Multiple Outcome Variables Research Articles

The Politics of Punishment: Why Dictators Join the International Criminal Court

Abstract Scholars commonly argue that international law and organizations promote democracy by helping dictators to credibly commit to accountability, individual rights, and transparency. Yet dictators routinely join treaties and international organizations without transitioning to democracy. International law and organizations can generate asymmetric costs for domestic actors because international rules often apply to both governments and non-state actors, yet dictators can limit how these rules are upheld at the domestic and international level. We argue that dictators are most likely to join such treaties and international organizations when they face strong domestic political competition. We illustrate our argument using the International Criminal Court (ICC), which has extensive powers to prosecute individuals for international crimes, including crimes against humanity, genocide, and war crimes. We show that ICC investigations and prosecutions have become a tool for incumbent dictators to target their domestic opponents. We examine the implications of our theory for multiple outcome variables, including the decision to join the ICC, violence, and the survival of dictators in power. Our evidence suggests that dictators are most likely to join the ICC when they face strong political opponents and are subsequently less likely to commit violence and more likely to survive in office.

Using decision analysis for intervention value efficiency to select optimized interventions in the multiphase optimization strategy.

Optimizing multicomponent behavioral and biobehavioral interventions presents a complex decision problem. To arrive at an intervention that is both effective and readily implementable, it may be necessary to weigh effectiveness against implementability when deciding which components to select for inclusion. Different components may have differential effectiveness on an array of outcome variables. Moreover, different decision-makers will approach this problem with different objectives and preferences. Recent advances in decision-making methodology in the multiphase optimization strategy (MOST) have opened new possibilities for intervention scientists to optimize interventions based on a wide variety of decision-maker preferences, including those that involve multiple outcome variables. In this study, we introduce decision analysis for intervention value efficiency (DAIVE), a decision-making framework for use in MOST that incorporates these new decision-making methods. We apply DAIVE to select optimized interventions based on empirical data from a factorial optimization trial. We define various sets of hypothetical decision-maker preferences, and we apply DAIVE to identify optimized interventions appropriate to each case. We demonstrate how DAIVE can be used to make decisions about the composition of optimized interventions and how the choice of optimized intervention can differ according to decision-maker preferences and objectives. We offer recommendations for intervention scientists who want to apply DAIVE to select optimized interventions based on data from their own factorial optimization trials. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Assessing Acute and Chronic Risks of Human Exposure to Arsenic: A Cross-Sectional Study in Ethiopia Employing Body Biomarkers.

Arsenic, a widely recognized and highly toxic carcinogen, is regarded as one of the most hazardous metalloids globally. However, the precise assessment of acute and chronic human exposure to arsenic and its contributing factors remains unclear in Ethiopia. The primary goal of this study was to assess the levels of acute and chronic arsenic exposure, as well as the contributing factors, using urine and nail biomarkers. A community-based analytical cross-sectional study design was employed for this study. Agilent 7900 series inductively coupled plasma mass spectrometry was used to measure the concentrations of arsenic in urine and nail samples. We performed a multiple linear regression analysis to assess the relationships between multiple predictors and outcome variables. The concentration of arsenic in the urine samples ranged from undetectable (<0.01) to 126.13, with a mean and median concentration of 16.02 and 13.5 μg/L, respectively. However, the mean and median concentration of arsenic in the nails was 1.01, ranging from undetectable (<0.01 μg/g) to 2.54 μg/g. Furthermore, Pearson's correlation coefficient analysis showed a significant positive correlation between arsenic concentrations in urine and nail samples (r = 0.432, P < .001). Also, a positive correlation was observed between urinary (r = 0.21, P = .007) and nail (r = 0.14, P = .044) arsenic concentrations and the arsenic concentration in groundwater. Groundwater sources and smoking cigarettes were significantly associated with acute arsenic exposure. In contrast, groundwater sources, cigarette smoking, and the frequency of showers were significantly associated with chronic arsenic exposure. The study's findings unveiled the widespread occurrence of both acute and chronic arsenic exposure in the study area. Consequently, it is crucial to prioritize the residents in the study area and take further measures to prevent both acute and chronic arsenic exposure.

Perinatal Mortality Despite Prenatal Diagnosis of Vasa Previa: A Systematic Review.

To determine the causes and potential preventability of perinatal deaths in prenatally identified cases of vasa previa. Reports of prenatally identified cases of vasa previa published in the English language literature since 2000 were identified in Medline and ClinicalTrials.gov with the search terms "vasa previa," "abnormal cord insertion," "velamentous cord," "marginal cord," "bilobed placenta," and "succenturiate lobe." All cases from the above search with an antenatally diagnosed vasa previa present at delivery in singleton or twin gestations with perinatal mortality information were included. Cases meeting inclusion criteria were manually abstracted, and multiple antenatal, intrapartum, and outcome variables were recorded. Deaths and cases requiring neonatal transfusion were analyzed in relation to plurality, routine hospitalization, and cervical length monitoring. A total of 1,109 prenatally diagnosed cases (1,000 singletons, 109 twins) were identified with a perinatal mortality rate attributable to vasa previa of 1.1% (95% CI 0.6-1.9%). All perinatal deaths occurred with unscheduled deliveries. The perinatal mortality rate in twin pregnancies was markedly higher than that in singleton pregnancies (9.2% vs 0.2%, P<.001), accounting for 80% of overall mortality despite encompassing only 9.8% of births. Compared with individuals with singleton pregnancies, those with twin pregnancies are more likely to undergo unscheduled delivery (56.4% vs 35.1%, P=.01) despite delivering 2 weeks earlier (33.2 weeks vs 35.1 weeks, P=.006). An institutional policy of routine hospitalization is associated with a reduced need for neonatal transfusion (0.9% vs 6.0%, P<.001) and a reduction in the perinatal mortality rate in twin pregnancies (0% vs 25%, P=.002) but not in singleton pregnancies (0% vs 0.5%, P=.31). Routine hospitalization and earlier delivery of twins may result in a reduction in the perinatal mortality rate. A smaller benefit from routine admission of individuals with singleton pregnancies cannot be excluded. There is currently insufficient evidence to recommend the routine use of cervical length measurements to guide clinical management.

Bony Facial Trauma Score Predicts Clinical Outcomes in Facial Trauma.

Background: The bony facial trauma score (BFTS) is a rubric used to assess the severity of facial trauma. Objectives: To compare the BFTS with relevant clinical outcomes while controlling for medical comorbidities and polytrauma. Methods: A retrospective review of facial trauma patients evaluated between 2017 and 2022 was conducted. While controlling for medical comorbidities and polytrauma, multivariate regression models were used to assess the relationship between BFTS and outcome variables such as length of stay (LOS) and malocclusion. Results: In total, 176 patients were included in the analysis. The average age was 36.5 years (standard deviation [SD] of 16.8), and 68.8% were male. The most common mechanism of injury was blunt force (92.6%) and the mean BFTS was 10.73 (SD of 11.05). BFTS was found to correlate with the following (p < 0.05): total LOS and ICU LOS, malocclusion, likelihood of requiring multiple surgeries, and diplopia. Conclusion: The BFTS is significantly correlated with multiple outcome variables while controlling for medical comorbidities and polytrauma.

Impact of C3 laminectomy on cervical sagittal alignment in cervical laminoplasty: a prospective, randomized controlled trial comparing clinical and radiological outcomes between C3 laminectomy with C4–C6 laminoplasty and C3–C6 laminoplasty

Background ContextC3 laminectomy in cervical laminoplasty is a modified laminoplasty technique that can preserve the semispinalis cervicis muscle attached to the C2 spinous process. Several previous studies have shown that this technique can lead to better outcomes of postoperative axial neck pain and C2–C3 range of motion (ROM) than conventional cervical laminoplasty. However, there is still a lack of understanding of total and proportional postoperative cervical sagittal alignment outcomes. PurposeTo assess the effects of C3 laminectomy in cervical laminoplasty on postoperative cervical alignment and clinical outcomes. DesignA single-center, patient-blinded, randomized controlled trial. Patient SampleWe included consecutive 126 patients diagnosed with cervical spondylotic myelopathy (CSM) or ossification of posterior longitudinal ligament (OPLL) who were scheduled for cervical laminoplasty from March 2017 to January 2020. Outcome MeasuresThe primary outcome measures were C2–C7 Cobb angle (CA) and neck disability index (NDI). Secondary outcomes measures included other clinical outcomes and radiographic parameters including segmental Cobb angle and presence of C2–C3 interlaminar fusion. MethodsPatients were randomly allocated to either the C3 laminectomy with C4–C6 laminoplasty group (LN group) or the C3–C6 laminoplasty group (LP group) at a 1:1 ratio. Laminoplasty was performed using a unilateral open-door technique and stabilized with titanium mini plates. A linear mixed model analysis was employed to examine the longitudinal data from postoperative 1-year through 3-year. Additional analysis between three types of cervical sagittal alignment morphology was done. ResultsAmong 122 patients who were randomly allocated to one of two groups (LN group, n=61; LP group, n=61), modified intent-to-treat analysis was done for 109 patients (LN group, n=51, LP group, n=58) who had available at least a year of postoperative data. Postoperative C2–C7 CA was not significantly different between the two groups. However, NDI was significantly different between the two groups (12.8±1.0 in the LN group vs 8.6±1.0 in LP group, p=.005), which exceeded the minimum clinically important difference (MCID). The postoperative C2–C3 CA was significantly greater in the LN group (7.1±0.5° in LN group vs 3.2±0.5° in LP group, p<.001) while C4–C7 CA was significantly smaller in the LN group (3.9±0.8° in LN group vs 7.7±0.7° in LP group, p<.001) with greater cSVA in the LN group (31.6±1.4 mm in LN group vs 25.5±1.3 mm in LP group at postoperative 3-year, p=.002). Postoperative Euro-Quality of Life-5 Dimension (EQ-5D), numerical rating scores for neck pain (NRS-N) were significantly better in the LP group than in the LN group (all p<.05) and only EQ-5D surpassed the MCID. The C2-C3 fusion rate was significantly different between the LN group (9.8%) and the LP group (44.8%) (p<.001). The LN group showed a higher prevalence of a specific cervical alignment morphology characterized by a sigmoid shape with proximal lordosis and distal kyphosis (S curve). This S curve demonstrated significantly unfavorable outcomes across multiple outcome variables. ConclusionThe impact of C3 laminectomy in cervical laminoplasty on postoperative kyphosis among patients with CSM or OPLL did not significantly differ from that of C3–C6 laminoplasty. However, C3 laminectomy in cervical laminoplasty might result in an unfavorable clinical outcome with an unbalanced cervical sagittal alignment characterized by a sigmoid shape with proximal lordosis and distal kyphosis.

Combining Probability and Nonprobability Samples by Using Multivariate Mass Imputation Approaches with Application to Biomedical Research.

Nonprobability samples have been used frequently in practice including public health study, economics, education, and political polls. Naïve estimates based on nonprobability samples without any further adjustments may suffer from serious selection bias. Mass imputation has been shown to be effective in practice to improve the representativeness of nonprobability samples. It builds an imputation model based on nonprobability samples and generates imputed values for all units in the probability samples. In this paper, we compare two mass imputation approaches including latent joint multivariate normal model mass imputation (e.g., Generalized Efficient Regression-Based Imputation with Latent Processes (GERBIL)) and fully conditional specification (FCS) procedures for integrating multiple outcome variables simultaneously. The Monte Carlo simulation study shows the benefits of GERBIL and FCS with predictive mean matching in terms of balancing the Monte Carlo bias and variance. We further evaluate our proposed method by combining the information from Tribal Behavioral Risk Factor Surveillance System and Behavioral Risk Factor Surveillance System data files.

Single Versus Two Plate Osteosynthesis for Parasymphysis Fractures of the Mandible: A Prospective Comparative Study.

Background The treatment of mandibular fractures has undergone a revolutionary change after the invention of miniplate osteosynthesis. There aren't manystudies in the literature comparing the outcomes of treating mandibular parasymphysis fractures with two miniplates versus one miniplate. Aim To evaluate the outcomes of single vs. two plate osteosynthesis in the management of parasymphysis fractures of the mandible. Materials and methods Sixteen patients with parasymphysis fracture of the mandible treated with a single high-profile miniplate or with two miniplates were included in the study. Multiple outcome variables such as fracture union, wound infection, dehiscence, iatrogenic dental injury,intraoperative time,plate exposure, and need for plate removalwere recorded andanalyzed statistically using the Student's t-test. Results The occurrence of iatrogenic dental injury (P= 0.021) and the mean operating time showed a statistically significant difference between the groups, whereas variables such as osseous healing, plate exposure, wound dehiscence, and postoperative paresthesia had no significant difference (P > 0.05). Conclusion Despite both systems providingenough stability for osseous healing, the use of a single high-profile miniplate demonstrated fewer post-operative problems, such as iatrogenic injury to the dental rootsand occurrence of infection/dehiscence and plate exposure, than the use of two miniplates.

Neurocognitive Deficits in First-Episode and Chronic Psychotic Disorders: A Systematic Review from 2009 to 2022.

Cognitive impairment in patients suffering from schizophrenia spectrum disorders has been discussed as a strong predictor for multiple disease outcome variables, such as response to psychotherapy, stable relationships, employment, and longevity. However, the consistency and severity of cognitive deficits across multiple domains in individuals with first-episode and chronic psychotic disorders is still undetermined. We provide a comprehensive overview of primary research from the years 2009 to 2022. Based on a Cochrane risk assessment, a systematic synthesis of 51 out of 3669 original studies was performed. Impairment of cognitive functioning in patients diagnosed with first-episode psychotic disorders compared with healthy controls was predicted to occur in all assessed cognitive domains. Few overall changes were predicted for chronically affected patients relative to those in the first-episode stage, in line with previous longitudinal studies. Our research outcomes support the hypothesis of a global decrease in cognitive functioning in patients diagnosed with psychotic disorders, i.e., the occurrence of cognitive deficits in multiple cognitive domains including executive functioning, memory, working memory, psychomotor speed, and attention. Only mild increases in the frequency of cognitive impairment across studies were observed at the chronically affected stage relative to the first-episode stage. Our results confirm and extend the outcomes from prior reviews and meta-analyses. Recommendations for psychotherapeutic interventions are provided, considering the broad cognitive impairment already observed at the stage of the first episode. Based on the risk of bias assessment, we also make specific suggestions concerning the quality of future original studies.

Boosting distributional copula regression.

Capturing complex dependence structures between outcome variables (e.g., study endpoints) is of high relevance in contemporary biomedical data problems and medical research. Distributional copula regression provides a flexible tool to model the joint distribution of multiple outcome variables by disentangling the marginal response distributions and their dependence structure. In a regression setup, each parameter of the copula model, that is,the marginal distribution parameters and the copula dependence parameters, can be related to covariates via structured additive predictors. We propose a framework to fit distributional copula regression via model-based boosting, which is a modern estimation technique that incorporates useful features like an intrinsic variable selection mechanism, parameter shrinkage and the capability to fit regression models in high-dimensional data setting, that is,situations with more covariates than observations. Thus, model-based boosting does not only complement existing Bayesian and maximum-likelihood based estimation frameworks for this model class but rather enables unique intrinsic mechanisms that can be helpful in many applied problems. The performance of our boosting algorithm for copula regression models with continuous margins is evaluated in simulation studies that cover low- and high-dimensional data settings and situations with and without dependence between the responses. Moreover, distributional copula boosting is used to jointly analyze and predict the length and the weight of newborns conditional on sonographic measurements of the fetus before delivery together with other clinicalvariables.

The Application of Conditional Probability to Harmonize Nuclear Cardiology Test Results.

Both exercise single photon emission computed tomography (SPECT) imaging and myocardial perfusion imaging with positron emission tomography produce multiple outcome variables. These include the stress electrocardiogram (ECG), visual perfusion assessment and quantitative myocardial blood flow. Bayes' analysis using conditional probability allows the distillation of multiple test results into a single probability of disease for individual patients. This paper examines the application of conditional probability analysis to two noninvasive modalities that generate multiple outcome results: exercise ECG combined with SPECT imaging and vasodilator RB-82 positron emission tomography perfusion imaging combined with quantitative measure of absolute myocardial blood flow. In this manner, a single probability of disease incorporating all the available data is generated for an individual patient.

Rationales for body camera implementation and outcome measures

AbstractAs police body cameras develop as a widely used mechanism to promote police transparency and accountability, researchers are tasked with measuring whether the treatment of this surveillance mechanism meets its stated goals. But the goals have not been clearly outlined and instead, the array of stated goals varies by jurisdiction, creating obstacles for policy diffusion and comparative analyses across numerous randomized controlled trials. Without clearly defined goals, there is no alignment on what success looks like. This narrative review seeks to uncover why body cameras have been implemented in police agencies and what these agencies expect to gain from their use. It details the range of rationales for the adoption of body cameras, which stakeholder parties benefit from goal attainment, and what outcome measurements researchers have and can use to measure body cameras' ability to reach those goals. Most systematic literature reviews of body camera studies simply focus on one outcome measurement. This paper provides a broad view of the body camera research involving multiple outcome variables. It maps these findings onto the stated goals to demonstrate which goals seem to be attainable and which seem to expect body cameras to be a silver bullet solution to societal problems.

Penalized mediation models for multivariate data.

Statistical methods to integrate multiple layers of data, from exposures to intermediate traits to outcome variables, are needed to guide interpretation of complex data sets for which variables are likely contributing in a causal pathway from exposure to outcome. Statistical mediation analysis based on structural equation models provide a general modeling framework, yet they can be difficult to apply to high-dimensional data and they are not automated to select the best fitting model. To overcome these limitations, we developed novel algorithms and software to simultaneously evaluate multiple exposure variables, multiple intermediate traits, and multiple outcome variables. Our penalized mediation models are computationally efficient and simulations demonstrate that they produce reliable results for large data sets. Application of our methods to a study of vascular disease demonstrates their utility to identify novel direct effects of single-nucleotide polymorphisms (SNPs) on coronary heart disease and peripheral artery disease, while disentangling the effects of SNPs on the intermediate risk factors including lipids, cigarette smoking, systolic blood pressure, and type 2 diabetes.

GESLM algorithm for detecting causal SNPs in GWAS with multiple phenotypes.

With the development of genome-wide association studies, how to gain information from a large scale of data has become an issue of common concern, since traditional methods are not fully developed to solve problems such as identifying loci-to-loci interactions (also known as epistasis). Previous epistatic studies mainly focused on local information with a single outcome (phenotype), while in this paper, we developed a two-stage global search algorithm, Greedy Equivalence Search with Local Modification (GESLM), to implement a global search of directed acyclic graph in order to identify genome-wide epistatic interactions with multiple outcome variables (phenotypes) in a case-control design. GESLM integrates the advantages of score-based methods and constraint-based methods to learn the phenotype-related Bayesian network and is powerful and robust to find the interaction structures that display both genetic associations with phenotypes and gene interactions. We compared GESLM with some common phenotype-related loci detecting methods in simulation studies. The results showed that our method improved the accuracy and efficiency compared with others, especially in an unbalanced case-control study. Besides, its application on the UK Biobank dataset suggested that our algorithm has great performance when handling genome-wide association data with more than one phenotype.

Multivariate approach in analyzing medical data with correlated multiple outcomes: An exploration using ACCORD trial data

BackgroundIn clinical setting, to answer a research question, very often more than one outcome variables are used which are statistically correlated. Univariate analysis approach, which is commonly used in such context, violates the assumption of independence for correlated variables, while multivariate approach could give more robust and precise clinical decision by accounting this correlation. This paper is a demonstration of the change in statistical decision in multivariate approach compared to univariate approach in analysing medical data with multiple correlated outcome variables. Methodology: The data used in this paper was the ACCORD trial data and the variables were Systolic blood pressure (SBP) and Diastolic blood pressure (DBP) which are correlated. The condition of bivariate normality was checked after removing the outliers. We compared the differences in means of SBP and DBP separately between the groups at different follow up time points by univariate approach using unpaired ‘t’ test and thereafter together by bivariate approach using Hotelling ‘T2’. Further the role of varied levels of correlation between SBP and DBP coupled with the variations in sample size in changing the statistical inference has been investigated. Robustness of these results were demonstrated through 1000 samples of simulated data from Accord trial data. ResultsThe statistical decision regarding difference in means of either SBP or DBP between the two groups at baseline, 12th, 36th and 84th month in both univariate and bivariate approaches were similar. At baseline and 84th month the hypotheses were accepted and at 12th and 36th month the hypotheses were rejected with both the approaches. However at 60th and 72nd month the univariate and multivariate approach results contradicted each other which reflect the significance of correlation in modifying the inference. The analysis results further indicated that varied levels of correlation and sample size too modify the inference in bivariate approach and contradict univariate results. ConclusionStudies with multiple correlated outcomes, the multivariate approach which accounts this statistical correlation has potential to change statistical decisions and provide more precise results. Hence multivariate approach is recommended in such situations.

Clinical outcome of intradural extramedullary spinal cord tumors: A single-center retrospective analytical study.

Background: Intradural extramedullary spinal cord tumors (IESCT) account for approximately two-thirds of largely benign intraspinal neoplasms. They occasionally present with acute neurological deterioration warranting emergent surgical intervention.Methods: Here, we reviewed a series of 31 patients with intradural extramedullary spinal tumors who underwent surgery from 2012 to 2019. Patients averaged 50.8 years of age, and there were 16 males and 15 females. Patients were followed for a minimum of 1 year. Multiple clinical outcome variables were studied (e.g., Karnofsky Performance Score [KPS], visual analog scale (VAS), and Frankel grade).Results: The majority of IESCT tumors were found in the thoracic spine 18 (58.06%) followed by the lumbar 8 (25.80%), cervical 1 (3.22%), and combined junctional tumors 4 (12.90%) (cervicothoracic-02 and thoracolumbar-02). Histopathological diagnoses included schwannomas-16 (51.61%), meningiomas-11 (35.48%), lipomas-2 (6.45%), hemangiomas-1 (3.22), and ependymomas-01 (03.22%). The VAS score was reduced in all cases, while KPS and Frankel grades were significantly improved. Complications included cerebrospinal fluid leakage, new/residual paresthesias, and tumor recurrence (12.50%).Conclusion: Most intradural extramedullary tumors are benign and are readily diagnosed utilizing MRI scans. Notably, good functional outcomes follow surgical intervention.

Pipeline or Pipedream: Gender Balance Legislation’s Effect on Women’s Presence in State Government

AbstractCan legislation encouraging women’s political involvement impact women’s desire to run for elected office? Eleven states have passed legislation to promote equal gender representation on appointed government boards, and many argue this legislation will also develop a pipeline of women candidates to run for elected office. This paper is the first scholarly work to assess if gender balance legislation (GBL) increases the number of women candidates and women legislators within a state. I use a nonparametric generalization of the difference-in-differences estimator and find very little evidence that GBL significantly impacts women’s representation at the state level. Results are consistent across multiple outcome variables and different model specifications, including two-way fixed effects, generalized synthetic control, and synthetic control models. The insignificant impact of GBL speaks to the need to thoroughly investigate which institutional reforms adequately feed the female candidate pipeline.

Decision-making with multiple correlated binary outcomes in clinical trials.

Clinical trials often evaluate multiple outcome variables to form a comprehensive picture of the effects of a new treatment. The resulting multidimensional insight contributes to clinically relevant and efficient decision-making about treatment superiority. Common statistical procedures to make these superiority decisions with multiple outcomes have two important shortcomings, however: (1) Outcome variables are often modeled individually, and consequently fail to consider the relation between outcomes; and (2) superiority is often defined as a relevant difference on a single, on any, or on all outcome(s); and lacks a compensatory mechanism that allows large positive effects on one or multiple outcome(s) to outweigh small negative effects on other outcomes. To address these shortcomings, this paper proposes (1) a Bayesian model for the analysis of correlated binary outcomes based on the multivariate Bernoulli distribution; and (2) a flexible decision criterion with a compensatory mechanism that captures the relative importance of the outcomes. A simulation study demonstrates that efficient and unbiased decisions can be made while Type I error rates are properly controlled. The performance of the framework is illustrated for (1) fixed, group sequential, and adaptive designs; and (2) non-informative and informative prior distributions.

Variants of psychopathy in Chinese male offenders: A latent profile analysis in a large prison sample

The current study aimed to identify meaningful subtypes of psychopathic traits among male offenders. A Latent Profile Analysis (LPA) based on the scores of the Levenson Self-Report Psychopathy Scale was performed in a large sample of Chinese male prisoners (N = 3375, M age = 36.03, SD = 9.50). Results of the LPA revealed the existence of four profiles: “moderate psychopathy group” (59.5%); “low psychopathy group” (19.5%); “high psychopathy-moderate callousness group” (14.7%); and “low psychopathy-high callousness group” (6.3%). Using the modified Bolck-Croon-Hagenaars (BCH) and categorical distal variable (DCAT) methods, we found that these profiles differed on multiple outcome variables including risk for recidivism, anxiety, depression, reactive aggression and proactive aggression. Overall, findings indicate that the variants of psychopathy found in western incarcerated populations could largely be generalized to the non-western populations, and for the first time suggest that a special profile with low total psychopathy but high callousness traits might exist among male offenders.

Multivariate one-sided testing in matched observational studies as an adversarial game

Summary We present a multivariate one-sided sensitivity analysis for matched observational studies, appropriate when the researcher has specified that a given causal mechanism should manifest itself in effects on multiple outcome variables in a known direction. The test statistic can be thought of as the solution to an adversarial game, where the researcher determines the best linear combination of test statistics to combat nature’s presentation of the worst-case pattern of hidden bias. The corresponding optimization problem is convex, and can be solved efficiently even for reasonably sized observational studies. Asymptotically, the test statistic converges to a chi-bar-squared distribution under the null, a common distribution in order-restricted statistical inference. The test attains the largest possible design sensitivity over a class of coherent test statistics, and facilitates one-sided sensitivity analyses for individual outcome variables while maintaining familywise error control through its incorporation into closed testing procedures.