A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization.
In regression modelling, measurement error models are often needed to correct for uncertainty arising from measurements of covariates/predictor variables. The literature on measurement error (or errors-in-variables) modelling is plentiful, however, general algorithms and software for maximum likelih...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0283798 |
| _version_ | 1797843165195010048 |
|---|---|
| author | Jakub Stoklosa Wen-Han Hwang David I Warton |
| author_facet | Jakub Stoklosa Wen-Han Hwang David I Warton |
| author_sort | Jakub Stoklosa |
| collection | DOAJ |
| description | In regression modelling, measurement error models are often needed to correct for uncertainty arising from measurements of covariates/predictor variables. The literature on measurement error (or errors-in-variables) modelling is plentiful, however, general algorithms and software for maximum likelihood estimation of models with measurement error are not as readily available, in a form that they can be used by applied researchers without relatively advanced statistical expertise. In this study, we develop a novel algorithm for measurement error modelling, which could in principle take any regression model fitted by maximum likelihood, or penalised likelihood, and extend it to account for uncertainty in covariates. This is achieved by exploiting an interesting property of the Monte Carlo Expectation-Maximization (MCEM) algorithm, namely that it can be expressed as an iteratively reweighted maximisation of complete data likelihoods (formed by imputing the missing values). Thus we can take any regression model for which we have an algorithm for (penalised) likelihood estimation when covariates are error-free, nest it within our proposed iteratively reweighted MCEM algorithm, and thus account for uncertainty in covariates. The approach is demonstrated on examples involving generalized linear models, point process models, generalized additive models and capture-recapture models. Because the proposed method uses maximum (penalised) likelihood, it inherits advantageous optimality and inferential properties, as illustrated by simulation. We also study the model robustness of some violations in predictor distributional assumptions. Software is provided as the refitME package on R, whose key function behaves like a refit() function, taking a fitted regression model object and re-fitting with a pre-specified amount of measurement error. |
| first_indexed | 2024-04-09T17:00:23Z |
| format | Article |
| id | doaj.art-340d0075e81948caaaa003ad9ff90ff3 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-09T17:00:23Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-340d0075e81948caaaa003ad9ff90ff32023-04-21T05:32:38ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01184e028379810.1371/journal.pone.0283798A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization.Jakub StoklosaWen-Han HwangDavid I WartonIn regression modelling, measurement error models are often needed to correct for uncertainty arising from measurements of covariates/predictor variables. The literature on measurement error (or errors-in-variables) modelling is plentiful, however, general algorithms and software for maximum likelihood estimation of models with measurement error are not as readily available, in a form that they can be used by applied researchers without relatively advanced statistical expertise. In this study, we develop a novel algorithm for measurement error modelling, which could in principle take any regression model fitted by maximum likelihood, or penalised likelihood, and extend it to account for uncertainty in covariates. This is achieved by exploiting an interesting property of the Monte Carlo Expectation-Maximization (MCEM) algorithm, namely that it can be expressed as an iteratively reweighted maximisation of complete data likelihoods (formed by imputing the missing values). Thus we can take any regression model for which we have an algorithm for (penalised) likelihood estimation when covariates are error-free, nest it within our proposed iteratively reweighted MCEM algorithm, and thus account for uncertainty in covariates. The approach is demonstrated on examples involving generalized linear models, point process models, generalized additive models and capture-recapture models. Because the proposed method uses maximum (penalised) likelihood, it inherits advantageous optimality and inferential properties, as illustrated by simulation. We also study the model robustness of some violations in predictor distributional assumptions. Software is provided as the refitME package on R, whose key function behaves like a refit() function, taking a fitted regression model object and re-fitting with a pre-specified amount of measurement error.https://doi.org/10.1371/journal.pone.0283798 |
| spellingShingle | Jakub Stoklosa Wen-Han Hwang David I Warton A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization. PLoS ONE |
| title | A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization. |
| title_full | A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization. |
| title_fullStr | A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization. |
| title_full_unstemmed | A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization. |
| title_short | A general algorithm for error-in-variables regression modelling using Monte Carlo expectation maximization. |
| title_sort | general algorithm for error in variables regression modelling using monte carlo expectation maximization |
| url | https://doi.org/10.1371/journal.pone.0283798 |
| work_keys_str_mv | AT jakubstoklosa ageneralalgorithmforerrorinvariablesregressionmodellingusingmontecarloexpectationmaximization AT wenhanhwang ageneralalgorithmforerrorinvariablesregressionmodellingusingmontecarloexpectationmaximization AT davidiwarton ageneralalgorithmforerrorinvariablesregressionmodellingusingmontecarloexpectationmaximization AT jakubstoklosa generalalgorithmforerrorinvariablesregressionmodellingusingmontecarloexpectationmaximization AT wenhanhwang generalalgorithmforerrorinvariablesregressionmodellingusingmontecarloexpectationmaximization AT davidiwarton generalalgorithmforerrorinvariablesregressionmodellingusingmontecarloexpectationmaximization |