Keyword search
Filter results by
Search HelpKeyword(s)
Subject
Year of publication
Survey or statistical program
Portal
Results
All (27)
All (27) (0 to 10 of 27 results)
- Articles and reports: 91F0015M2020002Description:
This document describes the production of demographic estimates for the second quarter of 2020 in the context of COVID-19. Limits to the usual approaches and alternate strategies that were considered are presented for each demographic component. When adjustments to the usual methodology were made, they are summarized in a succinct manner. A broad overview of potential adjustments for future releases of demographic estimates is also provided.
Release date: 2020-09-29 - Articles and reports: 91F0015M2020001Description:
This document describes the production of demographic estimates for the first quarter of 2020 in the context of COVID-19. Limits to the usual approaches and alternate strategies that were considered are presented for each demographic component. When adjustments to the usual methodology were made, they are summarized in a succinct manner. A broad overview of potential adjustments for future releases of demographic estimates is also provided.
Release date: 2020-06-18 - Articles and reports: 75F0002M2016003Description:
Periodically, income statistics are updated to reflect the most recent population estimates from the Census. Accordingly, with the release of the 2014 data from the Canadian Income Survey, Statistics Canada has revised estimates for 2006 to 2013 using new population totals from the 2011 Census. This paper provides unrevised estimates alongside revised estimates for key income series, indicating where the revisions were significant.
Release date: 2016-07-08 - Articles and reports: 75F0002M2012003Description:
The release of the 2010 Survey of Labour and Income Dynamics (SLID) data coincided with a historical revision of the 2006 to 2009 results. The survey weights were updated to take into account new population estimates based on the 2006 Census rather than the 2001 Census. This paper presents a summary of the impact of this revision on the 2006-2009 survey estimates.
Release date: 2012-11-01 - Articles and reports: 12-001-X201200111682Description:
Sample allocation issues are studied in the context of estimating sub-population (stratum or domain) means as well as the aggregate population mean under stratified simple random sampling. A non-linear programming method is used to obtain "optimal" sample allocation to strata that minimizes the total sample size subject to specified tolerances on the coefficient of variation of the estimators of strata means and the population mean. The resulting total sample size is then used to determine sample allocations for the methods of Costa, Satorra and Ventura (2004) based on compromise allocation and Longford (2006) based on specified "inferential priorities". In addition, we study sample allocation to strata when reliability requirements for domains, cutting across strata, are also specified. Performance of the three methods is studied using data from Statistics Canada's Monthly Retail Trade Survey (MRTS) of single establishments.
Release date: 2012-06-27 - Articles and reports: 12-001-X201000111247Description:
In this paper, the problem of estimating the variance of various estimators of the population mean in two-phase sampling has been considered by jackknifing the two-phase calibrated weights of Hidiroglou and Särndal (1995, 1998). Several estimators of population mean available in the literature are shown to be the special cases of the technique developed here, including those suggested by Rao and Sitter (1995) and Sitter (1997). By following Raj (1965) and Srivenkataramana and Tracy (1989), some new estimators of the population mean are introduced and their variances are estimated through the proposed jackknife procedure. The variance of the chain ratio and regression type estimators due to Chand (1975) are also estimated using the jackknife. A simulation study is conducted to assess the efficiency of the proposed jackknife estimators relative to the usual estimators of variance.
Release date: 2010-06-29 - Articles and reports: 12-001-X200900211036Description:
Surveys are frequently required to produce estimates for subpopulations, sometimes for a single subpopulation and sometimes for several subpopulations in addition to the total population. When membership of a rare subpopulation (or domain) can be determined from the sampling frame, selecting the required domain sample size is relatively straightforward. In this case the main issue is the extent of oversampling to employ when survey estimates are required for several domains and for the total population. Sampling and oversampling rare domains whose members cannot be identified in advance present a major challenge. A variety of methods has been used in this situation. In addition to large-scale screening, these methods include disproportionate stratified sampling, two-phase sampling, the use of multiple frames, multiplicity sampling, panel surveys, and the use of multi-purpose surveys. This paper illustrates the application of these methods in a range of social surveys.
Release date: 2009-12-23 - Articles and reports: 91F0015M2007008Geography: CanadaDescription:
If low fertility, aging, demographic growth and ethnocultural diversity are phenomena that accurately describe Canada overall, the same patterns may not necessarily hold true for urban and rural areas. The rhythm and sources of demographic growth have often been significantly different from one area to the next, which would suggest that the situation across Canada stems from the aggregation of different demographies, which are variable between types of regions.
The objective of this study is to examine demographic differences between urban and rural areas in Canada by analyzing communities along a gradient ranging from the largest metropolitan regions to the most rural areas. Applying a geographic structure to Census data from 1971 to 2001 that maintains constant borders over time, the authors analyze population growth across eight types of urban and rural regions; as well as the contribution of immigration, fertility and internal migration to growth differentials; and the consequences of these observed demographic differences in terms of aging and ethnocultural diversity.
The study finds that growth is concentrated in the most metropolitan areas in the country and in the rural areas on which they have a strong influence, and diminished as the degree of rurality increases. Internal migration between the different types of areas has largely contributed to this differential growth: the most urbanized areas-with the exception of Montréal, Toronto and Vancouver-underwent significant migratory gains as well as strong growth. This was also the case with the rural regions that had a strong metropolitan influence. The most rural regions experienced a weak demographic growth, in some cases a decline, despite having higher fertility than other regions. The strong growth in the three largest urban areas in Canada-Montréal, Toronto and Vancouver-is largely attributed to the high numbers of international immigrants who decided to settle there. The concentration of newcomers in these regions helped increase the gap between these three areas and the rest of the country in terms of ethnocultural diversity.
Release date: 2007-04-26 - Articles and reports: 15-206-X2007008Description:
This study is the third in a series related to the project launched in fall 2003 by the Canadian Productivity Accounts of Statistics Canada in order to compare productivity levels between Canada and the United States. The study's purpose is to examine the comparability of the components of the labour market of these two countries that serve as the sources of the differences in the gross domestic product (GDP) per capita between them. This study can be subdivided into three sections. The first section develops and illustrates the conceptual and methodological framework required to make Canada/United States estimates of labour and population comparable in terms of level. The second section presents revisions and an update to 2005 of the GDP per capita differences and its components, which were presented for the first time in the study by Baldwin, Maynard and Wong (2005), which covered the period from 1994 to 2002, at the time.
Lastly, using the year 2000 as an example, this study tries to quantify the "statistical error" that arises from using inadequate statistics or statistics not designed for this type of international comparison. This exercise reveals that the comparability of data on hours worked per job is especially crucial to identifying the origin of the differences in GDP per capita between labour productivity and hours worked per capita. The worst error involves comparing hours worked estimated from an employer survey with those obtained from a household survey. This type of comparison between Canada and the United States results in assigning an estimated 72% of the difference in GDP per capita to labour productivity when, in reality, it counted for barely 36% in 2000.
Release date: 2007-03-26 - Articles and reports: 12-001-X20040027758Description:
In this article, we study the use of Bayesian neural networks in finite population estimation.We propose estimators for finite population mean and the associated mean squared error. We also propose to use the student t-distribution to model the disturbances in order to accommodate extreme observations that are often present in the data from social sample surveys. Numerical results show that Bayesian neural networks have made a significant improvement in finite population estimation over linear regression based methods
Release date: 2005-02-03
Data (0)
Data (0) (0 results)
No content available at this time.
Analysis (27)
Analysis (27) (0 to 10 of 27 results)
- Articles and reports: 91F0015M2020002Description:
This document describes the production of demographic estimates for the second quarter of 2020 in the context of COVID-19. Limits to the usual approaches and alternate strategies that were considered are presented for each demographic component. When adjustments to the usual methodology were made, they are summarized in a succinct manner. A broad overview of potential adjustments for future releases of demographic estimates is also provided.
Release date: 2020-09-29 - Articles and reports: 91F0015M2020001Description:
This document describes the production of demographic estimates for the first quarter of 2020 in the context of COVID-19. Limits to the usual approaches and alternate strategies that were considered are presented for each demographic component. When adjustments to the usual methodology were made, they are summarized in a succinct manner. A broad overview of potential adjustments for future releases of demographic estimates is also provided.
Release date: 2020-06-18 - Articles and reports: 75F0002M2016003Description:
Periodically, income statistics are updated to reflect the most recent population estimates from the Census. Accordingly, with the release of the 2014 data from the Canadian Income Survey, Statistics Canada has revised estimates for 2006 to 2013 using new population totals from the 2011 Census. This paper provides unrevised estimates alongside revised estimates for key income series, indicating where the revisions were significant.
Release date: 2016-07-08 - Articles and reports: 75F0002M2012003Description:
The release of the 2010 Survey of Labour and Income Dynamics (SLID) data coincided with a historical revision of the 2006 to 2009 results. The survey weights were updated to take into account new population estimates based on the 2006 Census rather than the 2001 Census. This paper presents a summary of the impact of this revision on the 2006-2009 survey estimates.
Release date: 2012-11-01 - Articles and reports: 12-001-X201200111682Description:
Sample allocation issues are studied in the context of estimating sub-population (stratum or domain) means as well as the aggregate population mean under stratified simple random sampling. A non-linear programming method is used to obtain "optimal" sample allocation to strata that minimizes the total sample size subject to specified tolerances on the coefficient of variation of the estimators of strata means and the population mean. The resulting total sample size is then used to determine sample allocations for the methods of Costa, Satorra and Ventura (2004) based on compromise allocation and Longford (2006) based on specified "inferential priorities". In addition, we study sample allocation to strata when reliability requirements for domains, cutting across strata, are also specified. Performance of the three methods is studied using data from Statistics Canada's Monthly Retail Trade Survey (MRTS) of single establishments.
Release date: 2012-06-27 - Articles and reports: 12-001-X201000111247Description:
In this paper, the problem of estimating the variance of various estimators of the population mean in two-phase sampling has been considered by jackknifing the two-phase calibrated weights of Hidiroglou and Särndal (1995, 1998). Several estimators of population mean available in the literature are shown to be the special cases of the technique developed here, including those suggested by Rao and Sitter (1995) and Sitter (1997). By following Raj (1965) and Srivenkataramana and Tracy (1989), some new estimators of the population mean are introduced and their variances are estimated through the proposed jackknife procedure. The variance of the chain ratio and regression type estimators due to Chand (1975) are also estimated using the jackknife. A simulation study is conducted to assess the efficiency of the proposed jackknife estimators relative to the usual estimators of variance.
Release date: 2010-06-29 - Articles and reports: 12-001-X200900211036Description:
Surveys are frequently required to produce estimates for subpopulations, sometimes for a single subpopulation and sometimes for several subpopulations in addition to the total population. When membership of a rare subpopulation (or domain) can be determined from the sampling frame, selecting the required domain sample size is relatively straightforward. In this case the main issue is the extent of oversampling to employ when survey estimates are required for several domains and for the total population. Sampling and oversampling rare domains whose members cannot be identified in advance present a major challenge. A variety of methods has been used in this situation. In addition to large-scale screening, these methods include disproportionate stratified sampling, two-phase sampling, the use of multiple frames, multiplicity sampling, panel surveys, and the use of multi-purpose surveys. This paper illustrates the application of these methods in a range of social surveys.
Release date: 2009-12-23 - Articles and reports: 91F0015M2007008Geography: CanadaDescription:
If low fertility, aging, demographic growth and ethnocultural diversity are phenomena that accurately describe Canada overall, the same patterns may not necessarily hold true for urban and rural areas. The rhythm and sources of demographic growth have often been significantly different from one area to the next, which would suggest that the situation across Canada stems from the aggregation of different demographies, which are variable between types of regions.
The objective of this study is to examine demographic differences between urban and rural areas in Canada by analyzing communities along a gradient ranging from the largest metropolitan regions to the most rural areas. Applying a geographic structure to Census data from 1971 to 2001 that maintains constant borders over time, the authors analyze population growth across eight types of urban and rural regions; as well as the contribution of immigration, fertility and internal migration to growth differentials; and the consequences of these observed demographic differences in terms of aging and ethnocultural diversity.
The study finds that growth is concentrated in the most metropolitan areas in the country and in the rural areas on which they have a strong influence, and diminished as the degree of rurality increases. Internal migration between the different types of areas has largely contributed to this differential growth: the most urbanized areas-with the exception of Montréal, Toronto and Vancouver-underwent significant migratory gains as well as strong growth. This was also the case with the rural regions that had a strong metropolitan influence. The most rural regions experienced a weak demographic growth, in some cases a decline, despite having higher fertility than other regions. The strong growth in the three largest urban areas in Canada-Montréal, Toronto and Vancouver-is largely attributed to the high numbers of international immigrants who decided to settle there. The concentration of newcomers in these regions helped increase the gap between these three areas and the rest of the country in terms of ethnocultural diversity.
Release date: 2007-04-26 - Articles and reports: 15-206-X2007008Description:
This study is the third in a series related to the project launched in fall 2003 by the Canadian Productivity Accounts of Statistics Canada in order to compare productivity levels between Canada and the United States. The study's purpose is to examine the comparability of the components of the labour market of these two countries that serve as the sources of the differences in the gross domestic product (GDP) per capita between them. This study can be subdivided into three sections. The first section develops and illustrates the conceptual and methodological framework required to make Canada/United States estimates of labour and population comparable in terms of level. The second section presents revisions and an update to 2005 of the GDP per capita differences and its components, which were presented for the first time in the study by Baldwin, Maynard and Wong (2005), which covered the period from 1994 to 2002, at the time.
Lastly, using the year 2000 as an example, this study tries to quantify the "statistical error" that arises from using inadequate statistics or statistics not designed for this type of international comparison. This exercise reveals that the comparability of data on hours worked per job is especially crucial to identifying the origin of the differences in GDP per capita between labour productivity and hours worked per capita. The worst error involves comparing hours worked estimated from an employer survey with those obtained from a household survey. This type of comparison between Canada and the United States results in assigning an estimated 72% of the difference in GDP per capita to labour productivity when, in reality, it counted for barely 36% in 2000.
Release date: 2007-03-26 - Articles and reports: 12-001-X20040027758Description:
In this article, we study the use of Bayesian neural networks in finite population estimation.We propose estimators for finite population mean and the associated mean squared error. We also propose to use the student t-distribution to model the disturbances in order to accommodate extreme observations that are often present in the data from social sample surveys. Numerical results show that Bayesian neural networks have made a significant improvement in finite population estimation over linear regression based methods
Release date: 2005-02-03
Reference (0)
Reference (0) (0 results)
No content available at this time.
- Date modified: