A Principal Component Analysis (PCA) is a very useful statistical tool to restructure large datasets by reducing the amount of variables. This basically means that a dataset, with for example 30 variables, is reduced to only 3 or 4 variables that still contain a large proportion of the information from all the 30 variables. An advantage of the PCA analysis is to detect correlations between the individual variables. However, more interesting is that this analysis can help to identify ‘latent variables’ that are not visible by only looking at the individual variables. Because of these reasons, PCA analyses are performed frequently and can be found in many peer-reviewed articles.
ATLAS.ti provides tools to analyze unstructured data, i.e. data that cannot be meaningfully analyzed by formal, statistical approaches, such as textual and multimedia data, even short films clips or photographs. This presentation lays the foundation for how to use AtlasTi, a software of choice for many research professionals engaged in qualitative data analysis. Through both a powerpoint presentation and an interactive session, the presentation will explain: typical project phases, essential processes, and query and analysis tools for AtlasTi, and provide a sampling of how and why you might choose AtlasTi as a tool for your research.