Multivariate data collected from batches is usually monitored via control charts (CCs) based on MPCA and MPLS for batch to batch comparison. In addition, distribution free approaches include other dimensionality reduction methods for batch and time-wise analysis. However, techniques for multivariate data focused on variable-wise analysis haven't been widely developed. Here, we propose a nonparametric quality control strategy for off-line monitoring of batches and variables, besides visual clustering of observations within batches. In our approach, CCs based on Dual STATIS are created using robust bagplots to enhance signal detection in batch and variable-wise analysis, while parallel coordinate plots are used in identification of unusual observations' behavior per variable, regardless distributional assumptions. This proposed strategy poses the main advantage of detecting different type of changes through meaningful visualization tools, allowing easier interpretation of results in industrial settings. ARTICLE HISTORY

Half maximal effective concentration EC 50 is considered the main reference for evaluating the efficacy of the products in any plantation using doses and inhibition percentages from laboratory data. However, EC 50 is not the best representation when other relevant variables and their relationships could be involved. As an agricultural case study, fungicide sensitivity of Pseudocercospora fijiensis, the causal agent of black sigatoka, was evaluated on bananas' plantations in three provinces of Ecuador. In this study, multivariate statistical process control was adjusted to a fungicide efficacy evaluation case considering multiple data tables from different locations and years at the same time. The threshold conveyed by inhibition percentages, related to the EC 50 , along with locations and years allowed the multivariate analyses carried out in the proposal. The multivariate statistical control techniques applied were Multilinear Principal Component Analysis (MPCA) and Dual STATIS-Parallel Coordinates approach (DS-PC). A comparison was developed and showed that both methods discriminate correctly between the normal and anomalous conditions within plantations along years, validating the ability of the novel method DS-PC for exhibiting better signaling of anomalous plantations and performing variable-wise analysis to find out possible causes of this behavior in an easier time-saving graphical framework.

El control estadístico multivariante de procesos para la producción por lotes generalmente toma en consideración características correlacionadas para la inspección del desempeño del proceso. En la literatura, los investigadores han utilizado varias técnicas estadísticas de forma individual para abordar esta inspección durante las fases de control y seguimiento. Nuevas estrategias han explorado la posibilidad de combinar dos técnicas con el fin de optimizar el control y el monitoreo del proceso por lotes, como el enfoque DS-PC. Este enfoque novedoso se refiere al uso de Statis Dual y Coordenadas Paralelas e implica una serie de varios pasos de protocolos y aplicaciones de fórmulas que son propensas a errores y consumen mucho tiempo. Utilizando la metodología que se encuentra en la literatura, el paquete DSPC para R se desarrolló con el objetivo de ofrecer una herramienta simple para realizar el cómputo de Statis Dual rápidamente para las fases de control y seguimiento. Las salidas del paquete ofrecen visualizaciones gráficas para detectar comportamientos inusuales durante la producción a través de gráficos de control IS (Interestructura) y CO (Intraestructura). La salida también incluye el gráfico de coordenadas paralelas. Este paquete será útil para los profesionales interesados en la aplicación del enfoque DS-PC a cualquier industria de proceso por lotes a través de la automatización sugerida por defecto o la opción personalizada. Para familiarizar a los usuarios con esta estrategia, el paquete proporciona un conjunto de datos simulado de fabricación de bolsas de plástico industriales.