Running head: PCA IN COMPARATIVE ANALYSES Comparative analysis of principal components can be misleading
نویسندگان
چکیده
Most existingmethods formodeling trait evolution are univariate, while researchers are oen interested in investigating evolutionary patterns and processes across multiple traits. Principal components analysis (PCA) is commonly used to reduce the dimensionality of multivariate data as univariate trait models can be t to the individual principal components. e 15 problem with using standard PCA on phylogenetically structured data has been previously pointed out yet it continues to be widely used in the literature. Here we demonstrate precisely how using standard PCA can mislead inferences: the rst few principal components of traits evolved under constant-rate multivariate Brownian motion will appear to have evolved via an “early burst” process. A phylogenetic PCA (pPCA) has been proprosed to alleviate these 20 issues. However, when the true model of trait evolution deviates from the model assumed in the calculation of the pPCA axes, we nd that the use of pPCA suers from similar artifacts as standard PCA. We show that datasets with high eective dimensionality are particularly likely to lead to erroneous inferences. Ultimately, all of the problems we report stem from the same underlying issue—by considering only the rst few principal components as uni25 variate traits, we are eectively examining a biased sample of a multivariate pattern. ese results highlight the need for truly multivariate phylogenetic comparative methods. As these methods are still being developed, we discuss potential alternative strategies for using and interpreting models t to univariate axes of multivariate data.
منابع مشابه
Running head: PCA IN COMPARATIVE ANALYSES Statistical and conceptual challenges in the comparative analysis of principal components
متن کامل
Comparative Analysis of Principal Components Can be Misleading.
Most existing methods for modeling trait evolution are univariate, although researchers are often interested in investigating evolutionary patterns and processes across multiple traits. Principal components analysis (PCA) is commonly used to reduce the dimensionality of multivariate data so that univariate trait models can be fit to individual principal components. The problem with using standa...
متن کاملComparative Effectiveness of Semantic Feature Analysis (SFA) and Phonological Components Analysis (PCA) for Anomia Treatment in Persian Speaking Patients With Aphasia
Objectives: Anomia is one of the most common and persistent symptoms of aphasia. Although treatments of anomia usually focus on semantic and/or phonological levels, which both have been demonstrated to be effective, the relationship between the underlying functional deficit in naming and response to a particular treatment approach remains unclear. The aim of this study was to determine the rela...
متن کاملParallel Analysis: a Method for Determining Significant Principal Components
Numerous ecological studies use Principal Components Analysis (PCA) for exploratory analysis and data reduction. Determination of the number of components to retain is the most crucial problem confronting the researcher when using PCA. An incorrect choice may lead to the underextraction of components, but commonly results in overextraction. Of several methods proposed to determine the significa...
متن کاملEnergy Consumption Modeling in Activated Sludge Process Using Coupling PCA-ANFIS Approach
The main challenge in Wastewater Treatment Plants (WWTP) by activated sludge process is the reduction of the energy consumption that varies according to the pollutant load of influent. However, this energy is fundamentally used for aerators in a biological process. The modeling of energy consumption according to the decision parameters deemed necessary for good control of the active sludge ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015