Modelling and estimation of nonlinear quantile regression with clustered data

Evaluating a clinical mentorship intervention on maternal and neonatal complications in primary health facilities in Blantyre district, Malawi: A longitudinal analysis of the Global Action in Nursing program

BACKGROUND

While Malawi has made great strides increasing the number of facility-based births, maternal and neonatal mortality remains high. An intervention started in 2019 provided short-course training followed by year-long longitudinal bedside mentorship for nurse midwives at seven health facilities in Blantyre district. The intervention was initiated following invitation from the district to improve outcomes for patients during childbirth. This study examined the impact of the intervention on the reporting of obstetric and neonatal complications and related care.

METHODS

Patient level data were collected from the District Health Information System 2 database from intervention and non-intervention facilities. Bivariate analysis explored the impact of longitudinal bedside mentorship on select District Health Information System 2 variables at six-month intervals. Outcomes were then analyzed using nonlinear quantile mixed models to better account for the impact of time and clustering at the facility level.

RESULTS

Significant changes were found in the reporting of obstetric and neonatal complications over time at intervention facilities compared to non-intervention facilities. Intervention facilities showed statistically significant increases in the reporting of prolonged labor, pre/eclampsia, fetal distress, retained placenta, and premature labor. There was also a statistically significant decrease in the reporting of no complications in the multivariate model (95%CI: -0.8 to -0.2). In both the bivariate and multivariate models, the reporting of 'None' significantly decreased (0.8 % median), while the reporting of prematurity (0.2 % median) and asphyxia (0.3 % median) both significantly increased. The missingness of data at intervention facilities decreased to almost zero compared to non-intervention facilities.

DISCUSSION

The increase in reported maternal and neonatal complications suggests improved early identification of complications at the facility level. The improved accuracy of patient data from intervention facilities shows the impact mentorship has on data quality which is crucial for the allocation of resources. By highlighting the apparent dose-response relationship of longitudinal bedside mentorship, this study will inform the broader use of mentorship in training programs. Future research is needed to explore the impact of longitudinal mentorship on quality of care.

Does heat tolerance actually predict animals' geographic thermal limits?

The "climate extremes hypothesis" is a major assumption of geographic studies of heat tolerance and climatic vulnerability. However, this assumption remains vastly untested across taxa, and multiple factors may contribute to uncoupling heat tolerance estimates and geographic limits. Our dataset includes 1000 entries of heat tolerance data and maximum temperatures for each species' known geographic limits (hereafter, Tmax). We gathered this information across major animal taxa, including marine fish, terrestrial arthropods, amphibians, non-avian reptiles, birds, and mammals. We first tested if heat tolerance constrains the Tmax of sites where species could be observed. Secondly, we tested if the strength of such restrictions depends on how high Tmax is relative to heat tolerance. Thirdly, we correlated the different estimates of Tmax among them and across species. Restrictions are strong for amphibians, arthropods, and birds but often weak or inconsistent for reptiles and mammals. Marine fish describe a non-linear relationship that contrasts with terrestrial groups. Traditional heat tolerance measures in thermal vulnerability studies, like panting temperatures and the upper set point of preferred temperatures, do not predict Tmax or are inversely correlated to it, respectively. Heat tolerance restricts the geographic warm edges more strongly for species that reach sites with higher Tmax for their heat tolerance. These emerging patterns underline the importance of reliable species' heat tolerance indexes to identify their thermal vulnerability at their warm range edges. Besides, the tight correlations of Tmax estimates across on-land microhabitats support a view of multiple types of thermal challenges simultaneously shaping ranges' warm edges for on-land species. The heterogeneous correlation of Tmax estimates in the ocean supports the view that fish thermoregulation is generally limited, too. We propose new hypotheses to understand thermal restrictions on animal distribution.

Divergent Pattern of Development in Rats and Humans

Rattus norvegicus is the second most used laboratory species and the most widely used model in neuroscience. Nonetheless, there is still no agreement regarding the temporal relationship of development between humans and rats. We addressed this question by examining the time required to reach a set of homologous developmental milestones in both species. With this purpose, a database was generated with data collected through a bibliographic survey. This database was in turn compared with other databases about the same topic present in the literature. Finally, the databases were combined, covering for the first time the entire development of the rat including the prenatal, perinatal, and postnatal periods. This combined database includes 362 dates of 181 developmental events for each species. The developmental relationship between humans and rats was better fit by a logarithmic function than by a linear function. As development progresses, an increase in the dispersion of the data is observed. Developmental relationships should not be interpreted as a univocal equivalence. In this work is proposed an alternative interpretation where the age of one species is translated into a range of ages in the other.

Quantile hidden semi-Markov models for multivariate time series

This paper develops a quantile hidden semi-Markov regression to jointly estimate multiple quantiles for the analysis of multivariate time series. The approach is based upon the Multivariate Asymmetric Laplace (MAL) distribution, which allows to model the quantiles of all univariate conditional distributions of a multivariate response simultaneously, incorporating the correlation structure among the outcomes. Unobserved serial heterogeneity across observations is modeled by introducing regime-dependent parameters that evolve according to a latent finite-state semi-Markov chain. Exploiting the hierarchical representation of the MAL, inference is carried out using an efficient Expectation-Maximization algorithm based on closed form updates for all model parameters, without parametric assumptions about the states' sojourn distributions. The validity of the proposed methodology is analyzed both by a simulation study and through the empirical analysis of air pollutant concentrations in a small Italian city.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11222-022-10130-1.

Gender Dissimilarities in Human Capital Transferability of Cuban Immigrants in the US: A Clustering Quantile Regression Coefficients Approach with Consideration of Implications for Sustainability

Female participation in the labor market has been increasing over time. Despite the fact that the level of education among women has also increased considerably, the wage gap has not narrowed to the same extent. This dichotomy presents an important challenge that the United Nations Sustainable Development Goals with respect to gender inequities must address. Hispanics constitute the largest minority group in the US, totaling 60.6 million people (18.5% of the total US population in 2020). Cubans make up the third largest group of Hispanic immigrants in the US, representing 5% of workers. This paper analyzes the conditional income distribution of Cuban immigrants in the US using the clustering of effects curves (CEC) technique in a quantile regression coefficients modeling (QRCM) framework to compare the transferability of human capital between women and men. The method uses a flexible quantile regression approach and hierarchical clustering to model the effect of covariates (such as years of education, English proficiency, US citizenship status, and age at time of migration) on hourly earnings. The main conclusion drawn from the QRCM estimations was that being a woman had the strongest negative impact on earnings and was associated with lower wages in all quantiles of the distribution. CEC analysis suggested that educational attainment was included in different clusters for the two groups, which may have indicated that education did not play the same role for men and women in income distribution.

A Randomized, Multicenter, Open-Label, Blinded End Point, Phase 2, Feasibility, Efficacy, and Safety Trial of Preoperative Microvascular Protection in Patients Undergoing Major Abdominal Surgery

BACKGROUND

The endothelial glycocalyx, a carbohydrate-rich layer coating all endothelial surfaces, plays a fundamental role in the function of microcirculation. The primary aim of this study was to evaluate the feasibility of using dexamethasone and albumin to protect the endothelial glycocalyx in patients undergoing abdominal surgery. Secondary and exploratory outcomes included efficacy and safety.

METHODS

We conducted a multicenter, open-label, blinded end point, phase 2, randomized trial. Patients undergoing colorectal, pancreas, or liver surgery were recruited and randomized to receive either intravenous dexamethasone (16 mg) and 20% albumin (100 mL) at induction of anesthesia, then 200 mL of 20% albumin with each subsequent 1000 mL of crystalloid administered (dexamethasone and albumin [Dex-Alb] group), or crystalloid fluid only with no dexamethasone (control group). Feasibility end points included patient recruitment and retention, consent rate, and successful study drug administration. The primary efficacy end point was the measurement of plasma syndecan-1 level on postoperative day (POD) 1, and secondary end points were heparan sulfate levels and inflammatory markers measured at 4 perioperative timepoints. Safety end points included errors in administration of the intervention, hyperglycemia, occurrence of postoperative complications, and patient retention.

RESULTS

Seventy-two patients were randomized. All feasibility end points were achievable. There were no statistically significant differences observed in median (interquartile range) syndecan-1 levels on POD 1 (39 ng·mL-1 [20-97] in the Dex-Alb group versus 41 ng·mL-1 [19-84] in the control group; difference in medians -2.1, 95% confidence interval [CI], -13 to 8.6; P = .69). The Dex-Alb group had lower POD 1 heparan sulfate levels (319 ng·mL-1 [161-717] in the Dex-Alb group versus 1422 [670-2430] ng·mL-1 in the control group; difference in medians -1085, 95% CI, -1779 to -391) and C-reactive protein (CRP) levels on POD 1 (48 [29-77] mg·L-1 in the Dex-Alb group versus 85 mg·L-1 [49-133] in the control group; difference in medians -48, 95% CI, -75 to -21). Fewer patients had one or more postoperative complication in the Dex-Alb group than in the control group (6 [17%] vs 18 patients [50%]; odds ratio = 0.2, 95% CI, 0.06-0.6).

CONCLUSIONS

Intravenous dexamethasone and albumin administration was feasible but did not reduce syndecan-1 on POD 1 in patients undergoing abdominal surgery. Given the clinically important CIs observed between the groups for heparan sulfate, CRP, and postoperative complications, a larger trial assessing the associations between dexamethasone and albumin administration and these outcomes is warranted.

Asymmetric dependence between stock market returns and news during COVID-19 financial turmoil

•I investigate the stock market's reaction to coronavirus news in the top six most affected countries by the pandemic.•The fake news exerts a negative nonlinear influence on the inferior and the middle quantiles throughout the distribution of returns.•The media coverage leads to a decrease in returns across middle and superior quantiles and has no effects on the inferior ones.•During COVID19 turmoil superior quantiles of returns distribution exhibit negative dependence on past performances, while inferior and middle quantiles are not affected by this phenomenon.•The gold return has a positive correlation with the stock markets, which amplifies during extreme bearish and bullish periods indicating that it does not behave as a "Safe Havens" asset.

Model-robust designs for nonlinear quantile regression

We construct robust designs for nonlinear quantile regression, in the presence of both a possibly misspecified nonlinear quantile function and heteroscedasticity of an unknown form. The asymptotic mean-squared error of the quantile estimate is evaluated and maximized over a neighbourhood of the fitted quantile regression model. This maximum depends on the scale function and on the design. We entertain two methods to find designs that minimize the maximum loss. The first is local - we minimize for given values of the parameters and the scale function, using a sequential approach, whereby each new design point minimizes the subsequent loss, given the current design. The second is adaptive - at each stage, the maximized loss is evaluated at quantile estimates of the parameters, and a kernel estimate of scale, and then the next design point is obtained as in the sequential method. In the context of a Michaelis-Menten response model for an estrogen/hormone study, and a variety of scale functions, we demonstrate that the adaptive approach performs as well, in large study sizes, as if the parameter values and scale function were known beforehand and the sequential method applied. When the sequential method uses an incorrectly specified scale function, the adaptive method yields an, often substantial, improvement. The performance of the adaptive designs for smaller study sizes is assessed and seen to still be very favourable, especially so since the prior information required to design sequentially is rarely available.

Generalized linear mixed quantile regression with panel data

A new generalized linear mixed quantile model for panel data is proposed. This proposed approach applies GEE with smoothed estimating functions, which leads to asymptotically equivalent estimation of the regression coefficients. Random effects are predicted by using the best linear unbiased predictors (BLUP) based on the Tweedie exponential dispersion distributions which cover a wide range of distributions, including those widely used ones, such as the normal distribution, Poisson distribution and gamma distribution. A Taylor expansion of the quantile estimating function is used to linearize the random effects in the quantile process. The parameter estimation is based on the Newton-Raphson iteration method. Our proposed quantile mixed model gives consistent estimates that have asymptotic normal distributions. Simulation studies are carried out to investigate the small sample performance of the proposed approach. As an illustration, the proposed method is applied to analyze the epilepsy data.

Quantile Regression Modeling of Latent Trajectory Features with Longitudinal Data

Quantile regression has demonstrated promising utility in longitudinal data analysis. Existing work is primarily focused on modeling cross-sectional outcomes, while outcome trajectories often carry more substantive information in practice. In this work, we develop a trajectory quantile regression framework that is designed to robustly and flexibly investigate how latent individual trajectory features are related to observed subject characteristics. The proposed models are built under multilevel modeling with usual parametric assumptions lifted or relaxed. We derive our estimation procedure by novelly transforming the problem at hand to quantile regression with perturbed responses and adapting the bias correction technique for handling covariate measurement errors. We establish desirable asymptotic properties of the proposed estimator, including uniform consistency and weak convergence. Extensive simulation studies confirm the validity of the proposed method as well as its robustness. An application to the DURABLE trial uncovers sensible scientific findings and illustrates the practical value of our proposals.