Keyword search

In this paper, we study the problem of variance estimation for a ratio of two totals when marginal random hot deck imputation has been used to fill in missing data. We consider two approaches to inference. In the first approach, the validity of an imputation model is required. In the second approach, the validity of an imputation model is not required but response probabilities need to be estimated, in which case the validity of a nonresponse model is required. We derive variance estimators under two distinct frameworks: the customary two-phase framework and the reverse framework.

The Australian Bureau of Statistics has recently developed a generalized estimation system for processing its large scale annual and sub-annual business surveys. Designs for these surveys have a large number of strata, use Simple Random Sampling within Strata, have non-negligible sampling fractions, are overlapping in consecutive periods, and are subject to frame changes. A significant challenge was to choose a variance estimation method that would best meet the following requirements: valid for a wide range of estimators (e.g., ratio and generalized regression), requires limited computation time, can be easily adapted to different designs and estimators, and has good theoretical properties measured in terms of bias and variance. This paper describes the Without Replacement Scaled Bootstrap (WOSB) that was implemented at the ABS and shows that it is appreciably more efficient than the Rao and Wu (1988)'s With Replacement Scaled Bootstrap (WSB). The main advantages of the Bootstrap over alternative replicate variance estimators are its efficiency (i.e., accuracy per unit of storage space) and the relative simplicity with which it can be specified in a system. This paper describes the WOSB variance estimator for point-in-time and movement estimates that can be expressed as a function of finite population means. Simulation results obtained as part of the evaluation process show that the WOSB was more efficient than the WSB, especially when the stratum sample sizes are sometimes as small as 5.

The purpose of this work is to obtain reliable estimates in study domains when there are potentially very small sample sizes and the sampling design stratum differs from the study domain. The population sizes are unknown as well for both the study domain and the sampling design stratum. In calculating parameter estimates in the study domains, a random sample size is often necessary. We propose a new family of generalized linear mixed models with correlated random effects when there is more than one unknown parameter. The proposed model will estimate both the population size and the parameter of interest. General formulae for full conditional distributions required for Markov chain Monte Carlo (MCMC) simulations are given for this framework. Equations for Bayesian estimation and prediction at the study domains are also given. We apply the 1998 Missouri Turkey Hunting Survey, which stratified samples based on the hunter's place of residence and we require estimates at the domain level, defined as the county in which the turkey hunter actually hunted.

The European Community Household Panel (ECHP) is a panel survey covering a wide range of topics regarding economic, social and living conditions. In particular, it makes it possible to calculate disposable equivalized household income, which is a key variable in the study of economic inequity and poverty. To obtain reliable estimates of the average of this variable for regions within countries it is necessary to have recourse to small area estimation methods. In this paper, we focus on empirical best linear predictors of the average equivalized income based on "unit level models" borrowing strength across both areas and times. Using a simulation study based on ECHP data, we compare the suggested estimators with cross-sectional model-based and design-based estimators. In the case of these empirical predictors, we also compare three different MSE estimators. Results show that those estimators connected to models that take units' autocorrelation into account lead to a significant gain in efficiency, even when there are no covariates available whose population mean is known.

Coverage deficiencies are estimated and analysed for the 2000 population census in Switzerland. For the undercoverage component, the estimation is based on a sample independent of the census and a match with the census. For the overcoverage component, the estimation is based on a sample drawn from the census list and a match with the rest of the census. The over- and undercoverage components are then combined to obtain an estimate of the resulting net coverage. This estimate is based on a capture-recapture model, named the dual system, combined with a synthetic model. The estimators are calculated for the full population and different subgroups, with a variance estimated by a stratified jackknife. The coverage analyses are supplemented by a study of matches between the independent sample and the census in order to determine potential errors of measurement and location in the census data.

In this paper we describe a methodology for combining a convenience sample with a probability sample in order to produce an estimator with a smaller mean squared error (MSE) than estimators based on only the probability sample. We then explore the properties of the resulting composite estimator, a linear combination of the convenience and probability sample estimators with weights that are a function of bias. We discuss the estimator's properties in the context of web-based convenience sampling. Our analysis demonstrates that the use of a convenience sample to supplement a probability sample for improvements in the MSE of estimation may be practical only under limited circumstances. First, the remaining bias of the estimator based on the convenience sample must be quite small, equivalent to no more than 0.1 of the outcome's population standard deviation. For a dichotomous outcome, this implies a bias of no more than five percentage points at 50 percent prevalence and no more than three percentage points at 10 percent prevalence. Second, the probability sample should contain at least 1,000-10,000 observations for adequate estimation of the bias of the convenience sample estimator. Third, it must be inexpensive and feasible to collect at least thousands (and probably tens of thousands) of web-based convenience observations. The conclusions about the limited usefulness of convenience samples with estimator bias of more than 0.1 standard deviations also apply to direct use of estimators based on that sample.

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.

This publication presents quarterly information on Canada's National Income and Expenditure Accounts (NIEA), 1947-2008. It contains data on gross domestic product (GDP) by income and by expenditure, saving and investment, borrowing and lending of each of four broad sectors of the economy: (i) persons and unincorporated businesses, (ii) corporate and government business enterprises, (iii) governments and (iv) non-residents. Information is also provided for selected subsectors. The publication begins with an analysis of the economic developments in the most recent quarter. Some issues also contain more technical articles explaining national accounts methodology or analysing a particular aspect of the economy. The publication also includes a glossary, and is no longer being released.

A series of supporting data tables accompanies the Inuit analytical article from the 2006 Aboriginal Peoples Survey (APS). These tables provide data at the national level, for each of the four Inuit regions (Nunatsiavut, Nunavik, Nunavut and the Inuvialuit region), along with data for Inuit outside these regions for major themes covered in the analytical article. Data for the Inuit identity population aged 15 and over are provided for: Participation in harvesting activities; diagnosed with arthritis/rheumatism, high blood pressure, asthma, stomach problems or intestinal ulcers, heart problems, tuberculosis and diabetes; smoking status; self-rated health status and; reasons for not completing elementary or secondary school. For Inuit children aged 6 to 14, tables include: contact with a pediatrician, general practitioner or family physician in past 12 months; contact with another medical specialist and; food insecurity.

This publication presents early estimates of mineral production by class and by province, quantities and values.

Data for Canada, provinces, territories, census divisions, census subdivisions and dissemination areas are shown in this table.

This table is part of the topic 'Labour', which presents data on the paid work of the Canadian workforce, including detailed industry and occupation data, class of worker, and work activity during the reference year. The census is the only source of data covering the entire labour market, including Indian reserves, overseas households, and all provinces and territories.

This topic also presents data on the unpaid work of the Canadian workforce, including unpaid household work, unpaid child care, and unpaid senior care. These data, together with information on paid work, provide a more complete picture of the work activities of all Canadians.

It is possible to subscribe to all the day-of-release topic bundles. Refer to Catalogue no. 97-569-XCB for more information.

Data for Canada, provinces, territories, census divisions, census subdivisions and dissemination areas are shown in this table.

This table is part of the topic 'Income and earnings,' which presents data on the income of Canadian individuals, families, and households in the year 2005, including the composition of income, and data that serve to measure low income, known as the low income cut-off (LICO). The data also include the household incomes of Canadians by family type, age, and geography, as well as the household incomes of certain population groups (e.g., immigrants).

The composition of income includes earnings, income from government sources, and investments.

It is possible to subscribe to all the day-of-release bundles. Refer to Catalogue no. 97-569-XCB for more information.

The tables in the topic 'Labour' present data on the paid work of the Canadian workforce, including detailed industry and occupation data, class of worker, and work activity during the reference year. The census is the only source of data covering the entire labour market, including Indian reserves, overseas households, and all provinces and territories.

This topic also presents data on the unpaid work of the Canadian workforce, including unpaid household work, unpaid child care, and unpaid senior care. These data, together with information on paid work, provide a more complete picture of the work activities of all Canadians.

The tables in the topic "Income and earnings" present data on the income of Canadian individuals, families, and households in the year 2005, including the composition of income, and data that serve to measure low income, known as the low income cut-off (LICO). The data also include the household incomes of Canadians by family type, age, and geography, as well as the household incomes of certain population groups (e.g., immigrants).

The composition of income includes earnings, income from government sources, and investments.

This article profiles manure production in Canada and maps manure production by sub-sub-drainage area for 2006.

Data for Canada, provinces and territories are shown in this table.

This table is part of the topic 'Income and earnings,' which presents data on the income of Canadian individuals, families, and households in the year 2005, including the composition of income, and data that serve to measure low income, known as the low income cut-off (LICO). The data also include the household incomes of Canadians by family type, age, and geography, as well as the household incomes of certain population groups (e.g., immigrants).

The composition of income includes earnings, income from government sources, and investments.

It is possible to subscribe to all the day-of-release bundles. Refer to Catalogue no. 97-569-XCB for more information.

This table is available free on the Internet, Catalogue no. 97-563-XWE2006008.

Data for Canada, provinces and territories are shown in this table.

This table is part of the topic 'Income and earnings,' which presents data on the income of Canadian individuals, families, and households in the year 2005, including the composition of income, and data that serve to measure low income, known as the low income cut-off (LICO). The data also include the household incomes of Canadians by family type, age, and geography, as well as the household incomes of certain population groups (e.g., immigrants).

The composition of income includes earnings, income from government sources, and investments.

It is possible to subscribe to all the day-of-release bundles. Refer to Catalogue no. 97-569-XCB for more information.

This table is available free on the Internet, Catalogue no. 97-563-XWE2006009.

The European Community Household Panel (ECHP) is a panel survey covering a wide range of topics regarding economic, social and living conditions. In particular, it makes it possible to calculate disposable equivalized household income, which is a key variable in the study of economic inequity and poverty. To obtain reliable estimates of the average of this variable for regions within countries it is necessary to have recourse to small area estimation methods. In this paper, we focus on empirical best linear predictors of the average equivalized income based on "unit level models" borrowing strength across both areas and times. Using a simulation study based on ECHP data, we compare the suggested estimators with cross-sectional model-based and design-based estimators. In the case of these empirical predictors, we also compare three different MSE estimators. Results show that those estimators connected to models that take units' autocorrelation into account lead to a significant gain in efficiency, even when there are no covariates available whose population mean is known.

Coverage deficiencies are estimated and analysed for the 2000 population census in Switzerland. For the undercoverage component, the estimation is based on a sample independent of the census and a match with the census. For the overcoverage component, the estimation is based on a sample drawn from the census list and a match with the rest of the census. The over- and undercoverage components are then combined to obtain an estimate of the resulting net coverage. This estimate is based on a capture-recapture model, named the dual system, combined with a synthetic model. The estimators are calculated for the full population and different subgroups, with a variance estimated by a stratified jackknife. The coverage analyses are supplemented by a study of matches between the independent sample and the census in order to determine potential errors of measurement and location in the census data.

In this paper we describe a methodology for combining a convenience sample with a probability sample in order to produce an estimator with a smaller mean squared error (MSE) than estimators based on only the probability sample. We then explore the properties of the resulting composite estimator, a linear combination of the convenience and probability sample estimators with weights that are a function of bias. We discuss the estimator's properties in the context of web-based convenience sampling. Our analysis demonstrates that the use of a convenience sample to supplement a probability sample for improvements in the MSE of estimation may be practical only under limited circumstances. First, the remaining bias of the estimator based on the convenience sample must be quite small, equivalent to no more than 0.1 of the outcome's population standard deviation. For a dichotomous outcome, this implies a bias of no more than five percentage points at 50 percent prevalence and no more than three percentage points at 10 percent prevalence. Second, the probability sample should contain at least 1,000-10,000 observations for adequate estimation of the bias of the convenience sample estimator. Third, it must be inexpensive and feasible to collect at least thousands (and probably tens of thousands) of web-based convenience observations. The conclusions about the limited usefulness of convenience samples with estimator bias of more than 0.1 standard deviations also apply to direct use of estimators based on that sample.

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.

This guide focuses on the following demographic variable: Housing and dwelling characteristics.

This guide focuses on the following demographic variables: First official language spoken, Home language, Knowledge of non-official languages, Knowledge of official languages, Language of work, and Mother tongue.

Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts, data quality and historical comparability. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

This guide focuses on the following topics: Labour market activity and Unpaid work.

Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

This guide focuses on the following topic: Journey to work.

Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

These guides provide information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

This guide focuses on the following topics: Labour market activity and Unpaid work.

Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

This guide focuses on the following topic: Journey to work. Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

This guide focuses on the following demographic variables: Visible minority population and Population group.

Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

This guide focuses on the following demographic variable: Ethnic origin.

Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.

This guide focuses on the following demographic variables: Visible minority population and Population group.

Provides information that enables users to effectively use, apply and interpret data from the 2006 Census. Each guide contains definitions and explanations on census concepts. Additional information will be included for specific variables to help general users better understand the concepts and questions used in the census.