Analysis

Description: At Statistics Canada, many data sets are linked with quasi-identifiers such as the first name, last name, or address. In such cases, linkage errors are a potential concern and must be measured. In that regard, previous studies have shown that the evaluation may be based on modeling the number of links from a given record while accounting for all the interactions among the linkage variables and dispensing with clerical reviews, so long as the decision to link two records does not involve other records. In this communication, the methodology is adapted for a class of practical strategies, which violate this constraint by linking the records in consecutive waves, where a given wave links a subset of the records that are not linked in previous waves. In particular, the linkage may be based on a deterministic wave followed by a probabilistic one.

Description: The capture-recapture method can be applied to measure the coverage of administrative and big data sources, in official statistics. In its basic form, it involves the linkage of two sources while assuming a perfect linkage and other standard assumptions. In practice, linkage errors arise and are a potential source of bias, where the linkage is based on quasi-identifiers. These errors include false positives and false negatives, where the former arise when linking a pair of records from different units, and the latter arise when not linking a pair of records from the same unit. So far, the existing solutions have resorted to costly clerical reviews, or they have made the restrictive conditional independence assumption. In this work, these requirements are relaxed by modeling the number of links from a record instead. The same approach may be taken to estimate the linkage accuracy without clerical reviews, when linking two sources that each have some undercoverage.

Description:

When linking massive data sets, blocking is used to select a manageable subset of record pairs at the expense of losing a few matched pairs. This loss is an important component of the overall linkage error, because blocking decisions are made early on in the linkage process, with no way to revise them in subsequent steps. Yet, measuring this contribution is still a major challenge because of the need to model all the pairs in the Cartesian product of the sources, not just those satisfying the blocking criteria. Unfortunately, previous error models are of little use because they typically do not meet this requirement. This paper addresses the issue with a new finite mixture model, which dispenses with clerical reviews, training data, or the assumption that the linkage variables are conditionally independent. It applies when applying a standard blocking procedure for the linkage of a file to a register or a census with complete coverage, where both sources are free of duplicate records.

Description:

Non-probability samples are being increasingly explored by National Statistical Offices as a complement to probability samples. We consider the scenario where the variable of interest and auxiliary variables are observed in both a probability and non-probability sample. Our objective is to use data from the non-probability sample to improve the efficiency of survey-weighted estimates obtained from the probability sample. Recently, Sakshaug, Wisniowski, Ruiz and Blom (2019) and Wisniowski, Sakshaug, Ruiz and Blom (2020) proposed a Bayesian approach to integrating data from both samples for the estimation of model parameters. In their approach, non-probability sample data are used to determine the prior distribution of model parameters, and the posterior distribution is obtained under the assumption that the probability sampling design is ignorable (or not informative). We extend this Bayesian approach to the prediction of finite population parameters under non-ignorable (or informative) sampling by conditioning on appropriate survey-weighted statistics. We illustrate the properties of our predictor through a simulation study.

Key Words: Bayesian prediction; Gibbs sampling; Non-ignorable sampling; Statistical data integration.

Description:

In the context of its "admin-first" paradigm, Statistics Canada is prioritizing the use of non-survey sources to produce official statistics. This paradigm critically relies on non-survey sources that may have a nearly perfect coverage of some target populations, including administrative files or big data sources. Yet, this coverage must be measured, e.g., by applying the capture-recapture method, where they are compared to other sources with good coverage of the same populations, including a census. However, this is a challenging exercise in the presence of linkage errors, which arise inevitably when the linkage is based on quasi-identifiers, as is typically the case. To address the issue, a new methodology is described where the capture-recapture method is enhanced with a new error model that is based on the number of links adjacent to a given record. It is applied in an experiment with public census data.

Key Words: dual system estimation, data matching, record linkage, quality, data integration, big data.

Description:

This study describes record linkage of the Canadian Community Health Survey and the Canadian Mortality Database. The article explains the record linkage process and presents results about associations between health behaviours and mortality among a representative sample of Canadians.

Description:

Probabilistic linkage is susceptible to linkage errors such as false positives and false negatives. In many cases, these errors may be reliably measured through clerical-reviews, i.e. the visual inspection of a sample of record pairs to determine if they are matched. A framework is described to effectively carry-out such clerical-reviews based on a probabilistic sample of pairs, repeated independent reviews of the same pairs and latent class analysis to account for clerical errors.

Description:

Exact record linkage is an essential tool for exploiting administrative files, especially when one is studying the relationships among many variables that are not contained in a single administrative file. It is aimed at identifying pairs of records associated with the same individual or entity. The result is a linked file that may be used to estimate population parameters including totals and ratios. Unfortunately, the linkage process is complex and error-prone because it usually relies on linkage variables that are non-unique and recorded with errors. As a result, the linked file contains linkage errors, including bad links between unrelated records, and missing links between related records. These errors may lead to biased estimators when they are ignored in the estimation process. Previous work in this area has accounted for these errors using assumptions about their distribution. In general, the assumed distribution is in fact a very coarse approximation of the true distribution because the linkage process is inherently complex. Consequently, the resulting estimators may be subject to bias. A new methodological framework, grounded in traditional survey sampling, is proposed for obtaining design-based estimators from linked administrative files. It consists of three steps. First, a probabilistic sample of record-pairs is selected. Second, a manual review is carried out for all sampled pairs. Finally, design-based estimators are computed based on the review results. This methodology leads to estimators with a design-based sampling error, even when the process is solely based on two administrative files. It departs from the previous work that is model-based, and provides more robust estimators. This result is achieved by placing manual reviews at the center of the estimation process. Effectively using manual reviews is crucial because they are a de-facto gold-standard regarding the quality of linkage decisions. The proposed framework may also be applied when estimating from linked administrative and survey data.

Description: At Statistics Canada, many data sets are linked with quasi-identifiers such as the first name, last name, or address. In such cases, linkage errors are a potential concern and must be measured. In that regard, previous studies have shown that the evaluation may be based on modeling the number of links from a given record while accounting for all the interactions among the linkage variables and dispensing with clerical reviews, so long as the decision to link two records does not involve other records. In this communication, the methodology is adapted for a class of practical strategies, which violate this constraint by linking the records in consecutive waves, where a given wave links a subset of the records that are not linked in previous waves. In particular, the linkage may be based on a deterministic wave followed by a probabilistic one.

Description: The capture-recapture method can be applied to measure the coverage of administrative and big data sources, in official statistics. In its basic form, it involves the linkage of two sources while assuming a perfect linkage and other standard assumptions. In practice, linkage errors arise and are a potential source of bias, where the linkage is based on quasi-identifiers. These errors include false positives and false negatives, where the former arise when linking a pair of records from different units, and the latter arise when not linking a pair of records from the same unit. So far, the existing solutions have resorted to costly clerical reviews, or they have made the restrictive conditional independence assumption. In this work, these requirements are relaxed by modeling the number of links from a record instead. The same approach may be taken to estimate the linkage accuracy without clerical reviews, when linking two sources that each have some undercoverage.

Description:

When linking massive data sets, blocking is used to select a manageable subset of record pairs at the expense of losing a few matched pairs. This loss is an important component of the overall linkage error, because blocking decisions are made early on in the linkage process, with no way to revise them in subsequent steps. Yet, measuring this contribution is still a major challenge because of the need to model all the pairs in the Cartesian product of the sources, not just those satisfying the blocking criteria. Unfortunately, previous error models are of little use because they typically do not meet this requirement. This paper addresses the issue with a new finite mixture model, which dispenses with clerical reviews, training data, or the assumption that the linkage variables are conditionally independent. It applies when applying a standard blocking procedure for the linkage of a file to a register or a census with complete coverage, where both sources are free of duplicate records.

Description:

Non-probability samples are being increasingly explored by National Statistical Offices as a complement to probability samples. We consider the scenario where the variable of interest and auxiliary variables are observed in both a probability and non-probability sample. Our objective is to use data from the non-probability sample to improve the efficiency of survey-weighted estimates obtained from the probability sample. Recently, Sakshaug, Wisniowski, Ruiz and Blom (2019) and Wisniowski, Sakshaug, Ruiz and Blom (2020) proposed a Bayesian approach to integrating data from both samples for the estimation of model parameters. In their approach, non-probability sample data are used to determine the prior distribution of model parameters, and the posterior distribution is obtained under the assumption that the probability sampling design is ignorable (or not informative). We extend this Bayesian approach to the prediction of finite population parameters under non-ignorable (or informative) sampling by conditioning on appropriate survey-weighted statistics. We illustrate the properties of our predictor through a simulation study.

Key Words: Bayesian prediction; Gibbs sampling; Non-ignorable sampling; Statistical data integration.

Description:

In the context of its "admin-first" paradigm, Statistics Canada is prioritizing the use of non-survey sources to produce official statistics. This paradigm critically relies on non-survey sources that may have a nearly perfect coverage of some target populations, including administrative files or big data sources. Yet, this coverage must be measured, e.g., by applying the capture-recapture method, where they are compared to other sources with good coverage of the same populations, including a census. However, this is a challenging exercise in the presence of linkage errors, which arise inevitably when the linkage is based on quasi-identifiers, as is typically the case. To address the issue, a new methodology is described where the capture-recapture method is enhanced with a new error model that is based on the number of links adjacent to a given record. It is applied in an experiment with public census data.

Key Words: dual system estimation, data matching, record linkage, quality, data integration, big data.

Description:

This study describes record linkage of the Canadian Community Health Survey and the Canadian Mortality Database. The article explains the record linkage process and presents results about associations between health behaviours and mortality among a representative sample of Canadians.

Description:

Probabilistic linkage is susceptible to linkage errors such as false positives and false negatives. In many cases, these errors may be reliably measured through clerical-reviews, i.e. the visual inspection of a sample of record pairs to determine if they are matched. A framework is described to effectively carry-out such clerical-reviews based on a probabilistic sample of pairs, repeated independent reviews of the same pairs and latent class analysis to account for clerical errors.

Description:

Exact record linkage is an essential tool for exploiting administrative files, especially when one is studying the relationships among many variables that are not contained in a single administrative file. It is aimed at identifying pairs of records associated with the same individual or entity. The result is a linked file that may be used to estimate population parameters including totals and ratios. Unfortunately, the linkage process is complex and error-prone because it usually relies on linkage variables that are non-unique and recorded with errors. As a result, the linked file contains linkage errors, including bad links between unrelated records, and missing links between related records. These errors may lead to biased estimators when they are ignored in the estimation process. Previous work in this area has accounted for these errors using assumptions about their distribution. In general, the assumed distribution is in fact a very coarse approximation of the true distribution because the linkage process is inherently complex. Consequently, the resulting estimators may be subject to bias. A new methodological framework, grounded in traditional survey sampling, is proposed for obtaining design-based estimators from linked administrative files. It consists of three steps. First, a probabilistic sample of record-pairs is selected. Second, a manual review is carried out for all sampled pairs. Finally, design-based estimators are computed based on the review results. This methodology leads to estimators with a design-based sampling error, even when the process is solely based on two administrative files. It departs from the previous work that is model-based, and provides more robust estimators. This result is achieved by placing manual reviews at the center of the estimation process. Effectively using manual reviews is crucial because they are a de-facto gold-standard regarding the quality of linkage decisions. The proposed framework may also be applied when estimating from linked administrative and survey data.