只有值的分析方法演示

（優(yōu)選）只有值的分析方法當(dāng)前1頁，總共31頁。STATA簡(jiǎn)介由美國(guó)計(jì)算機(jī)資源中心（ComputerResourceCenter）研制；現(xiàn)在為Stata公司的產(chǎn)品；目前最高版本9.0；與SAS、SPSS一起并稱為三大權(quán)威統(tǒng)計(jì)軟件。操作靈活、簡(jiǎn)單、易學(xué)易用，同時(shí)具有數(shù)據(jù)管理軟件、統(tǒng)計(jì)分析軟件、繪圖軟件、矩陣計(jì)算軟件和程序語言的特點(diǎn)。當(dāng)前2頁，總共31頁。STATA的進(jìn)入和退出進(jìn)入：雙擊STATA軟件圖標(biāo)退出：菜單方式:File→Exit窗口方式命令方式:exit當(dāng)前3頁，總共31頁。STATA的用戶界面命令回顧變量列表結(jié)果輸出命令輸入菜單和工具欄當(dāng)前4頁，總共31頁。STATA數(shù)據(jù)管理數(shù)據(jù)的輸入與儲(chǔ)存數(shù)據(jù)庫的排序刪除變量或記錄保留變量或記錄產(chǎn)生新變量替換已存在的變量值當(dāng)前5頁，總共31頁。數(shù)據(jù)的輸入與存儲(chǔ)數(shù)據(jù)輸入數(shù)據(jù)編輯窗口；復(fù)制和粘貼。數(shù)據(jù)儲(chǔ)存save命令FileSaveAs當(dāng)前6頁，總共31頁。數(shù)據(jù)編輯窗口數(shù)據(jù)編輯按鈕窗口當(dāng)前7頁，總共31頁。使用數(shù)據(jù)編輯窗口輸入每一行代表一條記錄每一列代表一個(gè)變量當(dāng)前8頁，總共31頁。數(shù)據(jù)庫的排序

sort變量名1變量名2……

gsort+/-變量清單

sortx對(duì)變量x中數(shù)值從小到大進(jìn)行排列g(shù)sortx對(duì)變量x中數(shù)值從小到大進(jìn)行排列g(shù)sort-x對(duì)變量x中數(shù)值從大到小進(jìn)行排列當(dāng)前9頁，總共31頁。刪除（或保留）變量或記錄刪除變量或記錄dropvarlistdropifexpdropinrange保留變量或記錄keepvarlistkeepifexpkeepinrange[ifexp]

當(dāng)前10頁，總共31頁。刪除變量或記錄dropx1x2 /*刪除變量x1和x2dropx1-x3 /*刪除數(shù)據(jù)庫中介于x1和x3間的所有變量(包括x1和x3)dropifx<0 /*刪去x<0的所有記錄dropin1/3 /*刪去第1~3個(gè)記錄dropifx==. /*刪去x為缺失值的所有記錄dropifx==.|y==. /*刪去x或y之一為缺失值的所有記錄dropifx==.&y==./*刪去x和y同時(shí)為缺失值的所有記錄drop_all/*刪掉數(shù)據(jù)庫中所有變量和數(shù)據(jù)當(dāng)前11頁，總共31頁。保留變量或記錄keepin1/5/*保留第1～5個(gè)記錄，其余記錄刪除keepx1-x3/*保留數(shù)據(jù)庫中介于x1和x3間的所有變量(包括x1和x3)，其余變量刪除keepifx>0/*保留x>0的所有記錄，其余記錄刪除當(dāng)前12頁，總共31頁。用generate產(chǎn)生新變量

generate新變量＝表達(dá)式

geny＝x+1

/*產(chǎn)生新變量y，其值為x+1。

geny=log(x)ifx>0

/*產(chǎn)生新變量y，其值為所有x>0的對(duì)數(shù)log(x)，當(dāng)x<=0時(shí)，用缺失值代替。當(dāng)前13頁，總共31頁。替換已存在的變量值

replace變量＝表達(dá)式replacebolck=6ifblock==0

/*將block＝0的數(shù)全部替換為6。replacez=.ifz<0

/*將所有小于0的z值用缺失值代替。replaceage=25in2

/*將第2條記錄中的變量age替換為25。當(dāng)前14頁，總共31頁。Fixedandrandomeffectsmeta-analysismetanvarlist[ifexp][inrange][,rrorrdfixedrandomfixedirandomipetoby(byvar)

label(namevar=name,yearvar=year)]rrpoolsriskratios[default]orpoolsoddsratiosrdpoolsriskdifferencesfixedspecifiesafixedeffectmodelrandomspecifiesarandomeffectsmodel當(dāng)前15頁，總共31頁。Thefollowingnewvariablestothedataset

_ES Effectsize(ES)_seES StandarderrorofESor,whenORorRRarespecfied:_selogES thestandarderrorofitslogarithm_LCI LowerconfidencelimitforES_UCI UpperconfidencelimitforES_WT Studypercentageweight_SS Studysamplesize當(dāng)前16頁，總共31頁。Example1StudyCountryCaseControlCCAACCAAMisraRREuropean5311246103HouSMEuropean32712869ZhouWEuropean166428166499SpitzMREuropean4714139159David-BeabesGL1European346758197LingGAsian148396848ChenSAsian11512041ParkJYAsian12200145David-beabesGL2European117913130當(dāng)前17頁，總共31頁。Stataresultmetancaseccaseacontrolccontrolaifcountry=="European",orlabel(namevar=study)metanabcd,orlabel(namevar=study)

Study|OR[95%Conf.Interval]%Weight---------------------+----------------------------------------------MisraRR|1.0600.6581.70714.60HouSM|1.1110.6062.0368.85ZhouW|1.1660.9071.49850.23SpitzMR|1.3590.8402.19912.68David-BeabesGL1|1.7241.0392.8599.72David-beabesGL2|1.3920.5953.2583.92---------------------+----------------------------------------------M-HpooledOR|1.2331.0351.469100.00---------------------+----------------------------------------------Heterogeneitychi-squared=2.61(d.f.=5)p=0.760I-squared(variationinORattributabletoheterogeneity)=0.0%TestofOR=1:z=2.34p=0.019當(dāng)前18頁，總共31頁。Forestplot當(dāng)前19頁，總共31頁。Stataresultmetancaseccaseacontrolccontrolaifcountry=="Asian",orlabel(namevar=study)

Study|OR[95%Conf.Interval]%Weight---------------------+---------------------------------------------LingG|2.3580.9026.16625.55ChenS|0.4420.1901.02771.85ParkJY|1.9800.08048.9272.60---------------------+---------------------------------------------M-HpooledOR|0.9720.5441.737100.00---------------------+---------------------------------------------Heterogeneitychi-squared=6.81(d.f.=2)p=0.033I-squared(variationinORattributabletoheterogeneity)=70.6%TestofOR=1:z=0.10p=0.923當(dāng)前20頁，總共31頁。Stataresultmetancaseccaseacontrolccontrolaifcountry=="Asian",orlabel(namevar=study)random

Study|OR[95%Conf.Interval]%Weight---------------------+----------------------------------------------LingG|2.3580.9026.16642.15ChenS|0.4420.1901.02744.27ParkJY|1.9800.08048.92713.57---------------------+----------------------------------------------D+LpooledOR|1.0970.2794.316100.00---------------------+----------------------------------------------Heterogeneitychi-squared=6.81(d.f.=2)p=0.033I-squared(variationinORattributabletoheterogeneity)=70.6%Estimateofbetween-studyvarianceTau-squared=0.9175TestofOR=1:z=0.13p=0.894當(dāng)前21頁，總共31頁。Forestplot當(dāng)前22頁，總共31頁。Stataresultmetancaseccaseacontrolccontrola,orby(country)label(namevar=study)Study|OR[95%Conf.Interval]%Weight-------------------------+---------------------------------------------------AsianLingG|2.3580.9026.1662.38ChenS|0.4420.1901.0276.69ParkJY|1.9800.08048.9270.24Sub-totalM-HpooledOR|0.9720.5441.7379.32-------------------------+---------------------------------------------------EuropeanMisraRR|1.0600.6581.70713.24HouSM|1.1110.6062.0368.02ZhouW|1.1660.9071.49845.55SpitzMR|1.3590.8402.19911.50David-BeabesGL1|1.7241.0392.8598.81David-beabesGL2|1.3920.5953.2583.56Sub-totalM-HpooledOR|1.2331.0351.46990.68-------------------------+---------------------------------------------------OverallM-HpooledOR|1.2091.0221.430100.00-------------------------+---------------------------------------------------Test(s)ofheterogeneity:HeterogeneitydegreesofstatisticfreedomPI-squared**Asian6.8120.03370.6%European2.6150.7600.0%Overall10.0980.25920.7%OverallTestforheterogeneitybetweensub-groups:0.6710.415**I-squared:thevariationinORattributabletoheterogeneity)Significancetest(s)ofOR=1Asianz=0.10p=0.923Europeanz=2.34p=0.019Overallz=2.21p=0.027-------------------------------------------------------------------------當(dāng)前23頁，總共31頁。Forestplot當(dāng)前24頁，總共31頁。Example2研究編號(hào)(no)治療組對(duì)照組均數(shù)(meanE)標(biāo)準(zhǔn)差(SE)樣本量(nE)均數(shù)(meanC)標(biāo)準(zhǔn)差(SC)樣本量(nC)128.03.33029.02.835225.52.93427.42.731326.52.73227.52.931427.83.43329.82.631527.23.03028.12.932628.02.86029.23.150當(dāng)前25頁，總共31頁。Stataresultmetann1mean1sd1n2mean2sd2Study|SMD[95%Conf.Interval]%Weight---------------------+--------------------------------------------1|-0.329-0.8200.16215.342|-0.677-1.178-0.17614.743|-0.357-0.8550.14114.914|-0.658-1.162-0.15414.575|-0.305-0.8060.19614.736|-0.408-0.787-0.02925.71---------------------+--------------------------------------------I-VpooledSMD|-0.449-0.642-0.257100.00---------------------+--------------------------------------------Heterogeneitychi-squared=2.18(d.f.=5)p=0.824I-squared(variationinSMDattributabletoheterogeneity)=0.0%TestofSMD=0:z=4.58p=0.000當(dāng)前26頁，總共31頁。Forestplot當(dāng)前27頁，總共31頁。Testsforpublicationbiasinmeta-analysis

metabiasthetase_theta,by(by_var)graph({begg)當(dāng)前28頁，總共31頁。Stataresultgenlogor=log(_ES)genselogor=_selogESmetabiaslogorselogor,graph(begg)Note:defaultdatainputformat(theta,se_theta)assumed.TestsforPublicationBiasBegg'sTestadj.Kendall'sScore(P-Q)=6