Analysis

Researchers and policy makers often use data from nationally representative probability sample surveys. The number of topics covered by such surveys, and hence the amount of interviewing time involved, have typically increased over the years, resulting in increased costs and respondent burden. A potential solution to this problem is to carefully form subsets of the items in a survey and administer one such subset to each respondent. Designs of this type are called "split-questionnaire" designs or "matrix sampling" designs. The administration of only a subset of the survey items to each respondent in a matrix sampling design creates what can be considered missing data. Multiple imputation (Rubin 1987), a general-purpose approach developed for handling data with missing values, is appealing for the analysis of data from a matrix sample, because once the multiple imputations are created, data analysts can apply standard methods for analyzing complete data from a sample survey. This paper develops and evaluates a method for creating matrix sampling forms, each form containing a subset of items to be administered to randomly selected respondents. The method can be applied in complex settings, including situations in which skip patterns are present. Forms are created in such a way that each form includes items that are predictive of the excluded items, so that subsequent analyses based on multiple imputation can recover some of the information about the excluded items that would have been collected had there been no matrix sampling. The matrix sampling and multiple-imputation methods are evaluated using data from the National Health and Nutrition Examination Survey, one of many nationally representative probability sample surveys conducted by the National Center for Health Statistics, Centers for Disease Control and Prevention. The study demonstrates the feasibility of the approach applied to a major national health survey with complex structure, and it provides practical advice about appropriate items to include in matrix sampling designs in future surveys.

In this Issue is a column where the Editor biefly presents each paper of the current issue of Survey Methodology. As well, it sometimes contain informations on structure or management changes in the journal.

From 1995 to 2004, the proportion of women and men aged 25 to 54 in the labour force grew steadily. However, from 2004 into the first half of 2006, both women's and men's participation rates declined very slightly yet persistently. Is this the beginning of a new trend or does it merely reflect regular fluctuations in the economy? Particular attention is focused on women with young children.

Using tax data, this paper examines earnings instability among lone parents, unattached individuals, and two-parent families over the past two decades. When income tax effects and main sources of income were considered, no strong evidence of a widespread increase in instability was found. Government transfers play a particularly important role in reducing the earnings instability of lone mothers and unattached individuals

Rapid technological change and an increased emphasis on skill-based knowledge have led to an increased need for training entry-level workers and retraining older ones. How do the training rates of workers aged 25 to 34 compare with those aged 55 to 64? Personal and job-related characteristics are examined for training participants, as are employer support, self-directed learning, barriers faced, and objectives and outcomes of training.

A household's ability to afford housing has traditionally been measured using income information derived from the census. A household spending 30% or more of its income on shelter was considered to have a shelter-cost burden. The Survey of Household Spending provides an alternative denominator based on total household spending.

Just as the responsibility of raising children is lifting, many families are facing a new challenge providing care to aging parents, relatives or friends. The intensity of work and eldercare can affect the work life balance of the caregiver. An examination of the prevalence and impact of caregiving among those aged 45 to 64, looking at the hours spent on both paid work and informal care of seniors.

This monograph focuses on the differences in performance on the IALSS tests between people whose mother tongue is French and those whose mother tongue is English in Canada, particularly those living in a minority situation. Various factors are examined with the goal of explaining these differences. Schooling, age, reading and writing habits of everyday life, as well as the living environment explains a large part of the differences between linguistic groups.

This article uses data from the 2001 General Social Survey to examine patterns in leaving the parental home. It compares the transition process for five birth cohorts,with the focus on Wave 1 Boomers (born between 1947 and 1956) and their children in Generation X (born between 1967 and 1976). The differences in patterns of leaving the parental home are examined, and then the principal factors associated with a young person's initial launch into adulthood are identified.

This article examines involvement with the court system of young Canadians born between April 1979 and March 1980. It identifies how large a proportion of them were referred to court and the type of offence with which they were charged. Using data from the Youth Court Survey and the Adult Criminal Court Survey, it follows them as they moved from youth to young adulthood - that is, from age 12 to 21, inclusive

This service bulletin presents the nature of research and development distribution of current intramural research and development expenditures by Canadian firms for the years 2000 to 2004.

This service bulletin presents the geographic distribution of federal government science and technology expenditures. Data on federal government expenditures on science and technology are found in Volume 30, No. 6 of this publication series, released in September 2006. Science and technology (S&T) expenditures are the sum of expenditures on research and development (R&D) and on related scientific activities (RSA).

This report provides an overview of the results of the Survey of Financial Security (SFS). This survey collected information on the assets and debts of families and unattached individuals. Data collection took place from May to July 2005, in all provinces.

The 2005 SFS provides a comprehensive picture of the wealth of Canadians. Information was collected on the value of all major financial and non-financial assets and on the money owing on mortgages, vehicles, credit cards, student loans and other debts. The value of these assets less the debts is referred to in this report as net worth.

Gross domestic expenditures on research and development (GERD) represents total research and development (R&D) expenditures performed in a country's national territory during a given year. GERD includes R&D performed within a country and funded from abroad but excludes payments sent abroad for R&D performed in other countries.

This bulletin presents recent information on the performance and funding of Federal government expenditures on scientific activities, 2006/2007. The statistics presented are derived from the survey of science and technology (S&T) activities of federal departments and agencies. The data in this publication are consistent with expenditures of departments and agencies as reported in the Main Estimates 2006/2007, but do not reflect changes to 2006/2007 spending plans which may result from supplementary estimates or other departmental planning decisions.

The higher education sector is composed of "all universities, colleges of technology and other institutes of postsecondary education, whatever their source of finance or legal status. It also includes all research institutes, experimental stations and clinics operating under the direct control of, or administered by, or associated with higher education establishments.

This service bulletin contains historical and current data on research and development (R&D) expenditures and personnel in Canada, by industry. In Canada, the industrial or business enterprise sector is the largest R&D performer.

The statistics presented in this Bulletin are for the fiscal year ending August 31 and cover the period from 2002 to 2005.

This publication presents financial and operating statistics for telecommunications services industries, except the Cable and Other Program Distribution industry

Revised estimates of the Income and Expenditure Accounts covering the period 2002 to 2005 have been released along with those for the first quarter of 2006. The current revisions to GDP resulted from the inclusion of the most current estimates from data sources, including survey results, administrative data and public accounts.

This document presents the geographical distribution of federal government expenditures and staff for the fiscal year 2004/2005.

We discuss methods for the analysis of case-control studies in which the controls are drawn using a complex sample survey. The most straightforward method is the standard survey approach based on weighted versions of population estimating equations. We also look at more efficient methods and compare their robustness to model mis-specification in simple cases. Case-control family studies, where the within-cluster structure is of interest in its own right, are also discussed briefly.

Calibration weighting can be used to adjust for unit nonresponse and/or coverage errors under appropriate quasi-randomization models. Alternative calibration adjustments that are asymptotically identical in a purely sampling context can diverge when used in this manner. Introducing instrumental variables into calibration weighting makes it possible for nonresponse (say) to be a function of a set of characteristics other than those in the calibration vector. When the calibration adjustment has a nonlinear form, a variant of the jackknife can remove the need for iteration in variance estimation.

The theory of multiple imputation for missing data requires that imputations be made conditional on the sampling design. However, most standard software packages for performing model-based multiple imputation assume simple random samples, leading many practitioners not to account for complex sample design features, such as stratification and clustering, in their imputations. Theory predicts that analyses of such multiply-imputed data sets can yield biased estimates from the design-based perspective. In this article, we illustrate through simulation that (i) the bias can be severe when the design features are related to the survey variables of interest, and (ii) the bias can be reduced by controlling for the design features in the imputation models. The simulations also illustrate that conditioning on irrelevant design features in the imputation models can yield conservative inferences, provided that the models include other relevant predictors. These results suggest a prescription for imputers: the safest course of action is to include design variables in the specification of imputation models. Using real data, we demonstrate a simple approach for incorporating complex design features that can be used with some of the standard software packages for creating multiple imputations.

In this article, we propose a Bernoulli-type bootstrap method that can easily handle multi-stage stratified designs where sampling fractions are large, provided simple random sampling without replacement is used at each stage. The method provides a set of replicate weights which yield consistent variance estimates for both smooth and non-smooth estimators. The method's strength is in its simplicity. It can easily be extended to any number of stages without much complication. The main idea is to either keep or replace a sampling unit at each stage with preassigned probabilities, to construct the bootstrap sample. A limited simulation study is presented to evaluate performance and, as an illustration, we apply the method to the 1997 Japanese National Survey of Prices.

In this paper, the geometric, optimization-based, and Lavallée and Hidiroglou (LH) approaches to stratification are compared. The geometric stratification method is an approximation, whereas the other two approaches, which employ numerical methods to perform stratification, may be seen as optimal stratification methods. The algorithm of the geometric stratification is very simple compared to the two other approaches, but it does not take into account the construction of a take-all stratum, which is usually constructed when a positively skewed population is stratified. In the optimization-based stratification, one may consider any form of optimization function and its constraints. In a comparative numerical study based on five positively skewed artificial populations, the optimization approach was more efficient in each of the cases studied compared to the geometric stratification. In addition, the geometric and optimization approaches are compared with the LH algorithm. In this comparison, the geometric stratification approach was found to be less efficient than the LH algorithm, whereas efficiency of the optimization approach was similar to the efficiency of the LH algorithm. Nevertheless, strata boundaries evaluated via the geometric stratification may be seen as efficient starting points for the optimization approach.

To select a survey sample, it happens that one does not have a frame containing the desired collection units, but rather another frame of units linked in a certain way to the list of collection units. It can then be considered to select a sample from the available frame in order to produce an estimate for the desired target population by using the links existing between the two. This can be designated by Indirect Sampling.

Estimation for the target population surveyed by Indirect Sampling can constitute a big challenge, in particular if the links between the units of the two are not one-to-one. The problem comes especially from the difficulty to associate a selection probability, or an estimation weight, to the surveyed units of the target population. In order to solve this type of estimation problem, the Generalized Weight Share Method (GWSM) has been developed by Lavallée (1995) and Lavallée (2002). The GWSM provides an estimation weight for every surveyed unit of the target population.

This paper first describes Indirect Sampling, which constitutes the foundations of the GWSM. Second, an overview of the GWSM is given where we formulate the GWSM in a theoretical framework using matrix notation. Third, we present some properties of the GWSM such as unbiasedness and transitivity. Fourth, we consider the special case where the links between the two populations are expressed by indicator variables. Fifth, some special typical linkages are studied to assess their impact on the GWSM. Finally, we consider the problem of optimality. We obtain optimal weights in a weak sense (for specific values of the variable of interest), and conditions for which these weights are also optimal in a strong sense and independent of the variable of interest.

A survey of tourist visits originating intra and extra-region in Brittany was needed. For concrete material reasons, "border surveys" could no longer be used. The major problem is the lack of a sampling frame that allows for direct contact with tourists. This problem was addressed by applying the indirect sampling method, the weighting for which is obtained using the generalized weight share method developed recently by Lavallée (1995), Lavallée (2002), Deville (1999) and also presented recently in Lavallée and Caron (2001). This article shows how to adapt the method to the survey. A number of extensions are required. One of the extensions, designed to estimate the total of a population from which a Bernouilli sample has been taken, will be developed.

Félix-Medina and Thompson (2004) proposed a variant of Link-tracing sampling in which it is assumed that a portion of the population, not necessarily the major portion, is covered by a frame of disjoint sites where members of the population can be found with high probabilities. A sample of sites is selected and the people in each of the selected sites are asked to nominate other members of the population. They proposed maximum likelihood estimators of the population sizes which perform acceptably provided that for each site the probability that a member is nominated by that site, called the nomination probability, is not small. In this research we consider Félix-Medina and Thompson's variant and propose three sets of estimators of the population sizes derived under the Bayesian approach. Two of the sets of estimators were obtained using improper prior distributions of the population sizes, and the other using Poisson prior distributions. However, we use the Bayesian approach only to assist us in the construction of estimators, while inferences about the population sizes are made under the frequentist approach. We propose two types of partly design-based variance estimators and confidence intervals. One of them is obtained using a bootstrap and the other using the delta method along with the assumption of asymptotic normality. The results of a simulation study indicate that (i) when the nomination probabilities are not small each of the proposed sets of estimators performs well and very similarly to maximum likelihood estimators; (ii) when the nomination probabilities are small the set of estimators derived using Poisson prior distributions still performs acceptably and does not have the problems of bias that maximum likelihood estimators have, and (iii) the previous results do not depend on the size of the fraction of the population covered by the frame.

Survey sampling to estimate a Consumer Price Index (CPI) is quite complicated, generally requiring a combination of data from at least two surveys: one giving prices, one giving expenditure weights. Fundamentally different approaches to the sampling process - probability sampling and purposive sampling - have each been strongly advocated and are used by different countries in the collection of price data. By constructing a small "world" of purchases and prices from scanner data on cereal and then simulating various sampling and estimation techniques, we compare the results of two design and estimation approaches: the probability approach of the United States and the purposive approach of the United Kingdom. For the same amount of information collected, but given the use of different estimators, the United Kingdom's methods appear to offer better overall accuracy in targeting a population superlative consumer price index.

The 2005 National Survey of the Work and Health of Nurses (NSWHN) is the first nationally representative survey to focus on the working conditions and health of Canada's nurses. Registered nurses (RNs), licensed practical nurses (LPNs) and registered psychiatric nurses (RPNs) in all provinces and territories shared their perceptions on a variety of topics, including:- workload- working overtime, whether paid or unpaid- adverse events such as medication errors and patient falls- support and respect from co-workers and supervisors- staffing adequacy- working relations with physicians- their own chronic diseases and injuries- their mental health.

The 2005 NSWHN was developed in collaboration with organizations representing practicing nurses, health care researchers, health information specialists and federal government departments. The survey was conducted by Statistics Canada in partnership with the Canadian Institute for Health Information and Health Canada. A total of 18,676 nurses were interviewed, representing LPNs, RNs and RPNs in a variety of health care settings and in all provinces and territories. The survey's impressive response rate of 80% reflects the enthusiasm and support of nurses across the country.

The survey collected information on a rich array of topics reflecting the physical and emotional challenges nurses face in delivering patient care today. Nurses answered many questions about the quality of patient care, working relations with co-workers and managers, the amount of time they work to get their jobs done, and the way they feel about their jobs and careers as nurses. Data from the 2005 NSWHN will provide an invaluable resource for researchers, health care providers, policy makers and anyone with an interest in human resources, particularly in the health care field.

This publication presents data and analytical text on trips and socio-economic characteristics of Canadians travelling within Canada. Trip information includes purpose, activities, mode of transportation, length of stay, origin and destination, and expenditures. In addition to providing national data, the publication also includes some tables presenting provincial and metropolitan detail.

This analytical study updates data previously released in the 2002 Statistical Profile: Assessing Violence Against Women. New content has also been added concerning the experiences of Aboriginal women and women in the North.

...au courant is a four-page newsletter which promotes the analysis activities of Health Analysis and Measurement Group (HAMG) and its collaborators. Published three times a year, each issue highlights a policy-relevant study or subject area through a two-page summary article including charts, references, and a methods box. Shorter articles inform readers of upcoming studies, papers, and events related to the group's research projects.

This series of reports provides key background information on the trends and conditions in Canadian census metropolitan areas (CMAs) across a number of dimensions. Subjects covered include demographics, housing, immigration, Aboriginal persons, low-income and stressed neighbourhoods, economic conditions, health, location of work and commuting mode, and culture. Most reports cover the 1981-to-2001 period.

This report provides results of the Health Services Access Survey (HSAS), which is now part of the Canadian Community Health Survey. The HSAS gathers comprehensive and comparable information on the patterns of use of health care services and self-reported difficulties faced by Canadians aged 15 and over in accessing health care. Data are presented for Canada as a whole and by province when sample sizes are sufficient.

Data on waiting times for specialized services such as specialist visits for a new illness or condition, non-emergency surgeries and selected diagnostics tests are also presented.

This publication presents results from the Canadian Community Health Survey, a major cross-sectional survey whose objective is to produce timely data for more than 120 health regions across Canada.The publication includes links to data tables on a wide range of health topics, including non-medical determinants of health, health status, use of health care services and related socio-demographic information. Links are also provided to more detailed information about CCHS, including questionnaires, descriptions of survey methodology and data quality, and options for accessing detailed survey results.The survey is conducted every two years. Data are collected from 130,000 respondents, aged 12 or older, residing in households in each health regions.

This publication presents quarterly and year-to-date data as aggregated from reports for the major wireline and wireless telecommunications systems in Canada. Information is provided on operating revenue and expenses, salaries and wage payments, number of employees, capital expenditures, network PSTN (Public Switched Telephone Network) access lines, non-PSTN lines, wireless subscribers and traffic statistics.

This feasibility report provides a blueprint for improving data on fraud in Canada through a survey of businesses and through amendments to the Uniform Crime Reporting (UCR) Survey. Presently, national information on fraud is based on official crime statistics reported by police services to the Uniform Crime Reporting Survey. These data, however, do not reflect the true nature and extent of fraud in Canada due to under-reporting of fraud by individuals and businesses, and due to inconsistencies in the way frauds are counted within the UCR Survey. This feasibility report concludes that a better measurement of fraud in Canada could be obtained through a survey of businesses. The report presents the information priorities of government departments, law enforcement and the private sector with respect to the issue of fraud and makes recommendations on how a survey of businesses could help fulfill these information needs.

To respond to information priorities, the study recommends surveying the following types of business establishments: banks, payment companies (i.e. credit card and debit card companies), selected retailers, property and casualty insurance carriers, health and disability insurance carriers and selected manufacturers. The report makes recommendations regarding survey methodology and questionnaire content, and provides estimates for timeframes and cost.

The report also recommends changes to the UCR Survey in order to improve the way in which incidents are counted and to render the data collected more relevant with respect to the information priorities raised by government, law enforcement and the private sector during the feasibility study.

The purpose of the provincial and territorial reports is to present a summary of demographic, social and economic characteristics of the off reserve Aboriginal population in the Atlantic provinces, Québec, Ontario, Manitoba, Saskatchewan, Alberta, British Columbia, Yukon and Northwest Territories. Information on education, residential schools, information technology, employment, mobility and housing, health and language are highlighted. While most of the focus is on adults, there is also information provided on children. Data showing comparisons between Aboriginal groups are provided, as are some comparisons with the non-Aboriginal population. Findings are based on the 2001 Census and the 2001 Aboriginal Peoples Survey.