Multilevel Statistical Models Research Articles

Geographical match of objective and subjective measures of well-being at an intra-city scale

Despite human well-being serving as a crucial indicator for measuring social development and progress, the measurement of well-being faces great challenges. This study constructs a multi-level statistical model to investigate the geographical relationship between subjective well-being measure derived from a large-scale social survey and objective well-being measure derived by using a non-compensatory indicator aggregation technique and a variety of urban geospatial data. We find that a consistent resemblance between the subjective and objective measures of well-being at both the community (r = 0.61 with a p < 0.01) and sub-district scales (r = 0.62 with a p < 0.01) within a city. This finding is further supported by the estimation results from models that controls for a variety of covariate effects. Drawing on the close resemblance between the subjective and objective measures of human well-being, we develop a statistical model that links these two measurements to create a composite measure of well-being. Our results extend the understanding on the geographical match between subjective and objective measures of well-being at an intra-city spatial scale, and provide a new insight on how to leverage the emerging urban geospatial data and social survey when devising indicators of well-being.

A multilevel investigation of factors related to achievement in Ireland and Spain using PISA data

The Program for International Assessment (PISA) is a methodology for making comparative judgments about the quality of education systems. Celebrated by proponents as a transparent process that allows policy makers produce data informed judgments about relative quality of their national education system PISA – and through it the OECD – has become a key vehicle for informing and explaining educational policy development. This paper explores the Irish and Spanish outcomes of the 2018 round of PISA. It examines the contextual factors that are associated with performance at student and school level while at the same time developing a multi-level statistical model to explain divergent school performance profiles It finds that issues associated with the socio-economic level of the students, the repetition rate, and student age are common across all domains in both countries. It suggests that the socio-economic status of Spanish students at school level is not significant, that the shortage of teachers in Ireland affects student performance, and that immigrant status does not disadvantage Spanish student performance. It concludes by suggesting that studies involving a wider application of the model be undertaken to assess possible social, economic, and cultural causes that may explain the differences in variable significance in each country.

Construction of multilevel statistical models in health research: Foundations and generalities

This topic review aims to present a global vision of multilevel analysis models’ applicability to health research, explaining its theoretical, methodological, and statistical foundations. We describe the basic steps to build these models and examples of their application according to the data hierarchical structure. It ir worth noticing that before using these models, researchers must have a rationale for needing them, and a statistical evaluation accounting for the variance percentage explained by the observations grouping effect. The requirements to conduct this type of analysis depends on special conditions such as the type of variables, the number of units per level, or the type of hierarchical structure. We conclude that multilevel analysis models are a useful tool to integrate information, considering the complexity of the relationships and interactions involved in most health conditions, including the loss of independence between observation units.

The relationship between narcissistic traits and attitudes toward infidelity: A dyadic analysis.

Previous research suggested that narcissism is associated with infidelity and reduced commitment in relationships. However, the majority of studies supporting this association were conducted among individuals and did not examine dyadic paths and also conceptualized and measured narcissism as a global variable, lacking a nuance perspective of the two traits of narcissism (i.e., grandiose and vulnerable). The present study sought to examine attitudes toward infidelity from a dyadic perspective, using narcissism personality traits (grandiose and vulnerable) as predictors. The effect of narcissism personality traits on attitudes toward infidelity was investigated among 135 couples (N = 270) in enduring relationships. To assess whether attitudes toward infidelity were explained by grandiose narcissism and vulnerable narcissism, we used multivariate multilevel statistical model for matched pairs to evaluate the effect of each partner's characteristics on their own (actor effect) and their partner's (partner effect) attitudes. The results indicate that females' attitudes toward infidelity were positively associated with their own grandiose narcissism and vulnerable narcissism and negatively associated with their partner's grandiose narcissism. Males' attitudes toward infidelity were positively associated with both their own and their partner's vulnerable narcissism but not with their or their partner's grandiose narcissism. The results highlighted the importance of studying different aspects of narcissism in relation to dyadic processes within intimate relationships in general and regarding infidelity in particular. Our findings suggest that more or less favorable attitudes toward infidelity depend not only on the individual's narcissistic traits but on his/her partner's grandiosity and vulnerability as well. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Highlighting the potential of multilevel statistical models for analysis of individual agroforestry systems

Agroforestry is a land-use system that combines arable and/or livestock management with tree cultivation, which has been shown to provide a wide range of socio-economic and ecological benefits. It is considered a promising strategy for enhancing resilience of agricultural systems that must remain productive despite increasing environmental and societal pressures. However, agroforestry systems pose a number of challenges for experimental research and scientific hypothesis testing because of their inherent spatiotemporal complexity. We reviewed current approaches to data analysis and sampling strategies of bio-physico-chemical indicators, including crop yield, in European temperate agroforestry systems to examine the existing statistical methods used in agroforestry experiments. We found multilevel models, which are commonly employed in ecology, to be underused and under-described in agroforestry system analysis. This Short Communication together with a companion R script are designed to act as an introduction to multilevel models and to promote their use in agroforestry research.

Environmental impacts of renting rangelands: integrating remote sensing and household surveys at the parcel level

Land rental markets are growing worldwide and facilitate efficient utilization of land. However, the short duration of occupancy and limited property rights mean that rental contracts may discourage longer-term sustainable land management. Direct investigation into the relationship between land tenure and ecological outcomes has been hampered by scale-appropriate data on land tenure, resource management, and land outcomes. In this paper, we address these issues with a study design that combines participatory mapping, household surveys, and remote sensing. We analyzed these data in a multilevel statistical model, controlling for environmental and land management influences. Our results show that rented land parcels are associated with worse rangeland outcomes compared to privately held parcels. This study contributes to the literature by documenting important empirical effects of rental markets and presenting a replicable workflow for integrating earth observations and micro-level survey data, which can be adopted by researchers and practitioners in regions where land registry data is unavailable or inaccessible. The results have important implications for incentive and compensatory-based environmental policy.

CONSTRUCTION OF MULTILEVEL STATISTICAL MODELS FOR PREDICTING WETTABILITY INDICATORS OF EASTERN LAMBEISHOR AND YAREYU FIELDS

Link for citation: Saetgaraev A.D., Galkin V.I., Putilov I.S., Nevolin A.I. Сonstruction of multilevel statistical models for predicting wettability indicators of Eastern Lambeishor and Yareyu fields. Bulletin of the Tomsk Polytechnic University. Geo Аssets Engineering, 2023, vol. 334, no. 5, рр.63-69. In Rus. The relevance. All domestic standards for laboratory studies of core oil and gas reservoirs prescribe to clean it from hydrocarbons by extraction. Cleaning of core samples is included in the stage of preparation for the main types of research. For this, a wide range of different solvents and special extraction and distillation apparatuses are used. Core samples placed in the apparatus undergo multiple cleaning cycles for a long time with high -temperature exposure. This approach to the preparation of core samples is traditional and is used for both standard and special studies. However, extraction leads to a distorted understanding of the natural wettability of the rock surface, which is subject to change and, as a rule, hydrophilizes. In this regard, it is of scientific and practical interest to assess rock wettability at various stages of sample preparation – before and after the extraction. The main aim: development of a methodology for predicting the wettability of core samples before extraction from hydrocarbons using statistical research methods. Objects: core samples of the Zadonskaya deposit (D3zd) of the Eastern Lambeishor field, Artinskaya (P1ar) and Assel-Sakmarskaya (P1a+s) deposits of the Yareyu field. Methods: Amott (Amott–Harvey) method, statistical methods. Results. With the help of a set of laboratory studies using various statistical methods, a methodology was developed for predicting the values of the wettability index for oil before extraction based on the porosity and permeability properties of core samples.

The role of team compassion in mitigating the impact of hierarchical bullying

Abstract Hierarchical bullying in public healthcare organizations is an entrenched negative behaviour that results in a range of adverse outcomes for staff, including diminished wellbeing. This study integrates social exchange and conservation of resources theories as a lens for formulating hypotheses and employs multilevel statistical modelling to examine whether team-level compassion moderates the impact of hierarchical bullying on wellbeing. Using multilevel statistical modelling, the study analysed cross-sectional data from 632 healthcare workers nested within 48 teams in a single public health district in Australia. The findings indicate that work teams with higher levels of team compassion can mitigate the negative effects of hierarchical bullying on employee wellbeing. The results imply that investing in developing compassion within teams is an effective strategy for mitigating some harmful effects of hierarchical bullying on employee outcomes.

Sidewalks, trees and shade matter: A visual landscape assessment approach to understanding people’s preferences for walking

IntroductionPublic health professionals and urban designers consider neighborhood sidewalks as a vehicle for promoting outdoor physical activity. The design of streetscape and available greenness may also influence walking behaviors and physical activity more generally. MethodData collection included a visual landscape assessment (VLA) survey, followed by focus groups to evaluate streetscape features that influence participants’ preferences for and choice of walking routes. With the considerations of equity in access to the environmental amenities, the study was conducted in marginalized communities. Sixty-nine people from low-income neighborhoods in Denver, CO participated in this study. Data were analyzed both qualitatively and quantitatively, using multilevel statistical models. ResultsMore shade and trees, higher levels of maintenance, and the presence of a buffer between the street and sidewalk increase the likelihood of intuitively choosing a street for walking. The availability of natural surveillance, the presence of an open view, and the presence of attractive buildings increase the likelihood of cognitively choosing a street for walking. ConclusionPeople‘s preferences for and choice of walking routes, which include desired shade and walkability, should be considered in neighborhood planning to promote walkable environments.

Government repression and citizen support for democratic rights in Africa

ABSTRACT Public opinion polls conducted over the past five years point to a downward trend in African citizens’ support for civil society and media freedoms. This is despite the flourishing of civil society and media actors as well as the expansion of democracy on the continent in the post-Cold War period. What explains this downward trend in public support? We use cross-national polling data from the Afrobarometer survey to examine the decline in public support for freedoms of association and media between 2011 and 2018 in the African context, a continent that has experienced decades of democratization waves and pressure. Using a multilevel statistical modelling approach, we analyse the influence of government repression of civil society and media actors on citizen support for enhanced government control over freedoms of association and the media. Our study shows that the government’s repressive actions against civil society and media actors increases the probability that citizens will support control over association and media freedoms. Concerningly, this suggests government clampdowns on democratic rights influences the African publics to support such clampdowns, potentially legitimizing them.

Multi-level multi-domain statistical shape model of the subtalar, talonavicular, and calcaneocuboid joints.

Traditionally, two-dimensional conventional radiographs have been the primary tool to measure the complex morphology of the foot and ankle. However, the subtalar, talonavicular, and calcaneocuboid joints are challenging to assess due to their bone morphology and locations within the ankle. Weightbearing computed tomography is a novel high-resolution volumetric imaging mechanism that allows detailed generation of 3D bone reconstructions. This study aimed to develop a multi-domain statistical shape model to assess morphologic and alignment variation of the subtalar, talonavicular, and calcaneocuboid joints across an asymptomatic population and calculate 3D joint measurements in a consistent weightbearing position. Specific joint measurements included joint space distance, congruence, and coverage. Noteworthy anatomical variation predominantly included the talus and calcaneus, specifically an inverse relationship regarding talar dome heightening and calcaneal shortening. While there was minimal navicular and cuboid shape variation, there were alignment variations within these joints; the most notable is the rotational aspect about the anterior-posterior axis. This study also found that multi-domain modeling may be able to predict joint space distance measurements within a population. Additionally, variation across a population of these four bones may be driven far more by morphology than by alignment variation based on all three joint measurements. These data are beneficial in furthering our understanding of joint-level morphology and alignment variants to guide advancements in ankle joint pathological care and operative treatments.

A Mixed Methods Investigation of the Prevalence and Influencing Factors of Compassion Fatigue among Midwives in Different Areas of China.

Objective Exploring the influencing factors of compassion fatigue among midwives to prevent compassion fatigue from occurring and improve their mental health. Methods A method integrating the quantitative research method and qualitative research method is used. For the quantitative research, a cross-sectional study was carried out. State-run hospitals from three economic areas in China were selected as investigation scope from June 2018 to May 2021. A total of 515 midwives were chosen randomly from three economic areas. SPSS 22.0 was used for data cleaning and statistical description and analysis. The influencing factors of compassion fatigue among midwives were analyzed by fitting these two-level logistic models. For qualitative research, purposive sampling and maximum variation strategy were used to select midwives with mild or above compassion fatigue in the questionnaire survey. Field study and interviews were used to collect data. Results The results in the quantitative research showed that 515 valid questionnaires were received with 82.14% of midwives whose compassion fatigue were moderate or above. Multilevel statistical model analysis demonstrated that hospital level, children situation, area, working atmosphere, experiences of traumatic delivery, sleep quality, and social support level had impacts on the degree of midwives' compassion fatigue (p < 0.05). The result in the qualitative research showed that 34 midwives were interviewed, and 7 topic ideas were refined. Conclusion Overall, the incidence of compassion fatigue among midwives is high. Risk factors influencing the degree of midwives' compassion fatigue include lower social support, disharmonious working atmosphere, toddler situation, huge workload, experiences of traumatic delivery, and poor quality of sleep.

The coming of age for paid digital campaigning: equalization or normalization in the 2019 Belgian federal elections?

PurposePaid digital campaigning tools play an increasingly pivotal role in individual election campaigns worldwide. Extant literature often juxtaposes the equalization theory, which argues that these tools create a level playing field, and the normalization theory, which contends that strong and resource-rich politicians benefit most from digital tools. This article aims to inform this debate by looking at it from a campaign expenditure perspective beyond the Anglo-American bias of most research on the subject.Design/methodology/approachThe authors use an original dataset on campaign expenditures and resources of 1,798 candidates running for 13 Belgian parties in the 2019 federal parliamentary election. Relying on multilevel statistical models, the authors link the candidates' digital campaign expenses to their incumbency status, which is expected to affect digital campaigning.FindingsWhile earlier work on majoritarian cases often showed contradicting results, this study on the Belgian flexible-list proportional representation (PR) case provides strong support for the equalization theory by demonstrating that incumbents are not only less inclined to spend on digital tools than challengers, but also spend a smaller part of their budget on these tools.Originality/valueThis paper contributes to the literature by exploring the equalization versus normalization debate from a campaign expenditure perspective using a made to purpose dataset in a non-Anglo-American context.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-12-2021-0679

Mango enriched with sucrose and isomaltulose (Palatinose®) by osmotic dehydration: Effect of temperature and solute concentration through the application of multilevel statistical models

Osmotic dehydration (OD) is useful for the enrichment of mangos with interesting solutes. Isomaltulose has healthier properties than sucrose and its use is still scarce in OD processes. The OD of mangos with isomaltulose and sucrose was evaluated, and the effect of solute concentrations (25%, 30%, 35%) and temperatures (25, 35, 45°C) was estimated by multilevel statistical analysis in order to find the best conditions for a greater water loss (WL) and solid gain (SG). In sucrose OD, the highest concentration (35%) had the greatest effect than the temperature for WL and SG. For isomaltulose OD, the concentration provided greater WL and SG, but the effect of temperature was slightly more expressive for SG than WL. The maximum working conditions (35% of isomaltulose or sucrose and 45°C) promoted greater WL and SG for both carbohydrates, and with the OD it was possible to enrich mango with isomaltulose by taking advantage of the osmotic gradient, getting an osmodehydrated product with low glycemic and isulinemic indexes. Novelty impact statement Through the osmotic dehydration, it is possible to enrich mango samples with isomaltulose due to its healthy attributes. Instead, a traditional statistical analysis, the multilevel statistical modeling was applied, which was suitable for evidence that the highest solute concentration and temperature conditions promoted the greatest water loss and solid gain, favoring the enrichment process.

A Task-Specific Algorithm to Estimate Occupational (1→3)-β-D-glucan Exposure for Farmers in the Biomarkers of Exposure and Effect in Agriculture Study.

Farmers may be exposed to glucans (a cell component of molds) through a variety of tasks. The magnitude of exposure depends on each farmer's activities and their duration. We developed a task-specific algorithm to estimate glucan exposure that combines measurements of (1→3)-β-D-glucan with questionnaire responses from farmers in the Biomarkers of Exposure and Effect in Agriculture (BEEA) study. To develop the algorithm, we first derived task-based geometric means (GMs) of glucan exposure for farming tasks using inhalable personal air sampling data from a prior air monitoring study in a subset of 32 BEEA farmers. Next, these task-specific GMs were multiplied by subject-reported activity frequencies for three time windows (the past 30 days, past 7 days, and past 1 day) to obtain subject-, task-, and time window-specific glucan scores. These were summed together to obtain a total glucan score for each subject and time window. We examined the within- and between-task correlation in glucan scores for different time frames. Additionally, we assessed the algorithm for the 'past 1 day' time window using full-shift concentrations from the 32 farmers who participated in air monitoring the day prior to an interview using multilevel statistical models to compare the measured glucan concentration with algorithm glucan scores. We focused on the five highest exposed tasks: poultry confinement (300 ng/m3), swine confinement (300 ng/m3), clean grain bins (200 ng/m3), grind feed (100 ng/m3), and stored seed or grain (50 ng/m3); the remaining tasks were &lt;50 ng/m3 and had similar concentrations to each other. Overall, 67% of the participants reported at least one of these tasks. The most prevalent task was stored seed or grain (64%). The highest median glucan scores were observed for poultry confinement and swine confinement; these tasks were reported by 2% and 8% of the participants, respectively. The correlation between scores for the same task but different time windows was high for swine confinement and poultry confinement, but low for clean grain bins. Task-specific scores had low correlation with other tasks. Prior day glucan concentration was associated with the total glucan 'past 1 day' score and with swine confinement and clean grain bin task scores. This study provides insight into the variability and key sources of glucan exposure in a US farming population. It also provides a framework for better glucan exposure assessment in epidemiologic studies and is a crucial starting point for evaluating health risks associated with glucans in future epidemiologic evaluations of this population.

811 Statistical Analyses of Multiple Burn Wounds within an Animal

IntroductionPorcine animal models are frequently used to study the effects of various burn wound treatments and conditions. In these studies, multiple wounds are created on the dorsum of an anesthetized pig. Wounds within an animal are correlated, and the analysis of such a design should account for this dependence. Two recent studies are used as examples to illustrate the use of random effects for animal to account for the dependence of wound measurements within each pig.MethodsIn both studies, treatments were randomized to wound location, and neither contained repeated measurements within a wound.Study #1 investigated the effectiveness of enzymatic debridement. Forty 3-cm diameter partial-thickness burn wounds were created on the dorsum of 5 anesthetized pigs, arranged in 4 rows and 10 columns. Dorsal quadrants with 10 wounds each were created by combinations of two conditions: wounds that were wet or dry and wounds that were treated for either 72 or 96 hours. Debridement Efficiency Scores were calculated for each wound and evaluated for differences by inferential statistical comparisons between experimental treatments and conditions. The multilevel statistical model contained Treatment Group (5 levels), Treatment Time (2 levels: 72 hour and 96 hour), and Wet/Dry Condition (2 levels) as fixed effects, which were crossed to create a 3-way block, resulting in 2 wounds per animal for each Treatment, Wet/Dry, and Time combination. Random effects of animal and treatment block within animal were included in the model.Study #2 investigated the effectiveness of an experimental treatment applied at 3 different post-burn injury time points versus a standard of care (SOC). Up to 12 5-cm2 deep partial thickness wounds were created in 2 rows and 6 columns on each dorsum of 6 anesthetized pigs. Each treated wound was compared with a SOC wound located along the same cranio-caudal axis. Paired differences for wound closure % were calculated and analyzed with time as a fixed effect with a random effect for animal.ResultsFor Study #1, there were 200 total wounds, and for Study #2 there were 72 total wounds. These experimental units are not independent, as required by statistical testing. For both studies, there was graphical evidence that the burn wound measurements differed both within and between pigs. The statistical tests accounted for this variability by incorporating the effects due to pigs.ConclusionsMatching the statistical model to the experimental design is critical for correct interpretation of the results. Failure to use the correct model by assuming wounds within a pig are independent (and thereby ignoring any effect due to the pig) will result in erroneous statistical test results and less powerful tests of treatment differences.

Reassessing pharmacogenomic cell sensitivity with multilevel statistical models.

Pharmacogenomic experiments allow for the systematic testing of drugs, at varying dosage concentrations, to study how genomic markers correlate with cell sensitivity to treatment. The first step in the analysis is to quantify the response of cell lines to variable dosage concentrations of the drugs being tested. The signal to noise in these measurements can be low due to biological and experimental variability. However, the increasing availability of pharmacogenomic studies provides replicated data sets that can be leveraged to gain power. To do this, we formulate a hierarchical mixture model to estimate the drug-specific mixture distributions for estimating cell sensitivity and for assessing drug effect type as either broad or targeted effect. We use this formulation to propose a unified approach that can yield posterior probability of a cell being susceptible to a drug conditional on being a targeted effect or relative effect sizes conditioned on the cell being broad. We demonstrate the usefulness of our approach via case studies. First, we assess pairwise agreements for cell lines/drugs within the intersection of two data sets and confirm the moderate pairwise agreement between many publicly available pharmacogenomic data sets. We then present an analysis that identifies sensitivity to the drug crizotinib for cells harboring EML4-ALK or NPM1-ALK gene fusions, as well as significantly down-regulated cell-matrix pathways associated with crizotinib sensitivity.

Reassessing pharmacogenomic cell sensitivity with multi-level statistical models

Reassessing pharmacogenomic cell sensitivity with multi-level statistical models

Conflict and Climate Factors and the Risk of Child Acute Malnutrition Among Children Aged 24–59 Months: A Comparative Analysis of Kenya, Nigeria, and Uganda

Acute malnutrition affects a sizeable number of young children around the world, with serious repercussions for mortality and morbidity. Among the top priorities in addressing this problem are to anticipate which children tend to be susceptible and where and when crises of high prevalence rates would be likely to arise. In this article, we highlight the potential role of conflict and climate conditions as risk factors for acute malnutrition, while also assessing other vulnerabilities at the individual- and household-levels. Existing research reflects these features selectively, whereas we incorporate all the features into the same study. The empirical analysis relies on integration of health, conflict, and environmental data at multiple scales of observation to focuses on how local conflict and climate factors relate to an individual child’s health. The centerpiece of the analysis is data from the Demographic and Health Surveys conducted in several different cross-sectional waves covering 2003–2016 in Kenya, Nigeria, and Uganda. The results obtained from multi-level statistical models indicate that in Kenya and Nigeria, conflict is associated with lower weight-for-height scores among children, even after accounting for individual-level and climate factors. In Nigeria and Kenya, conflict lagged 1–3 months and occurring within the growing season tends to reduce WHZ scores. In Uganda, however, weight-for-height scores are primarily associated with individual-level and household-level conditions and demonstrate little association with conflict or climate factors. The findings are valuable to guide humanitarian policymakers and practitioners in effective and efficient targeting of attention, interventions, and resources that lessen burdens of acute malnutrition in countries prone to conflict and climate shocks.

The polycrystals grain structure formation for modified two-level crystal plasticity statistical models

In widespread multilevel statistical crystal plasticity models for describing the deformable polycrystalline materials behavior the spatial arrangement of structural elements (grains, subgrains) isn’t usually considered. At the same time for analyzing some physical mechanisms that have a significant effect on the polycrystals properties (for example, grain-boundary hardening, grain-boundary sliding, recrystallization, etc.), taking into account the mutual location of crystallites is critically important. In this regard, the authors have previously developed the statistical two-level elastic-viscoplastic model modification, which makes it possible to take into account this mutual arrangement. To implement this statistical model, information on a grain (subgrain) structure of investigated materials is required. The paper considers the procedure for describing the grain structure formation, based on using the polyhedra formed by the Laguerre method in a three-dimensional Euclidean space, with subsequent processing and transmission of the necessary data for setting a grain structure into the modified statistical model.