Keyword search

The purpose of this report is to provide an overview of existing methods and techniques making use of personal identifiers to support record linkage. Record linkage can be loosely defined as a methodology for manipulating and / or transforming personal identifiers from individual data records from one or more operational databases and subsequently attempting to match these personal identifiers to create a composite record about an individual. Record linkage is not intended to uniquely identify individuals for operational purposes; however, it does provide probabilistic matches of varying degrees of reliability for use in statistical reporting. Techniques employed in record linkage may also be of use for investigative purposes to help narrow the field of search against existing databases when some form of personal identification information exists.

In 1999, as part of its General Social Survey program, Statistics Canada conducted a survey on victimization and public perceptions of crime and the justice system. It was the third time that the General Social Survey (GSS) had examined victimization - previous surveys were conducted in 1993 and 1988.

For the 1999 survey, interviews were conducted by telephone with approximately 26,000 people, aged 15 and older, living in the 10 provinces. Respondents were asked for their opinions concerning the level of crime in their neighbourhood, their fear of crime and their views concerning the performance of the justice system. They were also asked about their attitudes toward sentencing adult and young offenders. Respondents were randomly presented with one of four hypothetical situations for which they were asked to choose "prison" or "non-prison". Respondents who selected prison sentences were given a follow-up question that asked them whether a sentence of one year of probation and 200 hours of community work was an acceptable alternative to the prison sentence.

This Juristat examines public attitudes toward sentencing adult and young offenders. It also analyzes public attitudes toward four sectors of the justice system including, the police, the criminal courts, the prison and parole systems.

This article examines whether the education levels of graduates surpass the needs of employers, and to what extent.

This article provides an analysis of the employment and earnings patterns of recent postsecondary graduates, based on three waves of the National Graduates Surveys.

This Juristat outlines the characteristics of criminal harassment incidents as well as the characteristics of the accused and victim for 1999, and identifies trends over the past five years. (Trend data are only available for the five-year period from 1995 to 1999.) This Juristat updates a similar Juristat written in 1996 using information collected from police forces and adult criminal courts to review the charges laid and sentences imposed for cases involving criminal harassment.

There are many different types of stalkers. However, most victims of criminal harassment know their accused quite well and, in many instances, the stalker and victim were involved in a previous relationship.

Statistics Canada publishes several measures of farm income, each produced for a different purpose. This bulletin describes the concepts behind these different measures, the methods by which the measures are constructed, and the uses for which they were designed.

Canada's ports handled a record 382.0 million tonnes (Mt.) of cargo in 1999 and a record of 2.2 million TEURS (twenty-foot-equivalent units) of containers.

Third quarter 1999 operating ratios for top carriers improved by one point over the same period one year earlier to 0.93 but were unchanged in the fourth quarter (0.94). Average revenue per carrier grew by 3% in the third quarter and 4% in the fourth quarter.

This study looks at those who voluntarily work part time, as well as their reasons for doing so, their levels of work-related stress, and their job characteristics.

This Bulletin provides recent information on the performance and funding of Federal Government Expenditures on Scientific Activities, 2000-2001. The statistics presented are derived from the survey of the science and technology (S&T) activities of Federal departments and agencies. According to international convention, S&T is divided into two fields; Natural Sciences and Engineering (NSE) and Social Sciences and Humanities (SSH). These fields of science are further divided into Research and Development (R&D) and Related Scientific Activities (RSA).

The publication provides principal statistics of the logging industry including number of establishments, number of employees, salaries and wages, cost of fuel and electricity, cost of materials, value of shipments and value added. It also presents commodity detail by province on inputs and outputs and estimates of total forest production, by products and by province. A data analysis, definitions and notes, a bibliography and a list of establishments by province are also included.

Montreal-Toronto was the top domestic market in 1998 for passengers on scheduled flights, followed by the Toronto-Vancouver market. Toronto-Vancouver was the top market for passengers on charter flights, followed by the Montreal-Toronto market.

Text Table 2.1 shows the change in the relationship between passenger counts and population for the ten most-frequented Canadian cities over the years 1973, 1993 and 1998.

Text Table 3.1 shows the relationship between passengers and population for each province and territory. In this table, passengers are assigned to each province/territory based on the ticket origin.

In this paper, the proportion of passengers flying within Canada that reach their destination on a direct flight is measured in order to assess the service that is offered by the carriers.

This on-line publication presents statistics and analysis on the volume of domestic air passenger traffic generated at Canadian cities and carried between pairs of Canadian points. The data may be used to indicate the relative community of interest between Canadian cities.

Revenues of private television broadcasters reached $1,862.9 in 1999, an increase of 2.2% from 1998. This increase is modest when compared to the two previous years where revenues grew 7.0% and 6.3% respectively. There was very little change in the relative importance of sources of revenues; the sale of air time accounted for 94.1% of revenues compared to 94.6% a year earlier.

To provide data users with a more complete picture of the activies associated with the Couriers and Local Messengers industry.

Revenues of private radio broadcasters reached $971.9 million in 1999, an increase of 3.2% from 1998. This increase is modest when compared to the two previous years where revenues rose 8.1% and 7.5% respectively.

Data on furniture and fixture industries clearly show the tremendous expansion period affecting these industries. Several establishments have taken advantage of the favourable economic conditions and the openness of North American markets to increase their deliveries to the United States. Foreign markets have been the driving force behind the furniture and fixture industries' growth in the past decade, since large establishments generally have more resources to break into these markets.

Richard Platek, the founding Chairman, who remained at the helm of the Journal until 1987, has provided an excellent overview of the gradual evolution of the Journal from a modest divisional to a respected departmental publication and then to an international publication of repute.

Dr. Fellegi considers the challenges facing government statistical agencies and strategies to prepare for these challenges. He first describes the environment of changing information needs and the social, economic and technological developments driving this change. He goes on to describe both internal and external elements of a strategy to meet these evolving needs. Internally, a flexible capacity for survey taking and information gathering must be developed. Externally, contacts must be developed to ensure continuing relevance of statistical programs while maintaining non-political objectivity.

Leslie Kish describes the challenges and opportunities of combining data from surveys of different populations. Examples include multinational surveys where the data from surveys of several countries are combined for comparison and analysis, as well as cumulated periodic surveys of the "same" population. He also compares and contrasts the combining of surveys with the combining of experiments.

In 1999 Statistics Sweden outlined a proposal for improved quality within the European Statistical System (ESS). The ESS comprises Eurostat and National Statistical Institutes (NSIs) associated with Eurostat. ... Basically Statistics Sweden proposed the creation of a LEG [Leadership Expert Group] on Quality].

In his paper Fritz Scheuren considers the possible uses of administrative records to enhance and improve population censuses. After reviewing previous uses of administrative records in an international context, he puts forward several proposals for research and development towards increased use of administrative records in the American statistical system.

Godambe and Thompson consider the problem of confidence intervals in survey sampling. They first review the use of estimating functions to obtain model robust pivotal quantities and associated confidence intervals, and then discuss the adaptation of this approach to the survey sampling context. Details are worked out for some more specific types of models, and an empirical comparison of this approach with more conventional methods is presented.

J.N.K. Rao gives an overview of the methods and models used for small area estimation. This is an update of his previous overview (Ghosh and Rao, 1994, Statistical Science). He first presents a general discussion of small area models, making a distinction between area level models and unit level models. He then describes the development in three main approaches for inference based on these models: EBLUP, EB and HB, gives several examples of recent applications. Finally, he presents an interesting discussion identifying the gaps and areas that require further research.

Sirken and Shimizu derive a Horvitz-Thompson estimator for population based establishment sample surveys (PBESs). A PBES is a survey of establishments where the sampling frame consists of establishments with which a preliminary sample of households or individuals has had some contact.

Jean-Claude Deville shows how to use simple tools to calculate the variance of a complex estimator using a linearization technique. The process is that of a software used at INSEE for estimation of the variance of a complex estimator. It gives a way of computing the variance of a total estimated by the simple expansion estimator. In the case of a complex statistic, the process uses a derived variable that reduces the computations to those of the simple expansion estimator. Multiple examples are given to illustrate the process.

Brewer proposes a method of weight calibration in survey sampling, called cosmetic calibration, which yields cosmetic estimators of totals, i.e. estimators that can be interpreted as both design-based and prediction based. He also discusses variance estimation and shows how the problem of negative weights can be easily and naturally handled using cosmetic calibration. Finally he compares the properties of the weights and the resulting estimators to some alternative approaches using some Australian far data.

Much work on probabilistic methods of linkage can be found in the statistical literature. However, although many groups undoubtedly still use deterministic procedures, not much literature is available on these strategies. Furthermore there appears to exist no documentation on the comparison of results for the two strategies. Such a comparison is pertinent in the situation where we have only non-unique identifiers like names, sex, race etc. as common identifiers on which the databases are to be linked. In this work we compare a stepwise deterministic linkage strategy with the probabilistic strategy, as implemented in AUTOMATCH, for such a situation. The comparison was carried out on a linkage between medical records from the Regional Perinatal Intensive Care Centers database and education records from the Florida Department of Education. Social security numbers, available in both databases, were used to decide the true status of the record pair after matching. Match rates and error rates for the two strategies are compared and a discussion of their similarities and differences, strengths and weaknesses is presented.

The fusion sample obtained by a statistical matching process can be considered a sample out of an artificial population. The distribution of this artificial population is derived. If the correlation between specific variables is the only focus the strong demand for conditional independence can be weakened. In a simulation study the effects of violations of some assumptions leading to the distribution of the artificial population are examined. Finally some ideas concerning the establishing of the claimed conditional independence by latent class analysis are presented.

Following the problems with estimating underenumeration in the 1991 Census of England and Wales the aim for the 2001 Census is to create a database that is fully adjusted to net underenumeration. To achieve this, the paper investigates weighted donor imputation methodology that utilises information from both the census and census coverage survey (CCS). The US Census Bureau has considered a similar approach for their 2000 Census (see Isaki et al 1998). The proposed procedure distinguishes between individuals who are not counted by the census because their household is missed and those who are missed in counted households. Census data is linked to data from the CCS. Multinomial logistic regression is used to estimate the probabilities that households are missed by the census and the probabilities that individuals are missed in counted households. Household and individual coverage weights are constructed from the estimated probabilities and these feed into the donor imputation procedure.

To reach their target audience efficiently, advertisers and media planners need information on which media their customers use. For instance, they may need to know what percentage of Diet Coke drinkers watch Baywatch, or how many AT&T customers have seen an advertisement for Sprint during the last week. All the relevant data could theoretically be collected from each respondent. However, obtaining full detailed and accurate information would be very expensive. It would also impose a heavy respondent burden under current data collection technology. This information is currently collected through separate surveys in New Zealand and in many other countries. Exposure to the major media is measured continuously, and product usage studies are common. Statistical matching techniques provide a way of combining these separate information sources. The New Zealand television ratings database was combined with a syndicated survey of print readership and product usage, using statistical matching. The resulting Panorama service meets the targeting information needs of advertisers and media planners. It has since been duplicated in Australia. This paper discusses the development of the statistical matching framework for combining these databases, and the heuristics and techniques used. These included an experiment conducted using a screening design to identify important matching variables. Studies evaluating and validating the combined results are also summarized. The following three major evaluation criteria were used; accuracy of combined results, statibility of combined results and the preservation of currency results from the component databases. The paper then discusses how the prerequisites for combining the databases were met. The biggest hurdle at this stage was the differences between the analysis techniques used on the two component databases. Finally, suggestions for developing similar statistical matching systems elsewhere will be given.

Data fusion as discussed here means to create a set of data on not jointly observed variables from two different sources. Suppose for instance that observations are available for (X,Z) on a set of individuals and for (Y,Z) on a different set of individuals. Each of X, Y and Z may be a vector variable. The main purpose is to gain insight into the joint distribution of (X,Y) using Z as a so-called matching variable. At first however, it is attempted to recover as much information as possible on the joint distribution of (X,Y,Z) from the distinct sets of data. Such fusions can only be done at the cost of implementing some distributional properties for the fused data. These are conditional independencies given the matching variables. Fused data are typically discussed from the point of view of how appropriate this underlying assumption is. Here we give a different perspective. We formulate the problem as follows: how can distributions be estimated in situations when only observations from certain marginal distributions are available. It can be solved by applying the maximum entropy criterium. We show in particular that data created by fusing different sources can be interpreted as a special case of this situation. Thus, we derive the needed assumption of conditional independence as a consequence of the type of data available.

The effect of the environment on health is of increasing concern, in particular the effects of the release of industrial pollutants into the air, the ground and into water. An assessment of the risks to public health of any particular pollution source is often made using the routine health, demographic and environmental data collected by government agencies. These datasets have important differences in sampling geography and in sampling epochs which affect the epidemiological analyses which draw them together. In the UK, health events are recorded for individuals, giving cause codes, a data of diagnosis or death, and using the unit postcode as a geographical reference. In contrast, small area demographic data are recorded only at the decennial census, and released as area level data in areas distinct from postcode geography. Environmental exposure data may be available at yet another resolution, depending on the type of exposure and the source of the measurements.

As the population ages, a greater demand for long-term care services and, in particular, nursing homes is expected. Policy analysts continue to search for alternative, less costly forms of care for the elderly and have attempted to develop programs to delay or prevent nursing-home entry. Health care administrators required information for planning the future demand for nursing-home services. This study assesses the relative importance of predisposing, enabling, and need characteristics in predicting and understanding nursing-home entry.

A population needs-based health care resource allocation model was developed and applied using age, sex and health status of populations to measure population need for health care in Ontario. To develop the model, provincial data on self-assessed health and health service utilization by age and sex from 62,413 respondents to the 1990 Ontario Health Survey (OHS) were used in combination with provincial health care expenditure data for the fiscal year 1995/96 by age and sex. The model was limited to the services that were covered in the OHS (general practitioner, specialist physician, optometry, physiotherapy, chiropractic and acute hospital). The distribution of utilization and expenditures between age-sex-health status categories was used to establish appropriate health care resource shares for each age-sex-health status combination. These resource shares were then applied to geographic populations using age, sex and health status data from the OHS together with more recent population estimates to determine the needs-based health care resource allocation for each area. Total dollar allocations were restricted to sum to the 1995/96 provincial budget and were compared with 1995/96 allocations to determine the extent to which Ontario allocations are consistent with the relative needs of the area populations.

To augment the amount of available information, data from different sources are increasingly being combined. These databases are often combined using record linkage methods. When there is no unique identifier, a probabilistic linkage is used. In that case, a record on a first file is associated with a probability that is linked to a record on a second file, and then a decision is taken on whether a possible link is a true link or not. This usually requires a non-negligible amount of manual resolution. It might then be legitimate to evaluate if manual resolution can be reduced or even eliminated. This issue is addressed in this paper where one tries to produce an estimate of a total (or a mean) of one population, when using a sample selected from another population linked somehow to the first population. In other words, having two populations linked through probabilistic record linkage, we try to avoid any decision concerning the validity of links and still be able to produce an unbiased estimate for a total of the one of two populations. To achieve this goal, we suggest the use of the Generalised Weight Share Method (GWSM) described by Lavallée (1995).

The application of dual system estimation (DSE) to matched Census / Post Enumeration Survey (PES) data in order to measure net undercount is well understood (Hogan, 1993). However, this approach has so far not been used to measure net undercount in the UK. The 2001 PES in the UK will use this methodology. This paper presents the general approach to design and estimation for this PES (the 2001 Census Coverage Survey). The estimation combines DSE with standard ratio and regression estimation. A simulation study using census data from the 1991 Census of England and Wales demonstrates that the ratio model is in general more robust than the regression model.