Sentence examples for multivariate linear modelling from inspiring English sources

In order to understand factors that predict exacerbation history, univariate and multivariate linear modelling was performed and is summarised in Table 3.

Univariate and multivariate linear modelling was done using the statistical software R version 2.15, whereas further statistical analyses were performed by using SPSS 19.0 software (SPSS Inc, Chicago, Ill).

Multivariate linear models were used to compare milk composition and health status between quarter types.

The initial univariate filter was applied to remove miRNA showing little predictive power from the multivariate linear model, and only those miRNA with p < 0.2 significance by F-test in the univariate linear model predicting signature score were considered.

Then, the penalised multivariate linear model with the least predictive error (as assessed on the validating folds) was selected, and coefficients for these miRNA were used for further analysis.

This permissive p-value was used to assure that the multivariate linear model did not contain artificially stringent associations, as the penalisation procedure also functions as a stringency filter, reducing the false discovery rate.

A univariate prescreen was applied using boosting to identify potentially associated features, and significantly associated covariates among the remaining features were identified with a multivariate linear model without zero-inflation.

The implementation of a new procedure for the determination of multiple multivariate linear models with latent factors is described.

Three multivariate linear models were fitted to the data.

It is easy to generalize the conclusions from univariate linear model to multivariate linear model.

In the case of, model (1.1) degenerates to the general multivariate linear model without restrictions.