The Generalized Additive Models for Location, Scale and Shape (GAMLSS) is a recent development which provides a framework with access to a large set of distributions and the ability to model all of the parameters of these distributions as functions of the explanatory variables within a data set. Read the rest of this entry »
In some experiments, where the aim is to compare a set of treatments, there are one or two sources of variation that can be accounted for at the design stage of a study. The statistical technique that is used in these situation is blocking and it can be used to reduce the variance of pairwise treatment comparisons. Read the rest of this entry »
The statistical methodology of design of experiments has a long history starting back with the work of Fisher, Yates and other researchers. One of the main motivating factors is to make good use of available resources and to avoid making decisions that cannot be corrected during the analysis stage of an investigation. Read the rest of this entry »
The online book on time series forecasting methods by Rob Hyndman and George Athanasopoulos has been completed and was announced on the Hyndsight blog. It is a very accessible book and worth reading to understand time series methodology and useful strategies for making predictions using these models.
The RHIPE website provides details of linking together the power of R and Hadoop.
The Seasonal Trend Decomposition using Loess (STL) is an algorithm that was developed to help to divide up a time series into three components namely: the trend, seasonality and remainder. The methodology was presented by Robert Cleveland, William Cleveland, Jean McRae and Irma Terpenning in the Journal of Official Statistics in 1990. The STL is available within R via the stl function. Read the rest of this entry »