STATISTICA – Variance Estimation and Precision (VEPAC)
Variance Estimation and Precision (VEPAC) software provides a comprehensive set of
techniques for analyzing data from experiments that include both fixed and random effects.
With VEPAC, you can obtain estimates of variance components and use them to make
precision statements while at the same time comparing fixed effects in the presence of
multiple sources of variation. In the VEPAC module, an alternative to ANOVA estimation is
provided by restricted maximum likelihood estimation (REML). The REML method is based on
quadratic forms and requires iteration to find a solution for the variance components.
VEPAC is an augmentation of the award-winning and widely adopted STATISTICA software
suite, enhancing the set of comprehensive STATISTICA products currently available for
analysis of variance, including General Linear Models, Generalized Linear/Nonlinear Models,
Design of Experiments (DOE), and Variance Components.
VEPAC is currently used by companies in Pharmaceutical, Chemical, Petrochemical, Consumer
Products, Semiconductor, and other industries for specific applications of analysis of variance,
˜ valuating method transfer between two labs of manufacturing facilities
˜ Evaluating the differences between treatment groups in a study that includes both fixed
and random effects
˜ Evaluating the factors that contribute to product variability in manufacturing
˜ Evaluating the contributions of variation attributed to instruments, operators, raw
materials, and other factors
Integrated in the VEPAC product, is a new graph type: the Variability Plot. The Variability Plot
is a display of data where the underlying organization of the data collection is represented by a
series of hierarchical or nested rectangles enclosing the data. This type of graph is useful to
evaluate the variability of one factor within several other organizing factors…
The VEPAC design specification dialog enables users to specify effects in the model and save
the design. Users have several options for displaying means as seen above, while the
variability plot helps to visualize the data.