在复杂抽样分析下选择最佳模型

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

我是一个新手，请问我用svyset了复杂抽样变量，在做线形回归模型的时候怎么可以选择最佳模型呢？没有svyset的时候可以看adjusted R-square的大小，用了svyset，就没有R-square了，怎么比呢?用AIC和BIC么？怎么做呢？能告诉我命令是什么么？

非常感谢！

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：抽样分析 复杂抽样 adjusted Square adjust adjusted 模型

Is svyset a SPSS's command?

SAS® Model Selection Macros for Complex Survey Data Using PROC SURVEYLOGISTIC/SURVEYREG

ABSTRACT
Regression model selection is widely used in analyzing survey data. In SAS 9.1, Proc Surveylogistic and Proc Surveyreg were developed for analyzing data from complex surveys (stratified and/or clustered surveys). But neither of them has the capacity of automated model selection. “Manual” coding for each specific task would be time-consuming and very labor intensive. This paper details two major macros to perform automated forward, backward and stepwise model selection for complex survey data: %StepSvylog for logistic regression using Proc Surveylogistic, and %StepSvyreg for linear regression using Proc Surveyreg.


http://www.mwsug.org/proceedings/2011/stats/MWSUG-2011-SA02.pdf

Multilevel Modeling of Complex Survey Data
Tihomir Asparouhov1
, Bengt Muthen2
Muthen & Muthen1
University of California, Los Angeles

http://www.statmodel.com/download/SurveyJSM1.pdf

Model Selection for Incomplete and Design-Based Samples: An Application to Cervix Cancer Screening

AbstractThe Akaike Information Criterion, AIC, is one of the most frequently used methods to select one or a few good, optimal regression models from a set of candidate models. In case the sample is incomplete, the naive use of this criterion on the so-called complete cases can lead to the selection of poor or inappropriate models. A similar problem occurs when a sample based on a design with unequal selection probabilities, is treated as a simple random sample. In this paper we consider a modification of AIC, based on reweighing the sample in analogy with the weighted Horvitz-Thompson estimates. It is shown that this weighted AIC-criterion provides better model choices for both incomplete and design-based samples. The use of the weighted AIC-criterion is illustrated on data from the Belgian Health Interview Survey, which motivated this research. Simulations show its performance in a variety of settings.
http://missingdata.lshtm.ac.uk/preprints/hens_et_al_v2.pdf

这个不是stata的么。。。

好好有学问啊