Latent Groups Research Articles

Experimental study on the expression of ubiquitin-specific protease-25 in temporal cortex of epileptic rats

Objective To study the expression of ubiquitin-specific protease 25 (USP25) in the temporal cortex of the kainic acid (KA) induced epilepsy rat model. Methods Fifty-two male SD rats were randomly divided into the epilepsy model group (n=39) and sham-operated control group (n=13) with the random number table. The epilepsy model group was established by injecting KA into the amygdala, then the epileptic rats were randomly divided into 3 groups according to the modeling success time: 1 day for acute period, 7 days for latent period and 30 days for chronic period (13 rats in each group). Those rats were sampled at the end of observation. Rats in the control group were injected with normal saline into the amygdala and sampled together with those in the experimental group. Immunohistochemistry and immunofluorescence double labeling was used to test USP25 expression and its co-expression with neurons (NeuN) and astrocytes (GFAP). Quantitative real-time PCR and Western blot were used to assess the change of USP25 in the temporal cortex of rats. Results In the ipsilateral temporal cortex, the positive cells of co-expression of USP25 and NeuN were increased in the later stage of epilepsy in the epilepsy model group, and the expression levels of USP25 mRNA and protein in different stages of epilepsy varied significantly (F= 25.48 and 7.68 respectively, both P<0.05). Compared with the control group (mRNA level: 1.00±0.36, protein level: 1.00±0.46), the expression of USP25 in the latent group (mRNA level: 10.80±4.82, protein level: 1.88±0.32) and the chronic group (mRNA level: 12.97±4.48, protein level: 1.92±0.26) were increased significantly (all P<0.05). In the contralateral temporal cortex, the expression levels of USP25 mRNA and protein in different stages of epilepsy also varied significantly (F=86.86 and 6.65 respectively, both P<0.05). Conclusions The increased expression of USP25 in the temporal cortex after the latent period has suggested that the deubiquitination pathway is involved in the chronic pathological process of temporal lobe epilepsy. Key words: Epilepsy, temporal lobe; Ubiquitin-specific protease 25; Rats

Improving Robustness in Q-Matrix Validation Using an Iterative and Dynamic Procedure.

In the context of cognitive diagnosis models (CDMs), a Q-matrix reflects the correspondence between attributes and items. The Q-matrix construction process is typically subjective in nature, which may lead to misspecifications. All this can negatively affect the attribute classification accuracy. In response, several methods of empirical Q-matrix validation have been developed. The general discrimination index (GDI) method has some relevant advantages such as the possibility of being applied to several CDMs. However, the estimation of the GDI relies on the estimation of the latent group sizes and success probabilities, which is made with the original (possibly misspecified) Q-matrix. This can be a problem, especially in those situations in which there is a great uncertainty about the Q-matrix specification. To address this, the present study investigates the iterative application of the GDI method, where only one item is modified at each step of the iterative procedure, and the required cutoff is updated considering the new parameter estimates. A simulation study was conducted to test the performance of the new procedure. Results showed that the performance of the GDI method improved when the application was iterative at the item level and an appropriate cutoff point was used. This was most notable when the original Q-matrix misspecification rate was high, where the proposed procedure performed better 96.5% of the times. The results are illustrated using Tatsuoka's fraction-subtraction data set.

Statistical Evaluation of Person-Oriented Mediation Using Configural Frequency Analysis.

Mediation analysis helps explain how and why two variables are related, providing information for investigating causal processes useful for theoretical and applied research (MacKinnon 2008). Inference from mediation analysis typically applies to the population, but researchers and clinicians are often interested in making inference to individual clients or small sub-populations of people. Person-oriented approaches focus on the differences between people, or latent groups of people, to ask how individuals differ across variables. A recently proposed method allows for the analysis of person differences as part of mediation. The method from configural frequency analysis, which we call configural frequency mediation, is based on log-linear modeling of contingency tables. The complexity of configural frequency mediation and its use of a causal steps mediation method, may contribute to the lack of application and study of this promising method since its introduction in the literature a decade ago (von Eye et al. 2009, 2010) In this paper we clarify the steps used for configural frequency mediation and report the results of a large statistical simulation study evaluating the method and comparing it to the variable-oriented traditional method using logistic regression analysis. Overall, configural frequency mediation analysis tended to have excessive type I error rates but we describe an alternative approach to configural mediation analysis based on a joint significance test that had adequate performance. We also clarify the decision rules that define configural mediation analysis and develop a test for configural frequency mediation using a joint significance mediation method.

Heterogeneous choice of home renewable energy equipment conditioning on the choice of electric vehicles

New mobility tools like electric vehicle and e-bike have been an important strategy in many cities for the reduction of traffic problems and the implementation of renewable energy infrastructures. The choice of individuals on mobility tools however may depend on the magnitude of a comparable cost. Home renewable energy equipment like solar panel which generates energy at home may potentially reduce the electricity expenditure of e-mobility. This paper therefore aims to investigate the choice behavior of individuals on their home renewable energy equipment conditioning on the choice of mobility tools. More specifically, we identify the differences among individuals in their preferences and the latent groups. Using the stated preference data collected in the city of Weiz, Austria, we estimated a latent class choice model with social demographics representing the user group membership. Results show that the synergy effect between EV and solar panels and self-sufficient home energy system is more attractive to people with low income although their willingness to buy are lower than people with high income.

Effects of intrauterine latent iron deficiency on auditory neural maturation in full‐term newborns

ObjectiveThis study analyzed the relationship between latent iron deficiency evaluated by ferritin, and the myelination of the central nervous system evaluated through the brainstem evoked response audiometry test. MethodA total of 109 full‐term newborns, born without anemia and risk factor for hearing deficiency, were enrolled. After delivery, umbilical cord blood was collected to determine ferritin and hematocrit levels. The brainstem evoked response audiometry test was carried out in the first 28 days of life. Analysis was performed between the control group (n=71) with ferritin greater than 75ng/mL, and the latent iron deficiency group (n=38) with ferritin between 11 and 75ng/mL. Results were presented as mean±standard deviation. Statistical analysis was performed using GraphPad prism7 and SPSS with a significance level of 5%. ResultsA significant higher V‐wave (p=0.02) and interpeak intervals I–III (p=0.014), I–V (p=0.0003), and III‐V (p=0.0002) latencies were found in the latent iron deficiency group, as well as a significant inversely proportional correlation between ferritin and the same wave and intervals (p=0.003, p=0.0013, p=0.0002, p=0.009, respectively). Multiple correlation analysis showed a significant correlation of latent iron deficiency with all interpeak intervals, even taking into account newborn gestational age. ConclusionIron deficiency anemia is a prevalent pathology; this study showed auditory delayed maturation associated to intrauterine iron deficiency, even in its latent form. This reinforces the importance of adopting effective measures, on a global scale, to prevent and treat this pathology in different life periods, especially in the most vulnerable population.

Estimating Social Gradients in Health for UK Mothers and Infants of Pakistani Origin: Do Latent Class Measures of Socioeconomic Position Help?

The social gradients in health typically seen in the whole UK population are attenuated/non-existent in some minority ethnic groups. This study aims to compare latent class measures to conventional measures of socioeconomic position (SEP) in the estimation of social gradients in health for women and infants of Pakistani origin in the Born in Bradford cohort. We compare social gradients in birth outcomes, smoking during pregnancy, and maternal mental health using various measures of SEP (including latent class analysis groups) with multivariate regression models. Social gradients in maternal mental health and low birth weight were more clearly defined than before. Otherwise, the latent class SEP variables did not reveal social gradients in health that were not obvious before. This study adds to the evidence that there are weak, if any, social gradients in maternal and child health among UK women and infants of Pakistani origin when measured with these SEP variables.

Social structure learning in human anterior insula.

Humans form social coalitions in every society, yet we know little about how we learn and represent social group boundaries. Here we derive predictions from a computational model of latent structure learning to move beyond explicit category labels and interpersonal, or dyadic, similarity as the sole inputs to social group representations. Using a model-based analysis of functional neuroimaging data, we find that separate areas correlate with dyadic similarity and latent structure learning. Trial-by-trial estimates of 'allyship' based on dyadic similarity between participants and each agent recruited medial prefrontal cortex/pregenual anterior cingulate (pgACC). Latent social group structure-based allyship estimates, in contrast, recruited right anterior insula (rAI). Variability in the brain signal from rAI improved prediction of variability in ally-choice behavior, whereas variability from the pgACC did not. These results provide novel insights into the psychological and neural mechanisms by which people learn to distinguish 'us' from 'them.'

Adverse childhood experiences and the associations with depression and anxiety in adolescents

ObjectivesThere has been increasing attention to adverse childhood experiences (ACEs) among adolescents in the U.S because ACEs may result in severe mental health issues. Although associations between ACEs and mental health have been explored, research on how different types or combinations of ACEs render different impacts on adolescents is limited. Therefore, this study aims to (a) examine latent classes of ACEs among adolescents who have experienced at least one ACE and (b) investigate associations of each latent group of ACEs with mental health problems, depression and anxiety. MethodQuestionnaires on ACEs and depression/anxiety from the 2016 National Survey of Children’s Health (NSCH) were used, and a total of 11,437 adolescents aged 10–17 years were included in this study. For analyses, latent class analysis (LCA) was implemented to identify the number and types of classes, which are pertinent to represent the heterogenous combinations of ACEs. Moreover, chi-square tests and ordinal regression were performed to investigate the associations of class memberships within ACEs with depression/anxiety. ResultsThe LCA found four class memberships within ACEs: Multiple High-Risk, Broken Family, Income Hardship, and Multiple Low-Risk. These classes displayed differences in depression/anxiety. For both pre-existing and current conditions of depression/anxiety, the most prominence has been found in the Multiple High-Risk, followed by the Multiple Low-Risk, the Broken Family, and the Income Hardship, in order. ConclusionsThese differences among the classes indicate that understanding of ACEs and interventions should be based on considering latent classes of ACEs.

A multivariate latent class profile analysis for longitudinal data with a latent group variable

In research on behavioral studies, significant attention has been paid to the stage-sequential process for multiple latent class variables. We now explore the stage-sequential process of multiple latent class variables using the multivariate latent class profile analysis (MLCPA). A latent profile variable, representing the stage-sequential process in MLCPA, is formed by a set of repeatedly measured categorical response variables. This paper proposes the extended MLCPA in order to explain an association between the latent profile variable and the latent group variable as a form of a two-dimensional contingency table. We applied the extended MLCPA to the National Longitudinal Survey on Youth 1997 (NLSY97) data to investigate the association between of developmental progression of depression and substance use behaviors among adolescents who experienced Authoritarian parental styles in their youth.

Synergistic Relay Reactions To Achieve Redox‐Neutral α‐Alkylations of Olefinic Alcohols with Ruthenium(II) Catalysis

AbstractHerein, we report a ruthenium‐catalyzed redox‐neutral α‐alkylation of unsaturated alcohols based on a synergistic relay process involving olefin isomerization (chain walking) and umpolung hydrazone addition, which takes advantage of the interaction between the two rather inefficient individual reaction steps to enable an efficient overall process. This transformation shows the compatibility of hydrazone‐type “carbanions” and active protons in a one‐pot reaction, and at the same time achieves the first Grignard‐type nucleophilic addition using olefinic alcohols as latent carbonyl groups, providing a higher yield of the corresponding secondary alcohol than the classical hydrazone addition to aldehydes does. A broad scope of unsaturated alcohols and hydrazones, including some complex structures, can be successfully employed in this reaction, which shows the versatility of this approach and its suitability as an alternative, efficient means for the generation of secondary and tertiary alcohols.

Three-Variate Longitudinal Patterns of Metabolic Control, Body Mass Index, and Insulin Dose during Puberty in a Type 1 Diabetes Cohort: A Group-Based Multitrajectory Analysis

To analyze the interrelationship of metabolic control, age- and sex-adjusted body mass index, and daily insulin dose and to identify heterogeneous multivariate developmental curves from childhood to young adulthood in a large cohort of children with type 1 diabetes (T1D) STUDY DESIGN: Data were extracted from the diabetes follow-up registry DPV. Longitudinal data from 9239 participants with T1D age 8-18years with diabetes duration ≥2years and ≥5years of follow-up were analyzed. We applied group-based multitrajectory modeling to identify latent groups of subjects following similar developmental curves across outcomes (hemoglobin A1c [HbA1c], age/sex-standardized body mass index [BMI-SDS], daily insulin dose per kg). Group number was based on Bayes information criterion and group size (≥5%). The group-based multitrajectory approach revealed 5 heterogeneous 3-variate trajectories during puberty. Individuals with stable good metabolic control, high-normal increasing BMI-SDS, and rising insulin dose patterns were classified as group 1 (33%). Group 2 (20%) comprised youths with intermediate-increasing HbA1c, low BMI-SDS, and steeply increasing insulin dose trajectories. Group 3 (11%) followed intermediate-rising HbA1c and high-normal increasing BMI-SDS developmental curves, while insulin dose increased steeply. In group 4 (14%), both high-increasing HbA1c and insulin dose trajectories were observed, while BMI-SDS was stable-normal. Group 5 (22%) included subjects with intermediate-rising HbA1c patterns, high-increasing BMI-SDS, and increasing insulin dose patterns. This study identified 5 distinct 3-variate curves of HbA1c, BMI-SDS, and insulin dose during puberty among youths with T1D. This approach demonstrates a considerable heterogeneity highlighting the importance of personalized medical care.

Multi-Group Transfer Learning on Multiple Latent Spaces for Text Classification

Transfer learning aims to leverage valuable information in one domain to promote the learning tasks in the other domain. Some recent studies indicated that the latent information, which has a close relationship with the high-level concepts, are more suitable for cross-domain text classification than learning raw features. To obtain more latent information existing in the latent feature space, some previous methods constructed multiple latent feature spaces. However, those methods ignored that the latent information of different latent spaces may lack the relevance for promoting the adaptability of transfer learning models, even may lead to negative knowledge transfer when there exists a glaring discrepancy among the different latent spaces. Additionally, since those methods learn the latent space distributions using a strategy of direct-promotion, their computational complexity increases exponentially as the number of latent spaces increases. To tackle this challenge, this paper proposes a Multiple Groups Transfer Learning (MGTL) method. MGTL first constructs multiple different latent feature spaces and then integrates the adjacent ones that have a similar latent feature dimension into one latent space group. Along this way, multiple latent space groups can be obtained. To enhance the relevance among these latent space groups, MGTL makes the adjacent groups contain one same latent space at least. Then, different groups will have more relevance than raw latent spaces. Second, MGTL utilizes an indirect-promotion strategy to connect different latent space groups. The computational complexity of MGTL increases linearly as the number of latent space groups increases and is superior to those multiple latent space methods based on direct-promotion. In addition, an iterative algorithm is proposed to solve the optimization problem. Finally, a set of systematic experiments demonstrate that MGTL outperforms all the compared existing methods.

Modeling Heterogeneity in Firm-level Return Predictability with Machine Learning

We develop an approach that combines the estimation of monthly firm-level expected returns with an assignment of firms to (possibly) latent groups, both based upon observable characteristics, using machine learning principles with linear models. The best performing methods are flexible two-stage sparse models that capture group-membership predictive relationships. Our results uncover sparsity together with firms' heterogeneity based on their characteristics, improving both predictability and interpretability. We propose statistical tests based on nonparametric bootstrapping for our results, and detail how different characteristics may matter for different groups of firms, making comparisons to the existing literature.

Being born to a single mother in France: trajectories of father’s involvement over the first year of life

This paper characterises families where the father is not living (or not living permanently) with the child from around birth, and identifies the drivers of the evolution of father contact over the first year of life across different types of household. We use a recent, nationally representative cohort of children born in France in 2011, Elfe (the Etude longitudinale française depuis l’enfance), and latent clustering techniques to identify different groups of households characterised by non-residential fatherhood. We show that non-residential fatherhood from around birth is not a marginal phenomenon in France, and it corresponds to a heterogeneity of situations, describing both advantaged and low involvement fathers, as well less disadvantaged but involved groups. Over the first year of life, most non-resident fathers managed to keep in contact with their child, including relatively disadvantaged groups such as migrant and young parents, although groups characterised by low father involvement shortly after birth lost contact. On the other hand, among a group of very involved non-resident fathers who were in a relationship with the mother, we observed high levels of contact and indeed co-residence when the child was one year of age. A number of channels emerged to explain the correlations between our latent groups and father contact at one year: notably, father engagement around birth, especially whether the father formally recognised the child. Trajectories of father–child involvement and of parental relationships are therefore at least as important as socio-economic conditions to understand future father contact.

Forecasting with Bayesian Grouped Random Effects in Panel Data

In this paper, we estimate and leverage latent constant group structure to generate the point, set, and density forecasts for short dynamic panel data. We implement a nonparametric Bayesian approach to simultaneously identify coefficients and group membership in the random effects which are heterogeneous across groups but fixed within a group. This method allows us to flexibly incorporate subjective prior knowledge on the group structure that potentially improves the predictive accuracy. In Monte Carlo experiments, we demonstrate that our Bayesian grouped random effects (BGRE) estimators produce accurate estimates and score predictive gains over standard panel data estimators. With a data-driven group structure, the BGRE estimators exhibit comparable accuracy of clustering with the Kmeans algorithm and outperform a two-step Bayesian grouped estimator whose group structure relies on Kmeans. In the empirical analysis, we apply our method to forecast the investment rate across a broad range of firms and illustrate that the estimated latent group structure facilitates forecasts relative to standard panel data estimators.

Hybrid Deep Framework for Group Event Recommendation

Group recommender systems suggesting items for a group of users have received many attentions recently. Some aggregation-based and model-based group recommendation methods have been proposed. However, the cold-start problem in group recommendation has not been well studied, which limits the application of group recommendation in many important domains, such as recommending offline events for a group of users. In this paper, we propose a new hybrid deep framework to solve cold-start problem of group event recommendation. Our framework incorporates multiple Restricted Boltzmann Machines (RBM) and conditional RBM. The former extracts high latent group preference from user feedback and group feedback. The latter obtains latent event features based on contextual information, such as location and organizer of events. Thus, the hybrid deep framework can utilize user feedback and contextual information of events to overcome cold-start problem. We conduct exhaustive experiments on two real-world datasets and the results show that our proposed framework outperforms the baseline group recommendation methods and alleviates the cold-start problem of group event recommendation effectively.

Factorisation machines considering the latent characteristics behind target data

A factorisation machine (FM) is often used as a regression-type prediction model that considers the interactions between features. In recent years, many researchers have focused on the differences between interactions from the perspective of prediction accuracy. In some cases, it can be assumed that there are several groups with different characteristics in terms of the relationships between input and output data for a target population. Therefore, there is a possibility that the effects of interactions will differ between input data groups, which are used to construct latent clusters. However, there has been little research on FMs considering the latent characteristics behind target data. Therefore, this paper proposes a novel type of FM that considers latent data characteristics. The proposed model can express the differences between the interaction effects of latent groups and it is expected to improve the prediction accuracy of FMs for complex problems. Based on a demonstration experiment using the MovieLens dataset, the effectiveness of our proposed model is verified.

Factorisation machines considering the latent characteristics behind target data

A factorisation machine (FM) is often used as a regression-type prediction model that considers the interactions between features. In recent years, many researchers have focused on the differences between interactions from the perspective of prediction accuracy. In some cases, it can be assumed that there are several groups with different characteristics in terms of the relationships between input and output data for a target population. Therefore, there is a possibility that the effects of interactions will differ between input data groups, which are used to construct latent clusters. However, there has been little research on FMs considering the latent characteristics behind target data. Therefore, this paper proposes a novel type of FM that considers latent data characteristics. The proposed model can express the differences between the interaction effects of latent groups and it is expected to improve the prediction accuracy of FMs for complex problems. Based on a demonstration experiment using the MovieLens dataset, the effectiveness of our proposed model is verified.

A Hybrid Generative Model for Online User Behavior Prediction

With the increase of rich datasets from various online platforms, predicting user behavior has been one of the most active research topics. The user behavior on these online platforms includes listening to music, watching videos, purchasing products, checking-in to places, and joining online sub-communities. Predicting online user behavior is an important challenge for various applications. Personalization, recommendation systems, target advertisements are based on user behavior prediction, where user's next purchases or actions need to be predicted. In this paper, we propose a hybrid generative model that can predict user behavior considering multiple factors. While previous work has been focused on two aspects individually: predicting repeat behavior or predicting new behavior, our model considers both aspects simultaneously during the learning process. The user-specific preference component is used to capture repeat behavior patterns, while the latent group preference component is used to discover new behavior. Besides these two components, we also consider the exogenous effect, which is not captured in the former two. Our experimental results on real-world datasets show how our proposed model outperforms the state-of-the-art model.

A Variational Autoencoder Mixture Model for Online Behavior Recommendation

Online behavior recommendation is an attractive research topic related to social media mining. This topic focuses on suggesting suitable behaviors for users in online platforms, including music listening, video watching, e-commerce, to name but a few to improve the user experience, an essential factor for the success of online services. A successful online behavior recommendation system should have the ability to predict behaviors that users used to performs and also suggest behaviors that users never performed before. In this paper, we develop a mixture model that contains two components to address this problem. The first component is the user-specific preference component that represents the habits of users based on their behavior history. The second component is the latent group preference component based on variational autoencoder, a deep generative neural network. This component corresponds to the hidden interests of users and allows us to discover the unseen behavior of users. We conduct experiments on various real-world datasets with different characteristics to show the performance of our model in different situations. The result indicates that our proposed model outperforms the previous mixture models for recommendation problem.