Counting unreported abortions: A binomial-thinned zero-inflated Poisson model
<b>Background</b>: Self-reported counts of intentional abortions in demographic surveys are significantly lower than the actual counts. To estimate the extent of misreporting, previous research has required either a gold standard or a validation sample. However, in most cases, a gold sta...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Max Planck Institute for Demographic Research
2017-01-01
|
| Series: | Demographic Research |
| Online Access: | https://www.demographic-research.org/volumes/vol36/2/ |
| _version_ | 1819237219184934912 |
|---|---|
| author | Vidhura Tennekoon |
| author_facet | Vidhura Tennekoon |
| author_sort | Vidhura Tennekoon |
| collection | DOAJ |
| description | <b>Background</b>: Self-reported counts of intentional abortions in demographic surveys are significantly lower than the actual counts. To estimate the extent of misreporting, previous research has required either a gold standard or a validation sample. However, in most cases, a gold standard or a validation sample is not available. <b>Objective</b>: Our main intention here is to show that a researcher has an alternative tool to estimate the extent of underreporting in a given dataset, particularly when neither a valid gold standard nor a validation sample is available. <b>Methods</b>: We adopt a binomial-thinned zero-inflated Poisson model and apply it to a sample dataset, the National Survey of Family Growth (NSFG), for which an alternative estimate of the average reporting rate (38Š) is available. We show how this model could be used to estimate the reporting probabilities of intentional abortions by each individual in addition to the overall average reporting rate. <b>Results</b>: Our model estimates the average reporting rate in the NSFG during 2006‒2013 as 35.3Š (SE 8.2Š). Individual reporting probabilities vary significantly. <b>Conclusions</b>: Our estimate of the average reporting rate of the dataset used is qualitatively and statistically similar to the available alternative estimate. <b>Contribution</b>: The model we propose can be used to predict the reporting probability of abortions of each individual, which in turn can be used to correct the bias due to underreporting in any model in which the number of abortions is used as the dependent variable or as one of the covariates. |
| first_indexed | 2024-12-23T13:16:51Z |
| format | Article |
| id | doaj.art-54297014206a4f1d976a4a3a7587e799 |
| institution | Directory Open Access Journal |
| issn | 1435-9871 |
| language | English |
| last_indexed | 2024-12-23T13:16:51Z |
| publishDate | 2017-01-01 |
| publisher | Max Planck Institute for Demographic Research |
| record_format | Article |
| series | Demographic Research |
| spelling | doaj.art-54297014206a4f1d976a4a3a7587e7992022-12-21T17:45:35ZengMax Planck Institute for Demographic ResearchDemographic Research1435-98712017-01-0136210.4054/DemRes.2017.36.22943Counting unreported abortions: A binomial-thinned zero-inflated Poisson modelVidhura Tennekoon0Indiana University - Purdue University Indianapolis<b>Background</b>: Self-reported counts of intentional abortions in demographic surveys are significantly lower than the actual counts. To estimate the extent of misreporting, previous research has required either a gold standard or a validation sample. However, in most cases, a gold standard or a validation sample is not available. <b>Objective</b>: Our main intention here is to show that a researcher has an alternative tool to estimate the extent of underreporting in a given dataset, particularly when neither a valid gold standard nor a validation sample is available. <b>Methods</b>: We adopt a binomial-thinned zero-inflated Poisson model and apply it to a sample dataset, the National Survey of Family Growth (NSFG), for which an alternative estimate of the average reporting rate (38Š) is available. We show how this model could be used to estimate the reporting probabilities of intentional abortions by each individual in addition to the overall average reporting rate. <b>Results</b>: Our model estimates the average reporting rate in the NSFG during 2006‒2013 as 35.3Š (SE 8.2Š). Individual reporting probabilities vary significantly. <b>Conclusions</b>: Our estimate of the average reporting rate of the dataset used is qualitatively and statistically similar to the available alternative estimate. <b>Contribution</b>: The model we propose can be used to predict the reporting probability of abortions of each individual, which in turn can be used to correct the bias due to underreporting in any model in which the number of abortions is used as the dependent variable or as one of the covariates.https://www.demographic-research.org/volumes/vol36/2/ |
| spellingShingle | Vidhura Tennekoon Counting unreported abortions: A binomial-thinned zero-inflated Poisson model Demographic Research |
| title | Counting unreported abortions: A binomial-thinned zero-inflated Poisson model |
| title_full | Counting unreported abortions: A binomial-thinned zero-inflated Poisson model |
| title_fullStr | Counting unreported abortions: A binomial-thinned zero-inflated Poisson model |
| title_full_unstemmed | Counting unreported abortions: A binomial-thinned zero-inflated Poisson model |
| title_short | Counting unreported abortions: A binomial-thinned zero-inflated Poisson model |
| title_sort | counting unreported abortions a binomial thinned zero inflated poisson model |
| url | https://www.demographic-research.org/volumes/vol36/2/ |
| work_keys_str_mv | AT vidhuratennekoon countingunreportedabortionsabinomialthinnedzeroinflatedpoissonmodel |