報(bào) 告 人：鄒國(guó)華，首都師范大學(xué)教授
報(bào)告時(shí)間：2025.07.16 14:00-15:00
報(bào)告地點(diǎn)：蘇州大學(xué)本部天元講堂
報(bào)告摘要：In the age of big data, model averaging has been proved to be a powerful tool for data analysis, which helps to mitigate bias and reduce over?tting that can arise from relying on a single model. However, outliers in large-scale datasets like image recognition and fraud detection can severely degrade traditional model averaging built on least squares or maximum likelihood. To address this challenge, we propose a robust jackknife model averaging (RJMA) approach, where the weights are selected by minimizing a leave-one-out cross-validation criterion. This framework is adaptable to situations where the dimensions of candidate models increase with the sample size. We establish the asymptotic optimality of the RJMA estimator, demonstrating its ability to minimize out-of-sample ?nal prediction errors. We also present the consistency of the proposed weight estimator to the theoretically optimal weight vector. Furthermore, in scenario where one or more correct models are present in the candidate model set, we show that RJMA assigns all weights to the correct models, leading to a consistent model averaging estimator. Additionally, we derive the in?uence function of the RJMA estimator and introduce the empirical prediction in?uence function to quantitatively evaluate its robustness. To illustrate the ef?cacy of our proposed methodology, we conduct numerical studies including Monte Carlo simulations and a real data analysis, which con?rm the practical applicability and robustness of the RJMA approach.
報(bào)告人簡(jiǎn)介：鄒國(guó)華，首都師范大學(xué)教授。博士畢業(yè)于中國(guó)科學(xué)院系統(tǒng)科學(xué)研究所，是國(guó)家杰出青年基金獲得者、“新世紀(jì)百千萬人才工程”國(guó)家級(jí)人選、中國(guó)科學(xué)院“百人計(jì)劃”入選者、享受國(guó)務(wù)院政府特殊津貼，獲中國(guó)科學(xué)院優(yōu)秀研究生指導(dǎo)教師稱號(hào)。主要從事統(tǒng)計(jì)學(xué)的理論研究及其在經(jīng)濟(jì)金融、生物醫(yī)學(xué)中的應(yīng)用研究工作，在統(tǒng)計(jì)模型選擇與平均、抽樣調(diào)查的設(shè)計(jì)與分析、決策函數(shù)的優(yōu)良性、疾病與基因的關(guān)聯(lián)分析等方面的研究中取得了一系列重要成果，得到了國(guó)內(nèi)外同行的好評(píng)與肯定，并被廣泛引用。共出版教材2本，發(fā)表學(xué)術(shù)論文140余篇；主持和參加過近30項(xiàng)國(guó)家科學(xué)基金項(xiàng)目以及全國(guó)性的實(shí)際課題，提出的預(yù)測(cè)方法被實(shí)際部門所采用。
