). More >>
- More features >>
MLwiN and Multilevel modelling
Multilevel modelling has rapidly become established as the appropriate tool for modelling data with complex hierarchical structures. It is important for extending our understanding of social, biological and other sciences beyond that which can be obtained through single level modelling. Multilevel modelling is now being used in Education, Medical science, Demography, Economics, Agriculture and many other areas.
The term multilevel refers to a nested membership relation among units in a system. In an education system, for example, students are members of classes, and classes are grouped within schools. When 'single level' techniques such as multiple regression are applied to data from a structure such as this, the analysis will ignore important aspects of the data structure and the results will often be misleading.
The basic procedures for modelling purely hierarchical data have been extended to include cross-classifications and cases where lower level units belong to more than one higher level unit. Thus, models can now be fitted to data with extremely complex structures.
Multivariate regression and multivariate analysis of variance can be conducted in a particularly flexible manner using a multilevel approach. The models can also be used to fit growth curves and other repeated measures data with either continuous or discrete responses, estimate variance and covariance components from studies with complex designs, and analyse data from studies employing rotation sampling. Multilevel time series data can be modelled. Multilevel generalised linear models can be fitted: for example, logit, log-log or probit models for binary response data and macros are available for multinomial ordered or unordered logistic models. Multilevel survival or event history models can be fitted. Complex sample survey data can be modelled flexibly and efficiently.