Victor Hugo Morales
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Victor Hugo Morales has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Carlos Arturo Panza
Departamento de Estadística, Universidad Nacional de Colombia, Bogotá 110221, Colombia
2 shared publications - Antonio José Martínez-López
Departamento de Matemáticas y Estadística, Universidad de Córdoba, Montería 230027, Colombia
1 shared publication - Fabián Alberto Barrios Simanca
Universidad de Córdoba
1 shared publication Jose Alberto Vargas
Statistics Department, Universidad Nacional de Colombia, Bogotá, Colombia
1 shared publication- N. Jose Alberto Vargas
National University of Colombia
1 shared publication - Osnamir Elias Bru-Cordero
Dirección Académica, Universidad Nacional de Colombia, Sede de La Paz, Valledupar 202010, Colombia
1 shared publication
Latest Publications
- Open Access
- 5 August 2026
- Published by Universidad Militar Nueva Granada in Revista Facultad de Ciencias Básicas
- Vol. 20 (1)
Caracterización de las variaciones espaciotemporales del material particulado PM2,5 en tres ciudades de Colombia mediante técnicas de análisis de datos funcionales
La contaminación del aire supone un riesgo importante para la salud respiratoria de las personas y, además de sus consecuencias sobre la salud, tiene efectos negativos, tanto ambientales como económicos. En este estudio se trabajó con datos de concentración de PM2,5, contaminante formado por partículas suspendidas en el aire con un diámetro aerodinámico menor o igual que 2,5 micrómetros (µm). Para el análisis, se utilizaron datos históricos de la calidad del aire provenientes de estaciones de monitoreo ubicadas en Bogotá, Medellín y Cali, durante el 2023, analizados mediante técnicas de análisis de datos funcionales como el análisis de varianza funcional (F-Anova) de una vía, comparaciones múltiples de detección de curvas atípicas y mapas de calor para visualizar la distribución espacial de las concentraciones. Los resultados del F-Anova mostraron que existe evidencia de diferencias significativas entre las concentraciones promedio de PM2,5 de las tres ciudades seleccionadas (p < 0,001 . Medellín presentó los mayores niveles de concentración, con valores entre 20,65 y 77,08 µg/m³, superiores a las metas intermedias anuales recomendadas por la Organización Mundial de la Salud. Adicionalmente, la ciudad mostró una mayor variabilidad espacial y temporal en las concentraciones registradas, mientras que Bogotá y Cali, con concentraciones promedio de 15,20 µg/m³ y 13,13 µg/m³, respectivamente, no presentaron diferencias significativas entre sí. Se concluye que Medellín presenta una situación preocupante en términos de calidad del aire en comparación con otras ciudades importantes del país, así como la utilidad del análisis de datos funcionales en este contexto.
- 5 August 2026
- Published by Universidad Militar Nueva Granada in Revista Facultad de Ciencias Básicas
- Vol. 20 (1)
Open AccessCaracterización de las variaciones espaciotemporales del material particulado PM2,5 en tres ciudades de Colombia mediante técnicas de análisis de datos funcionales
La contaminación del aire supone un riesgo importante para la salud respiratoria de las personas y, además de sus consecuencias sobre la salud, tiene efectos negativos, tanto ambientales como económicos. En este estudio se trabajó con datos de concentración de PM2,5, contaminante formado por partículas suspendidas en el aire con un diámetro aerodinámico menor o igual que 2,5 micrómetros (µm). Para el análisis, se utilizaron datos históricos de la calidad del aire provenientes de estaciones de monitoreo ubicadas en Bogotá, Medellín y Cali, durante el 2023, analizados mediante técnicas de análisis de datos funcionales como el análisis de varianza funcional (F-Anova) de una vía, comparaciones múltiples de detección de curvas atípicas y mapas de calor para visualizar la distribución espacial de las concentraciones. Los resultados del F-Anova mostraron que existe evidencia de diferencias significativas entre las concentraciones promedio de PM2,5 de las tres ciudades seleccionadas (p < 0,001 . Medellín presentó los mayores niveles de concentración, con valores entre 20,65 y 77,08 µg/m³, superiores a las metas intermedias anuales recomendadas por la Organización Mundial de la Salud. Adicionalmente, la ciudad mostró una mayor variabilidad espacial y temporal en las concentraciones registradas, mientras que Bogotá y Cali, con concentraciones promedio de 15,20 µg/m³ y 13,13 µg/m³, respectivamente, no presentaron diferencias significativas entre sí. Se concluye que Medellín presenta una situación preocupante en términos de calidad del aire en comparación con otras ciudades importantes del país, así como la utilidad del análisis de datos funcionales en este contexto.
- Open Access
- 11 July 2026
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 23 (7) , 895
Addressing Class Imbalance in Low Birth Weight Prediction: A Quantile-Based Outcome Redefinition Framework Using Colombian Health Surveillance Data
Low birth weight (LBW), defined by the World Health Organization as birth weight below 2500 g, remains a major public health concern. This study evaluates whether a quantile-based outcome redefinition can improve predictive severity stratification among newborns already classified as LBW. We analyzed deidentified SIVIGILA surveillance records from Medellín, Colombia (2011–2021; n = 10,185), all corresponding to confirmed LBW births. The analysis therefore does not model LBW versus normal birth weight. Instead, the binary outcome was redefined within the LBW cohort using the first quartile of birth weight ( = 2240 g), distinguishing a -defined severe LBW stratum from a moderate LBW stratum (2240–2499 g). The WHO 2500 g threshold is retained as the clinical and public-health definition of LBW; the threshold is used only for risk stratification, surveillance, and predictive modeling. Models based on logistic regression, class weighting, SMOTE, and Elastic Net were compared using discrimination, classification, and calibration metrics. The proposed outcome redefinition strategy led to higher sensitivity ( to ), F1 score ( to ), and AUC ( to ) compared with baseline models. A sensitivity–specificity tradeoff analysis across classification thresholds is also presented to support practical implementation in epidemiological surveillance contexts. Overall, the findings demonstrate that redefining the outcome variable using distribution-based thresholds can be an effective and interpretable strategy for mitigating class imbalance in rare-event epidemiological data, providing a practical framework for improving predictive modeling in maternal and neonatal health surveillance systems.- 11 July 2026
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 23 (7) , 895
Open AccessAddressing Class Imbalance in Low Birth Weight Prediction: A Quantile-Based Outcome Redefinition Framework Using Colombian Health Surveillance Data
Low birth weight (LBW), defined by the World Health Organization as birth weight below 2500 g, remains a major public health concern. This study evaluates whether a quantile-based outcome redefinition can improve predictive severity stratification among newborns already classified as LBW. We analyzed deidentified SIVIGILA surveillance records from Medellín, Colombia (2011–2021; n = 10,185), all corresponding to confirmed LBW births. The analysis therefore does not model LBW versus normal birth weight. Instead, the binary outcome was redefined within the LBW cohort using the first quartile of birth weight ( = 2240 g), distinguishing a -defined severe LBW stratum from a moderate LBW stratum (2240–2499 g). The WHO 2500 g threshold is retained as the clinical and public-health definition of LBW; the threshold is used only for risk stratification, surveillance, and predictive modeling. Models based on logistic regression, class weighting, SMOTE, and Elastic Net were compared using discrimination, classification, and calibration metrics. The proposed outcome redefinition strategy led to higher sensitivity ( to ), F1 score ( to ), and AUC ( to ) compared with baseline models. A sensitivity–specificity tradeoff analysis across classification thresholds is also presented to support practical implementation in epidemiological surveillance contexts. Overall, the findings demonstrate that redefining the outcome variable using distribution-based thresholds can be an effective and interpretable strategy for mitigating class imbalance in rare-event epidemiological data, providing a practical framework for improving predictive modeling in maternal and neonatal health surveillance systems. - Open Access
Revision of the Screening Robust Estimation Method for the Retrospective Analysis of Normal Processes
This paper provides a comprehensive review of the Screening Robust Estimation Method (SREM) for normal processes in Phase I. Particular emphasis is placed on the exponentially weighted moving average (EWMA) control chart, which is employed in the retrospective monitoring stage. A central concern addressed in this discussion is that the EWMA chart is said to be based on the false alarm rate (FAR) design criterion, but it is accurately implemented. It is well established that FAR-based methods for Phase I monitoring assume that the distribution of the monitoring statistic remains invariant at each sampling instance. However, the EWMA statistic inherently introduces a sequential dependence among all sampling moments, which contradicts this assumption. This paper shows that a modified EWMA chart, incorporating probability-based control limits rather than the conventional formulation utilized in the SREM, enhances the monitoring of normal processes in Phase I. Through simulations, it is established that the new design proposal of an EWMA chart for Phase I monitoring has a slightly narrower decision threshold among the control methodologies included in the study. The new chart is as effective as the traditional charts in detecting localized increases in the target value of the mean of a normal process, and outperforms them when other types of anomalies are present in the available preliminary samples.Open AccessRevision of the Screening Robust Estimation Method for the Retrospective Analysis of Normal Processes
This paper provides a comprehensive review of the Screening Robust Estimation Method (SREM) for normal processes in Phase I. Particular emphasis is placed on the exponentially weighted moving average (EWMA) control chart, which is employed in the retrospective monitoring stage. A central concern addressed in this discussion is that the EWMA chart is said to be based on the false alarm rate (FAR) design criterion, but it is accurately implemented. It is well established that FAR-based methods for Phase I monitoring assume that the distribution of the monitoring statistic remains invariant at each sampling instance. However, the EWMA statistic inherently introduces a sequential dependence among all sampling moments, which contradicts this assumption. This paper shows that a modified EWMA chart, incorporating probability-based control limits rather than the conventional formulation utilized in the SREM, enhances the monitoring of normal processes in Phase I. Through simulations, it is established that the new design proposal of an EWMA chart for Phase I monitoring has a slightly narrower decision threshold among the control methodologies included in the study. The new chart is as effective as the traditional charts in detecting localized increases in the target value of the mean of a normal process, and outperforms them when other types of anomalies are present in the available preliminary samples. - Open Access
Control Charts for Monitoring the Mean of Skew-Normal Samples
The presence of asymmetric data in production processes or service operations has prompted the development of new monitoring schemes. In this article, an adapted version of the exponentially weighted moving averages (EWMA) control chart with dynamic limits is proposed to monitor the mean of samples from the skew-normal distribution. The detection ability of the proposed control chart in online monitoring was investigated by simulating the average run length (ARL) performance for different out-of-control scenarios. The results of the simulation study suggest that the proposed scheme overcomes the main drawback of the recently developed Shewhart-type control scheme. As shown in this article, the existing Shewhart-type procedure exhibits the undesirable property of taking longer to detect changes in the mean value of skewed normal observations due to increases in the shape parameter of the basic distribution than in stable conditions. The proposed control chart was shown to work fairly acceptably in all considered out-of-control scenarios.
Open AccessControl Charts for Monitoring the Mean of Skew-Normal Samples
The presence of asymmetric data in production processes or service operations has prompted the development of new monitoring schemes. In this article, an adapted version of the exponentially weighted moving averages (EWMA) control chart with dynamic limits is proposed to monitor the mean of samples from the skew-normal distribution. The detection ability of the proposed control chart in online monitoring was investigated by simulating the average run length (ARL) performance for different out-of-control scenarios. The results of the simulation study suggest that the proposed scheme overcomes the main drawback of the recently developed Shewhart-type control scheme. As shown in this article, the existing Shewhart-type procedure exhibits the undesirable property of taking longer to detect changes in the mean value of skewed normal observations due to increases in the shape parameter of the basic distribution than in stable conditions. The proposed control chart was shown to work fairly acceptably in all considered out-of-control scenarios.
- 9 December 2019
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 51 (5) , 2646-2666
The effect of aggregating multivariate count data using Poisson profiles
The effect of aggregating data has been studied in several situations, including some related to health surveillance, from which univariate count data are frequently observed. However, this effect has not been studied in more complex situations such as the annual aggregations of cases of several diseases, discriminated by the age of patients. In this article we study the effect of aggregation of multivariate count data that depend on a single covariate, in the context of Statistical Quality Control, using a methodology based on Poisson profile monitoring. More specifically, the relative performance of two monitoring schemes is evaluated in terms of their average time to signal (ATS) when aggregated and disaggregated information is used. We also study whether or not the aggregation effect is the same for the two schemes.
- 9 December 2019
- Published by Taylor & Francis in Communications in Statistics - Simulation and Computation
- Vol. 51 (5) , 2646-2666
The effect of aggregating multivariate count data using Poisson profiles
The effect of aggregating data has been studied in several situations, including some related to health surveillance, from which univariate count data are frequently observed. However, this effect has not been studied in more complex situations such as the annual aggregations of cases of several diseases, discriminated by the age of patients. In this article we study the effect of aggregation of multivariate count data that depend on a single covariate, in the context of Statistical Quality Control, using a methodology based on Poisson profile monitoring. More specifically, the relative performance of two monitoring schemes is evaluated in terms of their average time to signal (ATS) when aggregated and disaggregated information is used. We also study whether or not the aggregation effect is the same for the two schemes.
- Open Access
- 1 July 2017
- Published by Universidad Nacional de Colombia in Revista Colombiana de Estadística
- Vol. 40 (2) , 243-262
Monitoring Aggregated Poisson Data for Processes with Time-Varying Sample Sizes
This article deals with the effect of data aggregation, when Poisson processes with varying sample sizes, are monitored. These aggregation procedures are necessary or convenient in many applications, and can simplify monitoring processes. In health surveillance applications it is a common practice to aggregate the observations during a certain time period and monitor the processes at the end of it. Also, in this type of applications it is very frequent that the sample size vary over time, which makes that instead of monitor the mean of the processes, as would be in the case of Poisson observations with constant sample size, the occurrence rate of an adverse event is monitored.Two control charts for monitoring the count Poisson data with time-varying sample sizes are proposed by Shen et al. (2013) and Dong et al. (2008). We use the average run length (ARL) to compare the performance of these control charts when different levels of aggregation, two scenarios of generating of sample size and different out-of-control states are considered. Simulation studies show the effect of data aggregation in some situations, as well as those in which their use may be appropriate without significantly compromising the prompt detection of out-of-control signals. We also show the effect of data aggregation with an example of application in health surveillance.
- 1 July 2017
- Published by Universidad Nacional de Colombia in Revista Colombiana de Estadística
- Vol. 40 (2) , 243-262
Open AccessMonitoring Aggregated Poisson Data for Processes with Time-Varying Sample Sizes
This article deals with the effect of data aggregation, when Poisson processes with varying sample sizes, are monitored. These aggregation procedures are necessary or convenient in many applications, and can simplify monitoring processes. In health surveillance applications it is a common practice to aggregate the observations during a certain time period and monitor the processes at the end of it. Also, in this type of applications it is very frequent that the sample size vary over time, which makes that instead of monitor the mean of the processes, as would be in the case of Poisson observations with constant sample size, the occurrence rate of an adverse event is monitored.Two control charts for monitoring the count Poisson data with time-varying sample sizes are proposed by Shen et al. (2013) and Dong et al. (2008). We use the average run length (ARL) to compare the performance of these control charts when different levels of aggregation, two scenarios of generating of sample size and different out-of-control states are considered. Simulation studies show the effect of data aggregation in some situations, as well as those in which their use may be appropriate without significantly compromising the prompt detection of out-of-control signals. We also show the effect of data aggregation with an example of application in health surveillance.