预览加载中，请您耐心等待几秒...

上海财经学院统计系举行学术讨论会.docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

上海财经学院统计系举行学术讨论会 Topic:AcademicDiscussiononStatisticsatShanghaiUniversityofFinanceandEconomics Introduction OnSeptember18,2021,theDepartmentofStatisticsatShanghaiUniversityofFinanceandEconomicsheldanacademicdiscussiononthelatesttrendsandchallengesinthefieldofstatistics.Theobjectiveofthediscussionwastoprovideaplatformforstatisticianstosharetheirresearchfindingsandtoexchangeideaswiththeirpeers.Thispaperpresentsanoverviewofthetopicsdiscussedinthemeeting. OverviewoftheDiscussion Thediscussionrevolvedaroundfourkeyareas:DataScience,TimeSeriesAnalysis,High-DimensionalInferenceandBayesianStatistics. DataScience Thediscussionbeganwithapresentationondatascience.Thepresenterdiscussedthevariousapproachestodatascienceandemphasizedtheimportanceofunderstandingtheunderlyingstatisticaltheory.Thediscussionfocusedonthemethodsthatareusedtoanalyzeandinterpretdata,suchasregressionanalysis,principalcomponentanalysis,andclusteranalysis.Thepresenteralsotouchedonthetechniquesusedinmachinelearning,suchasneuralnetworks,decisiontrees,andrandomforest. TimeSeriesAnalysis Thesecondpresentationfocusedontimeseriesanalysis.Thepresenterdiscussedthevariouschallengesthatarisewhenanalyzingtimeseriesdata,suchastheneedtoaccountfortemporaldependencies,non-stationarity,andnon-linearity.Thepresenterhighlightedtheimportanceofselectinganappropriatemodelforthedataanddiscussedthevariousmodelsthatarecommonlyused,suchasARIMA,ARCH/GARCHandVAR. High-DimensionalInference Thethirdpresentationfocusedonhigh-dimensionalinference.Thepresenterdiscussedthechallengesthatarisewhendealingwithhigh-dimensionaldata,suchasthecurseofdimensionalityandsparsity.Thepresenterhighlightedtheimportanceofdevelopingmethodsthatarerobusttohigh-dimensionaldataanddiscussedvariousapproaches,suchasLassoregressionandrandomprojection. BayesianStatistics ThefinalpresentationfocusedonBayesianStatistics.ThepresenterdiscussedthekeyconceptsofBayesianStatistics,suchaspriordistributionsandposteriordistributions.ThepresenterhighlightedtheadvantagesofBayesian