Premium
Linear Regression With Nested Errors Using Probability‐Linked Data
Author(s) -
Samart Klairung,
Chambers Ray
Publication year - 2014
Publication title -
australian and new zealand journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 41
eISSN - 1467-842X
pISSN - 1369-1473
DOI - 10.1111/anzs.12052
Subject(s) - statistics , estimator , mathematics , variance (accounting) , matching (statistics) , record linkage , generalized linear model , linkage (software) , small area estimation , standard error , statistical model , econometrics , regression analysis , linear model , population , biochemistry , chemistry , demography , accounting , sociology , business , gene
Summary Probabilistic matching of records is widely used to create linked data sets for use in health science, epidemiological, economic, demographic and sociological research. Clearly, this type of matching can lead to linkage errors, which in turn can lead to bias and increased variability when standard statistical estimation techniques are used with the linked data. In this paper we develop unbiased regression parameter estimates to be used when fitting a linear model with nested errors to probabilistically linked data. Since estimation of variance components is typically an important objective when fitting such a model, we also develop appropriate modifications to standard methods of variance components estimation in order to account for linkage error. In particular, we focus on three widely used methods of variance components estimation: analysis of variance, maximum likelihood and restricted maximum likelihood. Simulation results show that our estimators perform reasonably well when compared to standard estimation methods that ignore linkage errors.