RESUMO
Inhibitory control, the ability to suppress irrelevant thoughts or actions, is central to cognitive and social development. Protracted maturation of frontal brain networks has been reported as a major restraint for this ability, yet, young children, when motivated, successfully inhibit delayed responses. A better understanding of the age-dependent neural inhibitory mechanism operating during the awaiting-to-respond window in children may elucidate this conundrum. We recorded ERPs from children and parental adults to a visual-spatial working memory task with delayed responses. Cortical activation elicited during the first 1000 ms of the awaiting-to-respond window showed, as predicted by prior studies, early inhibitory effects in prefrontal ERPs (P200, 160-260 ms) associated with top-down attentional-biasing, and later effects in parietal/occipital ERPs (P300, 270-650 ms) associated with selective inhibition of task-irrelevant stimuli/responses and recurrent memory retrieval. Children successfully inhibited delayed responses and performed with a high level of accuracy (often over 90%), although, the prefrontal P200 displayed reduced amplitude and uniformly delayed peak latency, suggesting low efficacy of top-down attentional-biasing. P300, however, with no significant age-contrasts in latency was markedly elevated in children over the occipital/inferior parietal regions, with effects stronger in younger children. These results provide developmental evidence supporting the sensorimotor recruitment model of visual-spatial working memory relying on the occipital/parietal regions of the early maturing dorsal-visual network. The evidence is in line with the concept of age-dependent variability in the recruitment of cognitive inhibitory networks, complementing the former predominant focus on frontal lobes.
Assuntos
Encéfalo , Imageamento por Ressonância Magnética , Adulto , Mapeamento Encefálico , Criança , Pré-Escolar , Humanos , Inibição Psicológica , Lobo ParietalRESUMO
Latent class mediation modeling is designed to estimate the mediation effect when both the mediator and the outcome are latent class variables. We suggest using an adjusted one-step approach in which the latent class models for the mediator and the outcome are estimated first to decide on the number of classes, then the latent class models and the mediation model are jointly estimated. We present both an empirical demonstration and a simulation study to compare the performance of this one-step approach to a standard three-step approach with modal assignment (modal) and four different modern three-step approaches. Results from the study indicate that unadjusted modal, which ignores the classification errors of the latent class models, produced biased mediation effects. On the other hand, the adjusted one-step approach and the modern three-step approaches performed well with respect to bias for estimating mediation effects, regardless of measurement quality (i.e., model entropy) and latent class size. Among the three-step approaches we investigated, the maximum likelihood method with modal assignment and the BCH correction with robust standard error estimators are good alternatives to the adjusted one-step approach, given their unbiased standard error estimations.
Assuntos
Modelos Estatísticos , Viés , Simulação por Computador , Análise de Classes LatentesRESUMO
Infants who experience sensitive caregiving are at lower risk for numerous adverse outcomes. This is especially true for infants born preterm, leading them to be more susceptible to risks associated with poorer quality caregiving. Some research suggests that preterm and full-term infants differ on temperament, which may contribute to these findings. This study aimed to investigate associations between infant temperament (negative emotionality, positive affectivity/surgency, and orienting/regulatory capacity) and maternal sensitivity among infants born preterm (M = 30.2 weeks) and full term. It was hypothesized that mothers of infants born preterm and mothers of infants with more difficult temperaments would display lower sensitivity, indicated by lower responsiveness to nondistress, lower positive regard, and higher intrusiveness. Videotaped play interactions and a measure of temperament (Infant Behavior Questionnaire) were coded for 18 preterm and 44 full-term infants at 9 months (corrected) age. Results suggest that mothers of preterm and full-term infants differed significantly in responding to their infants, but these results cannot be explained by infant temperament. Preterm status and sociodemographic risk emerged as correlates of maternal behavior, such that mothers of infants born preterm and mothers with greater sociodemographic risk displayed lower levels of maternal sensitivity.
Los infantes que experimentan un cuidado sensible se encuentran bajo un riesgo más bajo en cuanto a numerosos resultados adversos. Esto es especialmente cierto para infantes nacidos prematuramente, lo cual conlleva que ellos sean más susceptibles a los riesgos asociados con una más pobre calidad de cuidado. Alguna investigación sugiere que los infantes prematuros y aquellos de completa gestación difieren en el temperamento, lo cual pudiera contribuir a estos resultados. Este estudio se propuso investigar las asociaciones entre el temperamento del infante (sentido negativo de la emoción, afectividad/resurgencia positiva y capacidad de orientación/regulatoria) y la sensibilidad materna entre infantes nacidos prematuramente (M = 30.2 semanas) y los nacidos dentro de la gestación completa. La hipótesis fue que las madres de infantes nacidos prematuramente y las madres de infantes con temperamentos más difíciles mostrarían una más baja sensibilidad, indicado por una más baja reacción sensible a la falta de angustia, más baja consideración positiva y más alta intrusión. Se codificaron las interacciones de juego grabadas en video y una medida de temperamento (Cuestionario de Conducta del Infante) para 18 prematuros y 44 infantes de gestación completa a los nueves meses (corregidos) de edad. Los resultados sugieren que las madres de infantes prematuros y de gestación completa difirieron significativamente al responder a sus infantes, pero estos resultados no pueden ser explicados con base en el temperamento del infante. La condición de prematuro y el riesgo sociodemográfico surgieron como una correlación del comportamiento materno, al punto que las madres de infantes nacidos prematuramente y las madres con mayores riesgos sociodemográficos mostraron niveles más bajos de sensibilidad materna.
Les nourrissons qui font l'expérience de soins sensibles sont à moindre risque pour bien des résultats adverses. Cela est particulièrement vrai des nourrissons nés prématurés, ce qui les amène à être plus susceptibles aux risques liés à une plus mauvaise qualité de soins de la personne qui prend soin d'eux. Certaines recherches suggèrent que les nourrissons prématurés et les nourrissons à terme diffèrent quant au tempérament, ce qui peut contribuer à ces résultats. Cette étude s'est donné pour but de rechercher les liens entre le tempérament du nourrisson (émotionalité négative, affectivité/dynamisme positif, et capacité d'orientation/régulatoire) et la sensibilité maternelle chez les nourrissons nés prématurés (M = 30,2 semaines) et ceux à plein terme. Nous avons pris pour hypothèse que les mères des nourrissons nés prématurés et les mères de nourrissons ayant des tempéraments plus difficiles feraient preuve d'une sensibilité plus basse, indiquée par une réaction moindre à la non-détresse, un égard positif plus bas et une intrusion plus élevée. Des interactions de jeu filmées et une mesure de tempérament (Questionnaire du Comportement du Nourrisson) ont été codées pour 18 prématurés et 44 nourrissons à termes à neuf mois (âge corrigé). Les résultats suggèrent que les mères de prématurés et de nourrissons à terme ont différé de manière importante dans leur réaction à leurs nourrissons, mais ces résultats ne peuvent pas être expliqués par le tempérament du nourrisson. Le statut de prématuré et le risque sociodémographique ont émergé comme corrélat du comportement maternel, de telle manière que les nourrissons nés prématurés et les mères avec un risque sociodémographique plus élevé ont fait état de niveaux plus bas de sensibilité maternelle.
Assuntos
Comportamento do Lactente , Temperamento , Feminino , Humanos , Lactente , Recém-Nascido , Comportamento Materno , Mães , Inquéritos e QuestionáriosRESUMO
Complex mediation models, such as a two-mediator sequential model, have become more prevalent in the literature. To test an indirect effect in a two-mediator model, we conducted a large-scale Monte Carlo simulation study of the Type I error, statistical power, and confidence interval coverage rates of 10 frequentist and Bayesian confidence/credible intervals (CIs) for normally and nonnormally distributed data. The simulation included never-studied methods and conditions (e.g., Bayesian CI with flat and weakly informative prior methods, two model-based bootstrap methods, and two nonnormality conditions) as well as understudied methods (e.g., profile-likelihood, Monte Carlo with maximum likelihood standard error [MC-ML] and robust standard error [MC-Robust]). The popular BC bootstrap showed inflated Type I error rates and CI under-coverage. We recommend different methods depending on the purpose of the analysis. For testing the null hypothesis of no mediation, we recommend MC-ML, profile-likelihood, and two Bayesian methods. To report a CI, if data has a multivariate normal distribution, we recommend MC-ML, profile-likelihood, and the two Bayesian methods; otherwise, for multivariate nonnormal data we recommend the percentile bootstrap. We argue that the best method for testing hypotheses is not necessarily the best method for CI construction, which is consistent with the findings we present.
Assuntos
Pesquisa Comportamental/métodos , Intervalos de Confiança , Modelos Estatísticos , Análise Multivariada , Teorema de Bayes , Simulação por Computador , Humanos , Método de Monte CarloRESUMO
To draw valid inference about an indirect effect in a mediation model, there must be no omitted confounders. No omitted confounders means that there are no common causes of hypothesized causal relationships. When the no-omitted-confounder assumption is violated, inference about indirect effects can be severely biased and the results potentially misleading. Despite the increasing attention to address confounder bias in single-level mediation, this topic has received little attention in the growing area of multilevel mediation analysis. A formidable challenge is that the no-omitted-confounder assumption is untestable. To address this challenge, we first analytically examined the biasing effects of potential violations of this critical assumption in a two-level mediation model with random intercepts and slopes, in which all the variables are measured at Level 1. Our analytic results show that omitting a Level 1 confounder can yield misleading results about key quantities of interest, such as Level 1 and Level 2 indirect effects. Second, we proposed a sensitivity analysis technique to assess the extent to which potential violation of the no-omitted-confounder assumption might invalidate or alter the conclusions about the indirect effects observed. We illustrated the methods using an empirical study and provided computer code so that researchers can implement the methods discussed.
Assuntos
Fatores de Confusão Epidemiológicos , Modelos Estatísticos , Análise Multinível/métodos , Algoritmos , Pesquisa Comportamental/métodos , Análise por ConglomeradosRESUMO
OBJECTIVE: American Indian and Alaska Native (AI/AN) populations experience greater health disparities in alcohol use outcomes compared with the general population. This secondary data analysis examines cultural factors related to alcohol use in reservation-based American Indian (AI) adults (N = 65; 41 males; mean age = 36.7 years) in a randomized controlled trial of a culturally tailored contingency management (CM) program. It was hypothesized that individuals with higher rates of cultural protective factors would have lower rates of alcohol use, whereas individuals with higher rates of risk factors would have higher rates of alcohol use. It was also hypothesized that enculturation would moderate the relationship between treatment group and alcohol use. METHOD: Generalized linear mixed modeling was used to calculate odds ratios (ORs) for the repeated measure, biweekly urine tests of the biomarker, ethyl glucuronide (EtG), across 12 weeks. The relationships between alcohol use (abstinence [EtG < 150 ng/ml]) or heavy drinking [EtG > 500 ng/ml]) and culturally relevant protective (enculturation, years lived on the reservation) and risk factors (discrimination, historical loss, historical loss symptoms) were examined. RESULTS: There was a negative association between enculturation and probability of submitting a heavy drinking urine sample (OR = 0.973; 95% CI [0.950, 0.996], p = .023), indicating that enculturation may serve as a protective factor against heavy drinking. CONCLUSIONS: Cultural factors (e.g., enculturation) may be important constructs to assess and incorporate into treatment planning with AI adults engaged in alcohol treatment.
Assuntos
Indígena Americano ou Nativo do Alasca , Indígenas Norte-Americanos , Adulto , Humanos , Masculino , Consumo de Bebidas Alcoólicas/epidemiologia , Terapia Comportamental/métodos , Fatores de Risco , FemininoRESUMO
Aims: Achieving an effective biocompatible system for siRNAs delivery to the tumor site remains a significant challenge. Materials & methods: Selenium nanoparticles (SeNPs) modified by chitosan (CS) and hyaluronic acid (HA) were fabricated for PLK1 siRNAs (siPLK1) delivery to the bladder cancer cells. The HA-CS-SeNP@siPLK1 efficacy was evaluated using in vitro and in vivo models. Results: HA-CS-SeNP@siPLK1 was selectively internalized into T24 cells through clathrin-mediated endocytosis. Treatment with HA-CS-SeNP@siPLK1 successfully silenced the PLK1 gene, inhibited cell proliferation and induced cell cycle arrest in vitro. HA-CS-SeNP@siPLK1 could also inhibit tumor growth in vivo without causing systemic toxicity. Conclusion: Our results suggest that HA-CS-SeNPs may provide a good vehicle for delivering siPLK1 to the bladder tumor site.
siRNAs are small biomolecules shown as novel insights in cancer gene therapy because of their capability to silence target genes. However, achieving an effective biocompatible system for siRNA delivery to the tumor site remains a significant challenge. This work aimed to develop a nanoparticle-based delivery system consisting of selenium nanoparticles modified by chitosan and hyaluronic acid to sustain the release of siRNAs to bladder cancer cells. The results of this study demonstrated that this nanosystem successfully silenced the PLK1 gene and reduced the proliferation in vitro and in vivo. These findings suggest that hyaluronic acid-chitosan-selenium nanoparticles may open a new insight for targeted gene therapy for bladder cancer.
Assuntos
Quitosana , Nanopartículas , Selênio , Neoplasias da Bexiga Urinária , Humanos , RNA Interferente Pequeno/genética , Ácido Hialurônico , Linhagem Celular Tumoral , Neoplasias da Bexiga Urinária/genética , Neoplasias da Bexiga Urinária/terapia , Receptores de Hialuronatos/genética , Receptores de Hialuronatos/metabolismoRESUMO
Doxorubicin (DOX) is a common chemotherapy agent that is used in clinics for the treatment of a wide spectrum of cancers. Herein, a novel approach for improving doxorubicin loading on nanoparticles and also controlled release is suggested using crosslinking doxorubicin molecules with glutaraldehyde. We investigated the loading efficiency of doxorubicin on CoFe2O4 nanoparticles in the absence and presence of glutaraldehyde. Based on the feasible, one-pot, and time-saving approach suggested here, the crosslinked DOX showed loading efficiency about twice more in comparison with the non-crosslinked DOX. In vitro doxorubicin release of three formulations including DOX crosslinked with glutaraldehyde (DOXGA), DOX loaded on CoFe2O4 (CFDOX) and DOX loaded on CoFe2O4 using glutaraldehyde (CFDOXGA) yielded a sustained release. The kinetic models such as first-order, Sahlin-Peppas, and Higuchi were employed for further exploration of DOX release profile. Our suggested method might extend to other nanomaterial-based drug delivery formulations to promote drug delivery efficiency.
Assuntos
Doxorrubicina , Nanopartículas , Glutaral , Doxorrubicina/farmacologia , Sistemas de Liberação de Medicamentos , Portadores de Fármacos , Liberação Controlada de FármacosRESUMO
Co-delivery of siRNA or miRNA with chemotherapeutic drugs into tumor sites is an attractive synergetic strategy for treating colorectal cancer (CRC) due to their complementary mechanisms. In the current work, a liposome nanoparticle (Huang et al., Cancer Metastasis Rev., 2018, 37, 173-187) coated by cationic chitosan (CS) using a controlled layer-by-layer (LbL) process was designed to deliver simultaneous si-KRAS, miRNA-532-3p, and 5-Fluorouracil (5-FU) into CRC cells. The LbL NPs exhibited a spherical structure with an average size of 165.9 nm and effectively protected si-KRAS and miRNA-532-3p against degradation by serum and nucleases. Interestingly, the LbL NPs were successfully entered into cells and efficiently promoted cytotoxicity and suppressed cancer cell migration and invasion. In vivo, the LbL NPs reduced tumor growth in SW480-tumor-bearing mice models. In conclusion, these results suggested that the LbL NPs co-loaded with 5-FU and miR-532-3p/si-KRAS might provide a promising potential strategy for inhibiting the malignant phenotypes of CRC cells.
RESUMO
Bladder cancer is one of the concerning urological malignant diseases in the world, which has a clinical need for effective targeted therapy. The development of nanotechnology-based gene delivery to bladder tumor sites is an effective strategy for targeted cancer therapy with low/no toxicity. With this view, in the present work, the mesoporous silica nanoparticles (MSNs) modified with c(RGDfK)-PLGA-PEG [c(RGDfK)-MSN NPs] were constructed for co-delivery of miR-34a and siPD-L1 within bladder cancer cells and tissues. Our findings showed that miR-34a is downregulated while PD-L1 is up-regulated in cell lines and animal studies. This nano-carrier is biocompatible in the serum environment and effectively protects miR-34a and siPD-L1 against serum degradation. However, we showed that c(RGDfK)-MSN NPs could simultaneously downregulate PD-L1 expression and up-regulate miR-34a in the T24 cells and T24 mice model and enhance anti-tumor effects both in vivo and in vitro. In conclusion, these findings presented new suggestions for improving targeted therapeutic strategies with specified molecular objectives for bladder cancer treatment.
RESUMO
Stress regulation begins to develop in the first year of life through interactions with caregivers, particularly in the presence of stressors. High quality caregiving, characterized by maternal sensitivity and responsiveness to the infant's emotional cues, is particularly important in the development of infant stress regulation. The purpose of this study was to assess the longitudinal stability of, and associations between, maternal interactive behavior and infant stress regulation (indexed by positive infant affect and cortisol reactivity) in response to the Still Face paradigm (SF) in a cohort of infants born preterm (< 32 weeks gestation, N = 22) at four months and nine months (adjusted age). The percent of time mothers spent using specific interaction styles (contingent maternal interaction (CMI), attention seeking, and watching) during Play/baseline, Reunion#1, and Reunion#2 SF episodes was calculated To assess infant stress regulation, two indices were obtained at both 4 and 9 months during the SF paradigm: the percent of positive affect displayed over each SF episode (0-100%) and a neuroendocrine stress response score based on salivary cortisol reactivity. We found three non-significant but medium-large effect size differences between 4 and 9 month variables, with more positive findings at 9 months. Regarding stability within the 4 month and 9 month episodes, maternal behavior and positive infant affect were non-significantly but moderately stable, with maternal watching behavior being particularly stable. Positive infant affect stability between Reunion#1 and Reunion#2 at 4 months was significantly greater than positive infant affect stability across these two episodes at 9 months. Regarding stability across 4 and 9 month (same) episodes, CMI and positive infant affect showed modest but non-significant stability across (same) 4 and 9 month episodes. Finally, with positive infant affect at Reunion#2 as the "outcome" of the Still Face, CMI at both 4 month Play and Reunion#1 episodes were significantly correlated with this "outcome." Further, positive infant affect at Reunion#2 was more strongly correlated with CMI at both Play and Reunion#1 for 4 month old compared with 9 month old infants. Thus, sensitive care appears particularly important for younger infants born preterm, and mothers' behavior early in a repeated stress exposure paradigm may be particularly important in maintaining positive infant affect and in the development of infants' stress regulation more generally. Identifying the longer-term effects of early stress on infant stress regulation, and its relationship with maternal interaction, has important implications for understanding trajectories of regulatory patterns and deficits. A greater understanding of these relationships is particularly important given that greater emotion and neuroendocrine stress regulation in infancy have been directly associated with numerous positive outcomes throughout childhood.
Assuntos
Comportamento do Lactente , Relações Mãe-Filho , Criança , Feminino , Humanos , Hidrocortisona , Lactente , Comportamento do Lactente/psicologia , Recém-Nascido , Comportamento Materno/psicologia , Relações Mãe-Filho/psicologia , Mães/psicologiaRESUMO
Nowadays, radiotherapy is one of the most effective treatments for breast cancer. In order to overcome the radioresistance of cancer cells, radio-sensitizing agents can be used combined with irradiation to increase the therapeutic efficiency. Curcumin can enhance the radiosensitivity of cancer cells and decrease their viability by the accumulation of these cells in the G2 phase. The encapsulation of curcumin in a nanoniosomal delivery system increases aqueous solubility and bioavailability, resulting in increased radio sensitivity. The present study aimed to enhance the radio-sensitizing effect of the curcumin-containing nanoniosome (Cur-Nio) when combined with irradiation. Thus, curcumin (0.5 mg ml-1) was loaded on a PEGylated nanoniosome containing Tween 60, cholesterol, DOTAP, and 1,2-distearoyl-sn-glycero-3-phosphoethanolamine-poly(ethylene glycol) (DSPE-PEG) (at ratios of 70:30:10:5, respectively) by the thin-film hydration method. The particle size, zeta potential, entrapment efficiency, and drug-release rate of formulated nanoniosomes were determined. In order to assess cytotoxicity and apoptosis, different doses of irradiation along with various concentrations of free curcumin and Cur-Nio (single or in combination with irradiation) were treated with breast cancer cells. The particle size and zeta potential of Cur-Nio were reported to be 117.5 nm and -15.1 mV, respectively. The entrapment efficiency (EE%) and loading capacities were 72.3% and 6.68%, respectively. The drug-release rate during 6 h was 65.9%. Cell survival in the presence of curcumin at doses of 1 and 3 Gy showed a significant reduction compared with cells irradiated at 48 h and 72 h (p < 0.000). Also, the rate of cytotoxicity and apoptosis was significantly higher in cells treated with the combination of curcumin-containing nanoniosomes and irradiation in comparison with those treated with free curcumin. These findings indicate that the efficacy of pre-treatment with Cur-Nio as a radiosensitizer during radiotherapy enhances irradiation-induced breast cancer cell apoptosis and is a useful strategy to increase the effectiveness of breast cancer therapy.
RESUMO
Mechanisms of behavior change are the processes through which interventions are hypothesized to cause changes in outcomes. Latent growth curve mediation models (LGCMM) are recommended for investigating the mechanisms of behavior change because LGCMM models establish temporal precedence of change from the mediator to the outcome variable. The Correlated Augmented Mediation Sensitivity Analyses (CAMSA) App implements sensitivity analysis for LGCMM models to evaluate if a mediating path (mechanism) is robust to potential confounding variables. The CAMSA approach is described and applied to simulated data, and data from a research study exploring a mechanism of change in the treatment of substance use disorder.
RESUMO
Approximately 25% of patients with staphylococcus aureus bacteremia (SAB) develop infective endocarditis (IE), which has a consequent mortality of 25-46%. Current guidelines recommend routine transthoracic echocardiography (TTE) for patients with SAB; transesophageal echocardiogram (TEE) is reserved for those in whom initial TTE is negative and clinical suspicion for IE remains high. We sought to elucidate high risk features of SAB associated with the development of IE that warrant a TEE after a negative TTE. This retrospective study included 213 patients who were diagnosed with SAB at the University of New Mexico Hospital between 2010-2020. A pre-determined list of clinical risk factors along with TTE and TEE status was extracted from the electronic medical record. The primary outcome was development of IE in patients with SAB. Multivariate logistic regression analysis was used to identify clinical risk factors for IE. Moreover, sensitivity and specificity of TTE and TEE was calculated. Out of 213 patients with SAB, 68 patients met diagnostic criteria for IE. Most patients (n = 209) underwent TTE and 171 patients underwent subsequent TEE. The overall sensitivity of TTE was 63% and overall sensitivity of TEE was 88%. Multivariate analysis showed significantly increased risk of IE in patients who had implanted permanent pacemaker (aOR 32.3, CI 5.23 - 281, p < 0.001) and persistent fever (aOR 6.97, CI 2.42 - 21.0 P < 0.001). Based on our analysis, we recommend that TEE should be strongly considered after negative TTE in SAB patients with intracardiac prosthetics or persistent fever despite appropriate antibiotic therapy.
Assuntos
Bacteriemia , Endocardite , Infecções Estafilocócicas , Antibacterianos , Bacteriemia/complicações , Bacteriemia/diagnóstico , Bacteriemia/epidemiologia , Ecocardiografia Transesofagiana , Endocardite/diagnóstico , Endocardite/diagnóstico por imagem , Humanos , Estudos Retrospectivos , Fatores de Risco , Infecções Estafilocócicas/complicações , Infecções Estafilocócicas/diagnóstico , Staphylococcus aureusRESUMO
This article describes the RMediation package,which offers various methods for building confidence intervals (CIs) for mediated effects. The mediated effect is the product of two regression coefficients. The distribution-of-the-product method has the best statistical performance of existing methods for building CIs for the mediated effect. RMediation produces CIs using methods based on the distribution of product, Monte Carlo simulations, and an asymptotic normal distribution. Furthermore, RMediation generates percentiles, quantiles, and the plot of the distribution and CI for the mediated effect. An existing program, called PRODCLIN, published in Behavior Research Methods, has been widely cited and used by researchers to build accurate CIs. PRODCLIN has several limitations: The program is somewhat cumbersome to access and yields no result for several cases. RMediation described herein is based on the widely available R software, includes several capabilities not available in PRODCLIN, and provides accurate results that PRODCLIN could not.
Assuntos
Intervalos de Confiança , Probabilidade , Software , Modelos Estatísticos , Projetos de PesquisaRESUMO
Mediation analysis relies on an untestable assumption of the no omitted confounders, which posits that an omitted variable that confounds the relationships between the antecedent, mediator, and outcome variables cannot exist. One common model in alcohol addiction studies is a nonrandomized latent growth curve mediation model (LGCMM), where the antecedent variable is not randomized, the two covarying mediators are latent intercept and slope modeling longitudinal effect of the repeated measures mediator, and an outcome variable that measures alcohol use. An important gap in the literature is lack of sensitivity analysis techniques to assess the effect of the violation of the no omitted confounder assumption in a nonrandomized LGCMM. We extend a sensitivity analysis technique, termed correlated augmented mediation sensitivity analysis (CAMSA), to a nonrandomized LGCMM. We address several unresolved issues in conducting CAMSA for the nonrandomized LGCMM and present: (a) analytical results showing how confounder correlations model a confounding bias, (b) algorithms to address admissible values for confounder correlations, (c) accessible R code within an SEM framework to conduct our proposed sensitivity analysis, and (d) an empirical example. We conclude that conducting sensitivity analysis to ascertain robustness of the mediation analysis is critical.
RESUMO
Mediation analysis is an important approach for investigating causal pathways. One approach used in mediation analysis is the test of an indirect effect, which seeks to measure how the effect of an independent variable impacts an outcome variable through 1 or more mediators. However, in many situations the proposed tests of indirect effects, including popular confidence interval-based methods, tend to produce poor Type I error rates when mediation does not occur and, more generally, only allow dichotomous decisions of "not significant" or "significant" with regards to the statistical conclusion. To remedy these issues, we propose a new method, a likelihood ratio test (LRT), that uses nonlinear constraints in what we term the model-based constrained optimization (MBCO) procedure. The MBCO procedure (a) offers a more robust Type I error rate than existing methods; (b) provides a p value, which serves as a continuous measure of compatibility of data with the hypothesized null model (not just a dichotomous reject or fail-to-reject decision rule); (c) allows simple and complex hypotheses about mediation (i.e., 1 or more mediators; different mediational pathways); and (d) allows the mediation model to use observed or latent variables. The MBCO procedure is based on a structural equation modeling framework (even if latent variables are not specified) with specialized fitting routines, namely with the use of nonlinear constraints. We advocate using the MBCO procedure to test hypotheses about an indirect effect in addition to reporting a confidence interval to capture uncertainty about the indirect effect because this combination transcends existing methods. (PsycInfo Database Record (c) 2020 APA, all rights reserved).
Assuntos
Interpretação Estatística de Dados , Modelos Estatísticos , Psicologia/métodos , HumanosRESUMO
This study presents formulae for the covariances between parameter estimates in a single mediator model. These covariances are necessary to build confidence intervals (CI) for effect size measures in mediation studies. We first analytically derived the covariances between the parameter estimates in a single mediator model. Using the derived covariances, we computed the multivariate-delta standard errors, and built the 95% CIs for the effect size measures. A simulation study evaluated the accuracy of the standard errors as well as the Type I error, power, and coverage of the CIs using various parameter values and sample sizes. Finally, we presented a numerical example and a SAS MACRO that calculates the CIs for the effect size measures.
Assuntos
Análise de Variância , Intervalos de Confiança , Modelos Estatísticos , Psicologia Social/estatística & dados numéricos , Análise de Regressão , Viés , Humanos , Análise MultivariadaRESUMO
In mediation analysis, conditions necessary for commonly recommended tests, including the confidence interval (CI)-based tests, to produce an accurate Type I error, do not generally hold for finite sample sizes and non-normally distributed model residuals. This is typically the case because of the complexity of testing a null hypothesis about indirect effects. To remedy these issues, we propose two extensions of the recently developed asymptotic Model-based Constrained Optimization (MBCO) likelihood ratio test (LRT), a promising new model comparison method for testing a general function of indirect effects. The proposed tests, semi-parametric and parametric bootstrap MBCO LRT are shown to yield a more accurate Type I error rate in smaller sample sizes and under various degrees of non-normality of the model residuals compared to the asymptotic MBCO LRT and the CI-based methods. We provide R script in the Supplemental Materials to perform all three MBCO LRTs.
RESUMO
Latent growth curve mediation models are increasingly used to assess mechanisms of behavior change. For latent growth mediation model, like any another mediation model, even with random treatment assignment, a critical but untestable assumption for valid and unbiased estimates of the indirect effects is that there should be no omitted variable that confounds indirect effects. One way to address this untestable assumption is to conduct sensitivity analysis to assess whether the inference about an indirect effect would change under varying degrees of confounding bias. We developed a sensitivity analysis technique for a latent growth curve mediation model. We compute the biasing effect of confounding on point and confidence interval estimates of the indirect effects in a structural equation modeling framework. We illustrate sensitivity plots to visualize the effects of confounding on each indirect effect and present an empirical example to illustrate the application of the sensitivity analysis.