science researchersintroduction to panel m科学researchersintroduction面板m_第1页
science researchersintroduction to panel m科学researchersintroduction面板m_第2页
science researchersintroduction to panel m科学researchersintroduction面板m_第3页
science researchersintroduction to panel m科学researchersintroduction面板m_第4页
science researchersintroduction to panel m科学researchersintroduction面板m_第5页
已阅读5页,还剩59页未读 继续免费阅读

下载本文档

版权说明:本文档由用户提供并上传,收益归属内容提供方,若内容存在侵权,请进行举报或认领

文档简介

Longitudinal Data Analysis for Social Science ResearchersIntroduction to Panel Modelswww.longitudinal.stir.ac.ukSIMPLE TABLE PANEL DATABEWARE BEWAREWomen in their 20s in 1991 Ten Years Later Traditionally used in social mobility work Can be made more exotic for example by incorporating techniques from loglinear modelling (there is a large body of methodological literature in this area)Change Score Less likely to use this approach in mainstream social science Understanding this will help you understand the foundation of more complex panel models (especially this afternoon)Yi 1 = bXi1 + ei1 Vector of explanatory variables and estimatesIndependent identifiably distributed errorOutcome 1 for individual iYi 1 = bXi1 + ei1 Vector of explanatory variables and estimatesIndependent identifiably distributed errorOutcome 1 for individual iEQUATION FOR TIME POINT 2Yi 1 = bXi1 + ei1 Yi 2 = bXi2 + ei2Considered together conventional regression analysis in NOT appropriate Yi 2 - Yi 1 = b(Xi2-Xi1) + (ei2 - ei1) Change in ScoreHere the b is simply a regression on the difference or change in scores. Women in 20s H.H. Income Month Before Interview (Wfihhmn)WAVE A WAVE BMEAN 1793.50 1788.15S.D. 1210.26 1171.36MEDIAN 1566.34 1587.50SKEWNESS 1.765 1.404PERCENTILES25% 914.43 950.5175% 2339.39 2353.85r =.679*A Simple Scatter PlotYi 2 - Yi 1 = b(Xi2-Xi1) + (ei2 - ei1) Change in ScoreHere the b is simply a regression on the difference or change in scores. Difference or change in scores(bfihhmn afihhmn) Models for Multiple MeasuresPanel ModelsPID WAVE SEX AGE Y001 1 1 20 1001 2 1 21 1001 3 1 22 1001 4 1 23 0001 5 1 24 0001 6 1 25 1Models for Multiple Repeated Measures“Increasingly, I tend to think of these approaches as falling under the general umbrella of generalised linear modelling (glm). This allows me to think about longitudinal data analysis simply as an extension of more familiar statistical models from the regression family. It also helps to facilitate the interpretation of results.”Some Common Panel Models(STATA calls these Cross-sectional time series!)Binary Y Logit xtlogit(Probit xtprobit)Count Y Poisson xtpoisson(Neg bino xtnbreg)Continuous Y Regression xtregModels for Multiple MeasuresAs social scientists we are often substantively interested in whether a specific event has occurred.Therefore for the next 30 minutes I will mostly be concentrating on models for binary outcomesRecurrent events are merely outcomes that can take place on a number of occasions. A simple example is unemployment measured month by month. In any given month an individual can either be employed or unemployed. If we had data for a calendar year we would have twelve discrete outcome measures (i.e. one for each month).Consider a binary outcome or two-state event0 = Event has not occurred1 = Event has occurredIn the cross-sectional situation we are used to modelling this with logistic regression.A study for six months0 = Unemployed; 1 = WorkingUNEMPLOYMENT AND RETURNING TO WORK STUDY Months1 2 3 4 5 6obs 0 0 0 0 0 0Constantly unemployedMonths1 2 3 4 5 6obs 1 1 1 1 1 1Constantly employedMonths1 2 3 4 5 6obs 1 0 0 0 0 0Employed in month 1 then unemployedMonths1 2 3 4 5 6obs 0 0 0 0 0 1Unemployed but gets a job in month sixHere we have a binary outcome so could we simply use logistic regression to model it?Yes and No We need to think about this issue.POOLED CROSS-SECTIONAL LOGIT MODELx it is a vector of explanatory variables and b is a vector of parameter estimates We could fit a pooled cross-sectional model to our recurrent events data.This approach can be regarded as a nave solution to our data analysis problem. We need to consider a number of issues.

温馨提示

  • 1. 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
  • 2. 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
  • 3. 本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
  • 4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
  • 5. 人人文库网仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对用户上传分享的文档内容本身不做任何修改或编辑,并不能对任何下载内容负责。
  • 6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
  • 7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。

评论

0/150

提交评论