Using Factor Analyses to Explore Data Generated by the National Grapevine Wood Diseases Survey

Résumé

The Grapevine Wood Diseases National Observatory yields a cohesive and large data set which may be analyzed withdifferent approaches. In our study, we deal with complex data composed of quantitative and qualitative variables whichevolve with time, since data for three successive years are available. The objective of the study was to produce the largestpossible amount of information from this data set, in order to highlight main trends. To this aim, we used several dataanalysis techniques. Our study proceeds in three stages. First, relationships between the different variables are identifiedusing bivariate measures of association and tests. Then factorial methods, namely multiple correspondence analysis andfactor analysis of mixed data are used to look for multivariate dependencies between the variables of the dataset. Last,we use factor analysis of multi-tables, each table representing a year, in order to account for the successive years of data.The exposition is accessible to readers with an intermediate knowledge of statistics. A prior exposure to multiplecorrespondence analysis is quite useful for reading the article.