Analysis

Description:

Nearly all surveys use complex sampling designs to collect data and these data are frequently used for statistical analyses beyond the estimation of simple descriptive parameters of the target population. Many procedures available in popular statistical software packages are not appropriate for this purpose because the analyses are based on the assumption that the sample has been drawn with simple random sampling. Therefore, the results of the analyses conducted using these software packages would not be valid when the sample design incorporates multistage sampling, stratification, or clustering. Two commonly used methods for analysing data from complex surveys are replication and Taylor linearization techniques. We discuss the use of WESVAR software to compute estimates and replicate variance estimates by properly reflecting complex sampling and estimation procedures. We also illustrate the WESVAR features by using data from two Westat surveys that employ complex survey designs: the Third International Mathematics and Science Study (TIMSS) and the National Health and Nutrition Examination Survey (NHANES).

Description:

For most survey samples, if not all, we have to deal with the problem of missing values. Missing values are usually caused by nonresponse (such as refusal of participant or interviewer was unable to contact respondent) but can also be produced at the editing step of the survey in an attempt to resolve problems of inconsistent or suspect responses. The presence of missing values (nonresponse) generally leads to bias and uncertainty in the estimates. To treat this problem, the appropriate use of all available auxiliary information permits the maximum reduction of nonresponse bias and variance. During this presentation, we will define the problem, describe the methodology that SEVANI is based on and discuss potential uses of the system. We will end the discussion by presenting some examples based on real data to illustrate the theory in practice.

In practice, it is very difficult to estimate the nonresponse bias. However, it is possible to estimate the nonresponse variance by assuming that the bias is negligible. In the last decade, many methods were indeed proposed to estimate this variance, and some of these have been implemented in the System for Estimation of Variance due to Nonresponse and Imputation (SEVANI).

The methodology used to develop SEVANI is based on the theory of two-phase sampling where we assume that the second phase of selection is nonresponse. However, contrary to two-phase sampling, an imputation or nonresponse model is required for variance estimation. SEVANI also assumes that nonresponse is treated by reweighting respondent units or by imputing their missing values. Three imputation methods are considered: the imputation of an auxiliary variable, regression imputation (deterministic or random) and nearest-neighbour imputation.

Description:

A wide class of models of interest in social and economic research can be represented by specifying a parametric structure for the covariances of observed variables. The availability of software, such as LISREL (Jöreskog and Sörbom 1988) and EQS (Bentler 1995), has enabled these models to be fitted to survey data in many applications. In this paper, we consider approaches to inference about such models using survey data derived by complex sampling schemes. We consider evidence of finite sample biases in parameter estimation and ways to reduce such biases (Altonji and Segal 1996) and associated issues of efficiency of estimation, standard error estimation and testing. We use longitudinal data from the British Household Panel Survey for illustration. As these data are subject to attrition, we also consider the issue of how to use nonresponse weights in the modelling.

Description:

Behavioural researchers use a variety of techniques to predict respondent scores on constructs that are not directly observable. Examples of such constructs include job satisfaction, work stress, aptitude for graduate study, children's mathematical ability, etc. The techniques commonly used for modelling and predicting scores on such constructs include factor analysis, classical psychometric scaling and item response theory (IRT), and for each technique there are often several different strategies that can be used to generate individual scores. However, researchers are seldom satisfied with simply measuring these constructs. They typically use the derived scores in multiple regression, analysis of variance and numerous multivariate procedures. Though using predicted scores in this way can result in biased estimates of model parameters, not all researchers are aware of this difficulty. The paper will review the literature on this issue, with particular emphasis on IRT methods. Problems will be illustrated, some remedies suggested, and areas for further research will be identified.

Description:

Analysis of dose-response relationships has long been important in toxicology. More recently, this type of analysis has been employed to evaluate public education campaigns. The data that are collected in such evaluations are likely to come from standard household survey designs with all the usual complexities of multiple stages, stratification and variable selection probabilities. On a recent evaluation, a system was developed with the following features: categorization of doses into three or four levels, propensity scoring of dose selection and a new jack-knifed Jonckheere-Terpstra test for a monotone dose-response relationship. This system allows rapid production of tests for monotone dose-response relationships that are corrected both for sample design and for confounding. The focus of this paper will be the results of a Monte-Carlo simulation of the properties of the jack-knifed Jonckheere-Terpstra.

Moreover, there is no experimental control over dosages and the possibility of confounding variables must be considered. Standard regressions in WESVAR and SUDAAN could be used to determine if there is a linear dose-response relationship while controlling on confounders, but such an approach obviously has low power to detect nonlinear but monotone dose-response relationships and is time-consuming to implement if there are a large number of possible outcomes of interest.

Description:

While censuses and surveys are often said to measure populations as they are, most reflect information about individuals as they were at the time of measurement, or even at some prior time point. Inferences from such data therefore should take into account change over time at both the population and individual levels. In this paper, we provide a unifying framework for such inference problems, illustrating it through a diverse series of examples including: (1) estimating residency status on Census Day using multiple administrative records, (2) combining administrative records for estimating the size of the US population, (3) using rolling averages from the American Community Survey, and (4) estimating the prevalence of human rights abuses.

Specifically, at the population level, the estimands of interest, such as the size or mean characteristics of a population, might be changing. At the same time, individual subjects might be moving in and out of the frame of the study or changing their characteristics. Such changes over time can affect statistical studies of government data that combine information from multiple data sources, including censuses, surveys and administrative records, an increasingly common practice. Inferences from the resulting merged databases often depend heavily on specific choices made in combining, editing and analysing the data that reflect assumptions about how populations of interest change or remain stable over time.

Description:

According to recent literature, the calibration method has gained much popularity on survey sampling and calibration estimators are routinely computed by many survey organizations. The choice of calibration variables for all existing approaches, however, remains ad hoc. In this article, we show that the model-calibration estimator for the finite population mean, which was proposed by Wu and Sitter (2001) through an intuitive argument, is indeed optimal among a class of calibration estimators. We further present optimal calibration estimators for the finite population distribution function, the population variance, variance of a linear estimator and other quadratic finite population functions under a unified framework. A limited simulation study shows that the improvement of these optimal estimators over the conventional ones can be substantial. The question of when and how auxiliary information can be used for both the estimation of the population mean using a generalized regression estimator and the estimation of its variance through calibration is addressed clearly under the proposed general methodology. Constructions of proposed estimators under two-phase sampling and some fundamental issues in using auxiliary information from survey data are also addressed under the context of optimal estimation.

Description:

In the 2001 Canadian Census of Population, calibration or regression estimation was used to calculate a single set of household level weights to be used for all census estimates based on a one in five national sample of more than two million households. Because many auxiliary variables were available, only a subset of them could be used. Otherwise, some of the weights would have been smaller than the number one or even negative. In this technical paper, a forward selection procedure was used to discard auxiliary variables that caused weights to be smaller than one or that caused a large condition number for the calibration weight matrix being inverted. Also, two calibration adjustments were done to achieve close agreement between auxiliary population counts and estimates for small areas. Prior to 2001, the projection generalized regression (GREG) estimator was used and the weights were required to be greater than zero. For the 2001 Census, a switch was made to a pseudo-optimal regression estimator that kept more auxiliary variables and, at the same time, required that the weights be one or more.

Description:

The US Census Bureau supports research into an optimal design program as an alternative to its current decennial redesign of demographic surveys. The optimal design program seeks to optimize redesign samples annually and reduce deterioration of the precision of survey estimates.

Initial research has focussed on the use of multi-agent systems (also known as distributed artificial intelligence) to produce optimal annual samples for all demographic surveys. The first multi-agent system optimizes redesign inputs. It represents each housing unit as an autonomous agent and solves the distributed constrain satisfaction problem (DCSP) to forecast household characteristics that are consistent with recent survey data and estimates. The second multi-agent system selects optimal samples for all demographic surveys. It represents each survey-state pair as a deliberative agent and applies the Bayesian optimization algorithm (BOA) at each design stage to partition the sampling units into sample and non-sample subsets. Thus, sampling units are selected directly, without the need for initial stratification.

Description:

If the dataset available to machine learning results from cluster sampling (e.g., patients from a sample of hospital wards), the usual cross-validation error rate estimate can lead to biased and misleading results. In this technical paper, an adapted cross-validation is described for this case. Using a simulation, the sampling distribution of the generalization error rate estimate, under cluster or simple random sampling hypothesis, is compared with the true value. The results highlight the impact of the sampling design on inference: clearly, clustering has a significant impact; the repartition between learning set and test set should result from a random partition of the clusters, not from a random partition of the examples. With cluster sampling, standard cross-validation underestimates the generalization error rate, and is deficient for model selection. These results are illustrated with a real application of automatic identification of spoken language.

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: The infographic uses data from the integrated file of the Postsecondary Student Information System, the 2016 Census, the 2021 Census and the T1 Family File to compare the job quality of Indigenous graduates with a bachelor's degree with that of non-racialized and non-Indigenous graduates two years after graduation. Job quality indicators include employment income, unionization rate, and employer pension plan coverage rate.

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: This infographic provides details about the number of graduates and median employment income two years after graduation for international postsecondary students, by educational qualification and field of study.

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: Release published in The Daily – Statistics Canada’s official release bulletin

Description: This study examined the impact of federal business innovation and growth support (BIGS) programs on firm financial performance measured using revenue, profit and employment metrics. Using Statistics Canada’s Business Linkable File Environment data, the study observed the effects of BIGS on exporting versus non-exporting firms and Canadian- versus U.S.-owned firms from 2015 to 2020. Unlike previous studies that relied mainly on survey data, one significant aspect of this research was the use of a new dataset, enabling panel data structures and models to be employed. To assess the impact of BIGS and research and development spending on three interrelated measures of firm financial performance, the CDM (Crépon et al., 1998) framework was adopted.

Description: This article provides perspectives on the extent to which recent changes in gross domestic product per capita represent a departure from their long-term trend and discusses factors that have facilitated per capita growth in previous decades.

Description: Many seniors work past their mid-60s for various reasons. Some find it necessary to keep working because of inadequate retirement savings, mortgage payments, unforeseen expenses, or the responsibility to support children and other family members in Canada or abroad. Others choose to work to provide a sense of personal fulfillment, stay active and remain engaged. This article uses data from the Labour Force Survey (LFS) and examines the degree to which Canadian-born and immigrant seniors aged 65 to 74 worked by choice or necessity in 2022.

Description: Since Canada is a vast country with diverse job opportunities available in various locations, some provinces and territories may face challenges and opportunities in retaining and attracting young skilled talent. This article is the first to inform the issue by determining the share of youth who grew up in a certain province or territory and eventually obtained a postsecondary education but left to work in another province or territory. The article also looks at young skilled workers who entered a province or territory to work, as a share of that province or territory’s initial population of homegrown young skilled labour.

Description: This article provides an integrated summary of recent changes in output, consumer prices, employment, and household finances. It highlights changes in the economic data during the second half of 2023 and into the winter months. The article also examines how economic conditions have changed as borrowing costs have risen.

Description: The participation of women-owned businesses in exports is important for policies aiming to ensure that the benefits of international trade reach all groups. Women-owned small and medium-sized enterprises (SMEs) in Canada are as likely to export as those owned by men, and their export intensity (exports as a share of total sales) was not significantly different. This article examines factors related to the exporting success of women-owned small and medium-sized enterprises in Canada.

Description: Social connections and relationships are important, yet often overlooked, indicators of well-being. For immigrants, these networks are also important for integration. This study examines how immigrant women’s sociodemographic characteristics and life-course circumstances are associated with the size and composition of their personal networks and provides comparisons with Canadian-born women.

Description: This study applies small area estimation (SAE) and a new geographic concept called Self-contained Labor Area (SLA) to the Canadian Survey on Business Conditions (CSBC) with a focus on remote work opportunities in rural labor markets. Through SAE modelling, we estimate the proportions of businesses, classified by general industrial sector (service providers and goods producers), that would primarily offer remote work opportunities to their workforce.

Description: The current study uses the 2011 National Household Survey and the 2016 and 2021 Censuses to provide data on the number of Indigenous foster children in private households, foster child rates, and disparity between Indigenous and non-Indigenous foster care rates between 2011 and 2021. Subsequently, select sociodemographic characteristics of Indigenous children in foster care and household characteristics are explored using the 2021 Census.

Description: Oral health is a crucial component of overall health, influencing both physical and mental well-being. Yet, despite the important role that access to and use of oral health care services play in maintaining optimal oral health, substantial disparities remain in access to oral health care services across population groups in Canada. Using data from the 2022 Canadian Community Health Survey, this study examines the association of dental insurance with oral health care access and use in Canada while accounting for income and sociodemographic factors. It contributes to a baseline of oral health care disparities before the implementation of the Canadian Dental Care Plan.

Description: Labour Statistics at a Glance features short analytical articles on specific topics of interest related to Canada's labour market. The studies examine recent or historical trends using data produced by the Centre for Labour Market Information, i.e., the Labour Force Survey, the Survey of Employment Payrolls and Hours, the Job Vacancy and Wage Survey, the Employment Insurance Coverage Survey and the Employment Insurance Statistics Program.

Description: The Health Research Working Paper Series publishes: analytical work-in-progress; background documentation for specific research projects (e.g methodological papers); lengthy reports intended for specific clients, and; compendiums of data tables. Publication in this series does not preclude publication of specific aspects of the work in a peer-reviewed journal.

Description: Environment fact sheets will include short, focused, single-theme analysis on key issues within the changing environment with regards to all Canadians. Over the course of the series, analysis will include topics on: air and climate, pollution and waste, environmental protection and quality, and natural resources.

Description: The ‘Eh Sayers’ podcast explores data of interest to Canadians, like social or news-worthy topics. It also aims to foster data literacy and deliver insight into the lives of Canadians by exploring the data the agency produces and tying it to real life situations through storytelling.

Description: This publication presents key highlights and results from the General Social Survey on the topics of caregiving and care receiving; social identity; giving, volunteering and participating; victimization; time use; and family.

Description: Statistics Canada produces videos that present key communications messages to multiple publics in an easy-to-understand way. As a communications tool, they make complex information and ideas easy to interpret by telling a visual story. Statistics Canada has videos on a variety of topics.

Description: The Canadian Survey on Disability (CSD) is a national survey of Canadians aged 15 and over whose everyday activities are limited because of a long-term condition or health-related problem.

Description: The newsletter offers information aimed at three main groups, businesses (small to medium), communities and ethno-cultural groups/communities. Articles and outreach materials will assist their understanding of national and local data from the many relevant sources found on the Statistics Canada website.

Description: This publication brings together and analyzes a wide range of data sources in order to provide information on various aspects of Canadian society, including labour, income, education, social, and demographic issues, that affect the lives of Canadians.

Description: This publication presents annual estimates of population for subprovincial areas of Canada, such as census metropolitan areas (CMAs), census agglomerations (CAs), economic regions (ERs) and census divisions (CDs). The following components of population change are also presented: births, deaths, immigration, emigration, returning emigration, net temporary emigration, net non-permanent residents and interprovincial and intraprovincial migration. The estimates are based on the most recent census of population results available at the time of publication, which have been adjusted for census net undercoverage (including adjustment for incompletely enumerated Indian reserves). This publication also contains highlights and an analysis of the most recent demographic trends, as well as a description of the concepts, methods and data quality of the estimates.