基于分組數(shù)據(jù)回歸系數(shù)的估計(jì).pdf

1、復(fù)旦大學(xué)碩士學(xué)位論文基于分組數(shù)據(jù)回歸系數(shù)的估計(jì)姓名：項(xiàng)陽(yáng)申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：概率論與數(shù)理統(tǒng)計(jì)指導(dǎo)教師：鄭明20070510復(fù)旦大學(xué)碩士學(xué)位論文iiABSTRACTAgroupedobservationmeansthatXisknowneitherliesinsideaninterval阢一1，乃)，ornotHowever，wearenotabletoolxrvetheexactvalueofXItisveryimportantbo

2、thinpracticeandintheorytostudythiskindofdata，foritoftenOccursinmedicalresemxchandeconomicanalysisRecentlythiskindofquestionisunderdiscussion，andsomeofthemhavebeensolvedInspiteofthat，therearemanyunresolvedquestionsinthisf

3、ieldInthispaper，wetrytostudytheproblemofestimatingtheregressioncoefficientsinthelinearregressionmodelsbasedOngroupeddataThepaperconsistsof5chaptersInchapter1weintroducebackgroundatwhichthelinearregressionmodelsbasedOngro

4、upeddataareproposedandtheproblemellcounteredduringtheprocessofcarryingouttheclassical岫lllnlikelihoodmethodInchapter2，weintroduceanusualalgorithmforhandlingincompletedata，EMalgorithm，anditsextendedalgorithms，SEMalgorithma

5、ndECMalgorithmInchapter3，wediscusstheexistbenceanduniquenessofMLEforclassicallinearregressionmodelsbased011groupeddataanduseEMalgorithmandSEMalgorithmtoobtaintheapproximatesolutionoftheMLEanditsasymptoticcovariancevarian

6、cerespectivelyInchapter4，weuseECMalgorithmtoobtaintheapproximatesolutionoftheMLEforgroupedheteroscedastieandgroupeddatalinearregressionmodelandSEMalgorithmtoestimateitsasymptoticcovariancevarianceInchapter5well艙ECMalgori

7、thmtoobtaintheapproximatesolutionoftheMLEformultiplelinearregressionmodelwithgroupeddataandSEMalgorithmtoestimateitsasymptoticcovariancevarianceBysimulationsweshowthatthesemethodsareavailableandeffectiveKeywords：MLE，grou