Collinearity in generalized linear models

Penalized estimation in parametric frailty model

Frailty model examines the effect of observable and non-observable factors on time to event data. Presence of collinearity produces unstable estimates of parameters. Therefore, this research focus on the penalized estimation of frailty model and proposed the new estimator which is the extension of ridge and principal component estimators. Simulation is run to reveal the performance of proposed estimator. Moreover, the technique is applied on NFHS (National Family Health Survey) data to examine the infant mortality in India.

Assessment of malaria risk in Southeast Asia: a systematic review

BACKGROUND

Several countries in Southeast Asia are nearing malaria elimination, yet eradication remains elusive. This is largely due to the challenge of focusing elimination efforts, an area where risk prediction can play an essential supporting role. Despite its importance, there is no standard numerical method to quantify the risk of malaria infection. Thus, there is a need for a consolidated view of existing definitions of risk and factors considered in assessing risk to analyse the merits of risk prediction models. This systematic review examines studies of the risk of malaria in Southeast Asia with regard to their suitability in addressing the challenges of malaria elimination in low transmission areas.

METHODS

A search of four electronic databases over 2010-2020 retrieved 1297 articles, of which 25 met the inclusion and exclusion criteria. In each study, examined factors included the definition of the risk and indicators of malaria transmission used, the environmental and climatic factors associated with the risk, the statistical models used, the spatial and temporal granularity, and how the relationship between environment, climate, and risk is quantified.

RESULTS

This review found variation in the definition of risk used, as well as the environmental and climatic factors in the reviewed articles. GLM was widely adopted as the analysis technique relating environmental and climatic factors to malaria risk. Most of the studies were carried out in either a cross-sectional design or case-control studies, and most utilized the odds ratio to report the relationship between exposure to risk and malaria prevalence.

CONCLUSIONS

Adopting a standardized definition of malaria risk would help in comparing and sharing results, as would a clear description of the definition and method of collection of the environmental and climatic variables used. Further issues that need to be more fully addressed include detection of asymptomatic cases and considerations of human mobility. Many of the findings of this study are applicable to other low-transmission settings and could serve as a guideline for further studies of malaria in other regions.

Biased proportional hazard regression estimator in the existence of collinearity

This paper proposed a new biased proportional hazard regression (PHR) estimator which is the combination of elastic net proportional hazard regression (ENPHR) and principal components proportional hazard regression (PCPHR) estimator. Comparison of proposed estimator with ENPHR, PCPHR, ridge PHR, lasso PHR, r - k class PHR and maximum likelihood (ML) estimators is done in terms of scalar mean square error (MSE). Simulation study is conducted to examine the performance of each estimator. Furthermore, the developed estimator is utilized to analyze the infant mortality in Delhi, India.

Systemic physiology augmented functional near-infrared spectroscopy: a powerful approach to study the embodied human brain

In this Outlook paper, we explain why an accurate physiological interpretation of functional near-infrared spectroscopy (fNIRS) neuroimaging signals is facilitated when systemic physiological activity (e.g., cardiorespiratory and autonomic activity) is measured simultaneously by employing systemic physiology augmented functional near-infrared spectroscopy (SPA-fNIRS). The rationale for SPA-fNIRS is twofold: (i) SPA-fNIRS enables a more complete interpretation and understanding of the fNIRS signals measured at the head since they contain components originating from neurovascular coupling and from systemic physiological sources. The systemic physiology signals measured with SPA-fNIRS can be used for regressing out physiological confounding components in fNIRS signals. Misinterpretations can thus be minimized. (ii) SPA-fNIRS enables to study the embodied brain by linking the brain with the physiological state of the entire body, allowing novel insights into their complex interplay. We envisage the SPA-fNIRS approach will become increasingly important in the future.

Parametric Frailty Analysis in Presence of Collinearity: An Application to Assessment of Infant Mortality

This paper analyzes the time to event data in the presence of collinearity. To address collinearity, the ridge regression estimator was applied in multiple and logistic regression as an alternative to the maximum likelihood estimator (MLE), among others. It has a smaller mean square error (MSE) and is therefore more precise. This paper generalizes the approach to address collinearity in the frailty model, which is a random effect model for the time variable. A simulation study is conducted to evaluate its performance. Furthermore, the proposed method is applied on real life data taken from the largest sample survey of India, i.e., national family health survey (2005–2006 ) data to evaluate the association of different determinants on infant mortality in India.

Influence of Nutrient Intake on 24 Hour Urinary Hydration Biomarkers Using a Clustering-Based Approach

Previous work focusing on understanding nutrient intake and its association with total body water homeostasis neglects to consider the collinearity of types of nutrients consumed and subsequent associations with hydration biomarkers. Therefore, the purpose of this study was to analyze consumption patterns of 23 a priori selected nutrients involved in osmotic homeostasis, as well as their association with 24 h urinary hydration markers among fifty African–American first-year college students through a repeated measures observation in a daily living setting. Through application of hierarchical clustering, we were able to identity four clusters of nutrients based on 24 h dietary recalls: (1) alcohol + pinitol, (2) water + calcium + magnesium + erythritol + inositol + sorbitol + xylitol, (3) total calories + total fat + total protein + potassium + sodium + zinc + phosphorous + arginine, and (4) total carbohydrates + total fiber + soluble fiber + insoluble fiber + mannitol + betaine. Furthermore, we found that consumption of nutrients in Cluster #2 was significantly predictive of urine osmolality (p = 0.004); no other clusters showed statistically significant associations with 24 h urinary hydration biomarkers. We conclude that there may be some nutrients that are commonly consumed concomitantly (at the day level), across a variety of settings and populations, and that a limited subset of the clustering of these nutrients may associate with body water status.

Effects of residual smoothing on the posterior of the fixed effects in disease-mapping models

Disease-mapping models for areal data often have fixed effects to measure the effect of spatially varying covariates and random effects with a conditionally autoregressive (CAR) prior to account for spatial clustering. In such spatial regressions, the objective may be to estimate the fixed effects while accounting for the spatial correlation. But adding the CAR random effects can cause large changes in the posterior mean and variance of fixed effects compared to the nonspatial regression model. This article explores the impact of adding spatial random effects on fixed effect estimates and posterior variance. Diagnostics are proposed to measure posterior variance inflation from collinearity between the fixed effect covariates and the CAR random effects and to measure each region's influence on the change in the fixed effect's estimates by adding the CAR random effects. A new model that alleviates the collinearity between the fixed effect covariates and the CAR random effects is developed and extensions of these methods to point-referenced data models are discussed.