Accounting for Uncertainty in Heteroscedasticity in Nonlinear Regression

Toxicologists and pharmacologists often describe toxicity of a chemical using parameters of a nonlinear regression model. Thus estimation of parameters of a nonlinear regression model is an important problem. The estimates of the parameters and their uncertainty estimates depend upon the underlying error variance structure in the model. Typically, a priori the researcher would not know if the error variances are homoscedastic (i.e., constant across dose) or if they are heteroscedastic (i.e., the variance is a function of dose). Motivated by this concern, in this paper we introduce an estimation procedure based on preliminary test which selects an appropriate estimation procedure accounting for the underlying error variance structure. Since outliers and influential observations are common in toxicological data, the proposed methodology uses M-estimators. The asymptotic properties of the preliminary test estimator are investigated; in particular its asymptotic covariance matrix is derived. The performance of the proposed estimator is compared with several standard estimators using simulation studies. The proposed methodology is also illustrated using a data set obtained from the National Toxicology Program.     

Children's experiences with an intervention aimed to prevent further physical abuse

Although many children across cultures are victims of physical abuse, few treatment models target these children and their parents. In Sweden, Combined Parent–Child Cognitive Behavioural Therapy for families at risk for child physical abuse has been successfully used according to pretreatment and posttreatment studies. However, few studies have explored how physically abused children experience treatment. This study includes 20 physically abused children aged 9–17 who completed Combined Parent–Child Cognitive Behavioural Therapy. Children had a positive overall impression of the treatment and highlighted addressing the abuse, as well as processing their experiences as particularly essential. Children described a positive transformation in their family life as a result of treatment, including violence cessation and bonding among family members. Children experienced the intervention as inclusive and child‐friendly. The implications of the promising findings are discussed.     

公共性视角下平台“大数据杀熟”的规制逻辑与路径

平台“大数据杀熟”是通过算法侵害消费者权益的行为,存在社会伦理和技术伦理的双重可责性,应当予以规制。《反垄断法》《消费者权益保护法》《价格法》等传统法律制度对“大数据杀熟”的规制存在理念与制度层面的困境。鉴于大数据平台所具有的公共性特征及“大数据杀熟”侵害对象的不特定性,“大数据杀熟”规制可以借鉴公用事业理论,采取事前监管方式,对适格的平台主体施加透明、合理、非歧视的价格制定和标示义务,并通过设立专业的平台监管机构,确保上述义务得到履行。     

A Randomized Controlled Trial of a Financial Literacy Curriculum for Survivors of Intimate Partner Violence

Financial literacy programs are quickly gaining in popularity around the globe. A relatively new target group is survivors of intimate partner violence (IPV), an economically vulnerable group for whom resource acquisition is related to personal safety and well-being. This study is a randomized controlled trial of a financial literacy curriculum designed for and delivered to a sample of 300 IPV survivors from 14 agencies in seven US states and Puerto Rico. Findings, based on difference-in-difference analyses and OLS regression models, indicate a strong effect of the curriculum on self-reported financial knowledge and behaviors and support the expansion of similar programs for survivors.     

对中国经济运行状况的分析

从经济的投资、消费和出口数据看,中国经济增速确实在下行。为了保持中国经济8%的增速,我们已付出了很高的代价;经过35年的高速增长,在各行各业产能基本过剩的情况下,中国经济增速正在下移。观察1950年代后日本、中国台湾和香港地区经济发展的过程,其经济高速增长后,也是一个台阶又一个台阶地下来。中国不能再靠高投资来推动经济增长。     

The Mother‐Citizen and the Working Girl: First‐Wave Feminist Citizenship Claims in Canada and Discursive Opportunities for Twenty‐First Century Childcare Policy

L'État providence Canadien est déséquilibré: leader mondial dans certains domaines de l'investissement social—plus particulièrement en soins de santé et enseignement supérieur—il traîne dans d'autres domaines de la dépense d'aide sociale, y compris les politiques de garde d'enfants. Nous constatons qu'aujourd'hui la résistance dans la plupart des régions du Canada à la politique de garde d'enfants universel a des racines historiques profondes. Elle est de fait intégré dans le cadre même du bien‐être social canadien: le contrat de citoyenneté sociale. Nous employons une approche de “bas en haut” sur l'état du bien‐être en nous concentrant sur la façon dont les acteurs collectifs, en particulier, les féministes de la première vague et leurs contemporains au sein des organisations du mouvement ouvrier, ont encadrées et caractérisé la citoyenneté sociale féminine; Nous constatons que l'exclusion de l'adhésion des femmes employées tronque les possibilités discursives par lesquelles des revendications pour des provisions universelles de bien‐être sociale pourraient être apportées. Canada's welfare state is lopsided: while leading the world in some areas of social investment—most notably health care and higher education—it is a laggard in other areas of social welfare spending, including childcare policies. We find that policy resistance to universal childcare in most regions of Canada today has deep historical roots and is, indeed, embedded into the very framework of the Canadian welfare state: the social citizenship contract. We employ a “bottom‐up” perspective on the welfare state focusing on how collective actors, in particular, first‐wave feminists and their contemporaries within labor movement organizations, framed and characterized female social citizenship in ways that excluded employed women from full membership and, in this, truncated discursive opportunities by which claims for universal welfare state provisions could be made.     

Asymptotic equivalence of the harrell-davis median estimator and the sample median

This paper presents an asymptotic equivalence result with a sharp rate of convergence forthe sample median and the Harrell-Davis median estimator. The consequences of this result are discussed.     

On shrinkage m-estimators of location parameters

For a general class of continuous ( and marginally symmetric ) inultivariate distributions, based on suitable M-statistics ( involving bounded but possibly discontinuous score generating functions), shrinkage estimators of location are considered. These estimators are based on the James-Stein type rule and incorporates the idea of preliminary test estimation too. The main emphasis is laid on the study of asymptotic tdistributional ) risk properties of these est-innators, and asymptotic tin-) adraissibility results are also studied under fairly general regularity conditions.