Prepaid parameter estimation without likelihoods.
In various fields, statistical models of interest are analytically intractable and inference is usually performed using a simulation-based method. However elegant these methods are, they are often painstakingly slow and convergence is difficult to assess. As a result, statistical inference is greatl...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2019-09-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1007181 |
| _version_ | 1818716769660960768 |
|---|---|
| author | Merijn Mestdagh Stijn Verdonck Kristof Meers Tim Loossens Francis Tuerlinckx |
| author_facet | Merijn Mestdagh Stijn Verdonck Kristof Meers Tim Loossens Francis Tuerlinckx |
| author_sort | Merijn Mestdagh |
| collection | DOAJ |
| description | In various fields, statistical models of interest are analytically intractable and inference is usually performed using a simulation-based method. However elegant these methods are, they are often painstakingly slow and convergence is difficult to assess. As a result, statistical inference is greatly hampered by computational constraints. However, for a given statistical model, different users, even with different data, are likely to perform similar computations. Computations done by one user are potentially useful for other users with different data sets. We propose a pooling of resources across researchers to capitalize on this. More specifically, we preemptively chart out the entire space of possible model outcomes in a prepaid database. Using advanced interpolation techniques, any individual estimation problem can now be solved on the spot. The prepaid method can easily accommodate different priors as well as constraints on the parameters. We created prepaid databases for three challenging models and demonstrate how they can be distributed through an online parameter estimation service. Our method outperforms state-of-the-art estimation techniques in both speed (with a 23,000 to 100,000-fold speed up) and accuracy, and is able to handle previously quasi inestimable models. |
| first_indexed | 2024-12-17T19:24:32Z |
| format | Article |
| id | doaj.art-731981b6f1c641bbb91d854e920ddbb8 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-12-17T19:24:32Z |
| publishDate | 2019-09-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-731981b6f1c641bbb91d854e920ddbb82022-12-21T21:35:25ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582019-09-01159e100718110.1371/journal.pcbi.1007181Prepaid parameter estimation without likelihoods.Merijn MestdaghStijn VerdonckKristof MeersTim LoossensFrancis TuerlinckxIn various fields, statistical models of interest are analytically intractable and inference is usually performed using a simulation-based method. However elegant these methods are, they are often painstakingly slow and convergence is difficult to assess. As a result, statistical inference is greatly hampered by computational constraints. However, for a given statistical model, different users, even with different data, are likely to perform similar computations. Computations done by one user are potentially useful for other users with different data sets. We propose a pooling of resources across researchers to capitalize on this. More specifically, we preemptively chart out the entire space of possible model outcomes in a prepaid database. Using advanced interpolation techniques, any individual estimation problem can now be solved on the spot. The prepaid method can easily accommodate different priors as well as constraints on the parameters. We created prepaid databases for three challenging models and demonstrate how they can be distributed through an online parameter estimation service. Our method outperforms state-of-the-art estimation techniques in both speed (with a 23,000 to 100,000-fold speed up) and accuracy, and is able to handle previously quasi inestimable models.https://doi.org/10.1371/journal.pcbi.1007181 |
| spellingShingle | Merijn Mestdagh Stijn Verdonck Kristof Meers Tim Loossens Francis Tuerlinckx Prepaid parameter estimation without likelihoods. PLoS Computational Biology |
| title | Prepaid parameter estimation without likelihoods. |
| title_full | Prepaid parameter estimation without likelihoods. |
| title_fullStr | Prepaid parameter estimation without likelihoods. |
| title_full_unstemmed | Prepaid parameter estimation without likelihoods. |
| title_short | Prepaid parameter estimation without likelihoods. |
| title_sort | prepaid parameter estimation without likelihoods |
| url | https://doi.org/10.1371/journal.pcbi.1007181 |
| work_keys_str_mv | AT merijnmestdagh prepaidparameterestimationwithoutlikelihoods AT stijnverdonck prepaidparameterestimationwithoutlikelihoods AT kristofmeers prepaidparameterestimationwithoutlikelihoods AT timloossens prepaidparameterestimationwithoutlikelihoods AT francistuerlinckx prepaidparameterestimationwithoutlikelihoods |