Analysis

Skip to main content
Skip to footer

Language selection

Français

Search and menus

Search and menus

Search

Skip to filters. View results.

What’s new on our website

Statistics Canada's Trust Centre

Results

All (24)

All (24) (0 to 10 of 24 results)

1. Estimation methods on multiple sampling frames in two-stage sample designs Archived
Articles and reports: 12-001-X201400214090
Description:
When studying a finite population, it is sometimes necessary to select samples from several sampling frames in order to represent all individuals. Here we are interested in the scenario where two samples are selected using a two-stage design, with common first-stage selection. We apply the Hartley (1962), Bankier (1986) and Kalton and Anderson (1986) methods, and we show that these methods can be applied conditional on first-stage selection. We also compare the performance of several estimators as part of a simulation study. Our results suggest that the estimator should be chosen carefully when there are multiple sampling frames, and that a simple estimator is sometimes preferable, even if it uses only part of the information collected.
Release date: 2014-12-19
2. Potential gains from using unit level cost information in a model-assisted framework Archived
Articles and reports: 12-001-X201400214110
Description:
In developing the sample design for a survey we attempt to produce a good design for the funds available. Information on costs can be used to develop sample designs that minimise the sampling variance of an estimator of total for fixed cost. Improvements in survey management systems mean that it is now sometimes possible to estimate the cost of including each unit in the sample. This paper develops relatively simple approaches to determine whether the potential gains arising from using this unit level cost information are likely to be of practical use. It is shown that the key factor is the coefficient of variation of the costs relative to the coefficient of variation of the relative error on the estimated cost coefficients.
Release date: 2014-12-19
3. From multiple modes for surveys to multiple data sources for estimates Archived
Articles and reports: 12-001-X201400214128
Description:
Users, funders and providers of official statistics want estimates that are “wider, deeper, quicker, better, cheaper” (channeling Tim Holt, former head of the UK Office for National Statistics), to which I would add “more relevant” and “less burdensome”. Since World War II, we have relied heavily on the probability sample survey as the best we could do - and that best being very good - to meet these goals for estimates of household income and unemployment, self-reported health status, time use, crime victimization, business activity, commodity flows, consumer and business expenditures, et al. Faced with secularly declining unit and item response rates and evidence of reporting error, we have responded in many ways, including the use of multiple survey modes, more sophisticated weighting and imputation methods, adaptive design, cognitive testing of survey items, and other means to maintain data quality. For statistics on the business sector, in order to reduce burden and costs, we long ago moved away from relying solely on surveys to produce needed estimates, but, to date, we have not done that for household surveys, at least not in the United States. I argue that we can and must move from a paradigm of producing the best estimates possible from a survey to that of producing the best possible estimates to meet user needs from multiple data sources. Such sources include administrative records and, increasingly, transaction and Internet-based data. I provide two examples - household income and plumbing facilities - to illustrate my thesis. I suggest ways to inculcate a culture of official statistics that focuses on the end result of relevant, timely, accurate and cost-effective statistics and treats surveys, along with other data sources, as means to that end.
Release date: 2014-12-19
4. Homicide in Canada, 2013 Archived
Articles and reports: 85-002-X201400114108
Description:
This annual Juristat article presents 2013 homicide data. Short and long-term trends in homicide are examined at the national, provincial/territorial and census metropolitan area levels. Gang-related homicides, firearm-related homicides, intimate partner homicides, youth homicides and international comparisons of homicide are also explored.
Release date: 2014-12-01
5. Canadian Agriculture Statistics
Stats in brief: 11-629-X2014002
Description:
An animated video which illustrates the nature and breadth of the agricultural statistical data collected and disseminated by Statistics Canada.
Release date: 2014-11-28
6. Survey Sampling In Official Statistics - Some Thoughts On Directions Archived
Articles and reports: 11-522-X201300014251
Description:
I present a modeller's perspective on the current status quo in official statistics surveys-based inference. In doing so, I try to identify the strengths and weaknesses of the design and model-based inferential positions that survey sampling, at least as far as the official statistics world is concerned, finds itself at present. I close with an example from adaptive survey design that illustrates why taking a model-based perspective (either frequentist or Bayesian) represents the best way for official statistics to avoid the debilitating 'inferential schizophrenia' that seems inevitable if current methodologies are applied to the emerging information requirements of today's world (and possibly even tomorrow's).
Release date: 2014-10-31
7. What Big Data May Mean for Surveys Archived
Articles and reports: 11-522-X201300014272
Description:
Two converging trends raise questions about the future of large-scale probability surveys conducted by or for National Statistical Institutes (NSIs). First, increasing costs and rising rates of nonresponse potentially threaten the cost-effectiveness and inferential value of surveys. Second, there is growing interest in Big Data as a replacement for surveys. There are many different types of Big Data, but the primary focus here is on data generated through social media. This paper supplements and updates an earlier paper on the topic (Couper, 2013). I review some of the concerns about Big Data, particularly from the survey perspective. I argue that there is a role for both high-quality surveys and big data analytics in the work of NSIs. While Big Data is unlikely to replace high-quality surveys, I believe the two methods can serve complementary functions. I attempt to identify some of the criteria that need to be met, and questions that need to be answered, before Big Data can be used for reliable population-based inference.
Release date: 2014-10-31
8. Study of the “product” sampling scheme as illustrated by the ELFE survey Archived
Articles and reports: 11-522-X201300014286
Description:
The Étude Longitudinale Française depuis l’Enfance (ELFE) [French longitudinal study from childhood on], which began in 2011, involves over 18,300 infants whose parents agreed to participate when they were in the maternity hospital. This cohort survey, which will track the children from birth to adulthood, covers the many aspects of their lives from the perspective of social science, health and environmental health. In randomly selected maternity hospitals, all infants in the target population, who were born on one of 25 days distributed across the four seasons, were chosen. This sample is the outcome of a non-standard sampling scheme that we call product sampling. In this survey, it takes the form of the cross-tabulation between two independent samples: a sampling of maternity hospitals and a sampling of days. While it is easy to imagine a cluster effect due to the sampling of maternity hospitals, one can also imagine a cluster effect due to the sampling of days. The scheme’s time dimension therefore cannot be ignored if the desired estimates are subject to daily or seasonal variation. While this non-standard scheme can be viewed as a particular kind of two-phase design, it needs to be defined within a more specific framework. Following a comparison of the product scheme with a conventional two-stage design, we propose variance estimators specially formulated for this sampling scheme. Our ideas are illustrated with a simulation study.
Release date: 2014-10-31
9. Demosim's Population Projection Model: Updates and New Developments Archived
Articles and reports: 11-522-X201300014289
Description:
This paper provides an overview of the main new features that will be added to the forthcoming version of the Demosim microsimulation projection model based on microdata from the 2011 National Household Survey. The paper first describes the additions to the base population, namely new variables, some of which are added to the National Household Survey data by means of data linkage. This is followed by a brief description of the methods being considered for the projection of language variables, citizenship and religion as examples of the new features for events simulated by the model.
Release date: 2014-10-31
10. Two approaches to linking census and hospital data Archived
Articles and reports: 82-003-X201401014098
Geography: Province or territory
Description:
This study compares registry and non-registry approaches to linking 2006 Census of Population data for Manitoba and Ontario to Hospital data from the Discharge Abstract Database.
Release date: 2014-10-15

Stats in brief (1)

Stats in brief (1) ((1 result))

1. Canadian Agriculture Statistics
Stats in brief: 11-629-X2014002
Description:
An animated video which illustrates the nature and breadth of the agricultural statistical data collected and disseminated by Statistics Canada.
Release date: 2014-11-28

Articles and reports (23)

Articles and reports (23) (0 to 10 of 23 results)

1. Estimation methods on multiple sampling frames in two-stage sample designs Archived
Articles and reports: 12-001-X201400214090
Description:
When studying a finite population, it is sometimes necessary to select samples from several sampling frames in order to represent all individuals. Here we are interested in the scenario where two samples are selected using a two-stage design, with common first-stage selection. We apply the Hartley (1962), Bankier (1986) and Kalton and Anderson (1986) methods, and we show that these methods can be applied conditional on first-stage selection. We also compare the performance of several estimators as part of a simulation study. Our results suggest that the estimator should be chosen carefully when there are multiple sampling frames, and that a simple estimator is sometimes preferable, even if it uses only part of the information collected.
Release date: 2014-12-19
2. Potential gains from using unit level cost information in a model-assisted framework Archived
Articles and reports: 12-001-X201400214110
Description:
In developing the sample design for a survey we attempt to produce a good design for the funds available. Information on costs can be used to develop sample designs that minimise the sampling variance of an estimator of total for fixed cost. Improvements in survey management systems mean that it is now sometimes possible to estimate the cost of including each unit in the sample. This paper develops relatively simple approaches to determine whether the potential gains arising from using this unit level cost information are likely to be of practical use. It is shown that the key factor is the coefficient of variation of the costs relative to the coefficient of variation of the relative error on the estimated cost coefficients.
Release date: 2014-12-19
3. From multiple modes for surveys to multiple data sources for estimates Archived
Articles and reports: 12-001-X201400214128
Description:
Users, funders and providers of official statistics want estimates that are “wider, deeper, quicker, better, cheaper” (channeling Tim Holt, former head of the UK Office for National Statistics), to which I would add “more relevant” and “less burdensome”. Since World War II, we have relied heavily on the probability sample survey as the best we could do - and that best being very good - to meet these goals for estimates of household income and unemployment, self-reported health status, time use, crime victimization, business activity, commodity flows, consumer and business expenditures, et al. Faced with secularly declining unit and item response rates and evidence of reporting error, we have responded in many ways, including the use of multiple survey modes, more sophisticated weighting and imputation methods, adaptive design, cognitive testing of survey items, and other means to maintain data quality. For statistics on the business sector, in order to reduce burden and costs, we long ago moved away from relying solely on surveys to produce needed estimates, but, to date, we have not done that for household surveys, at least not in the United States. I argue that we can and must move from a paradigm of producing the best estimates possible from a survey to that of producing the best possible estimates to meet user needs from multiple data sources. Such sources include administrative records and, increasingly, transaction and Internet-based data. I provide two examples - household income and plumbing facilities - to illustrate my thesis. I suggest ways to inculcate a culture of official statistics that focuses on the end result of relevant, timely, accurate and cost-effective statistics and treats surveys, along with other data sources, as means to that end.
Release date: 2014-12-19
4. Homicide in Canada, 2013 Archived
Articles and reports: 85-002-X201400114108
Description:
This annual Juristat article presents 2013 homicide data. Short and long-term trends in homicide are examined at the national, provincial/territorial and census metropolitan area levels. Gang-related homicides, firearm-related homicides, intimate partner homicides, youth homicides and international comparisons of homicide are also explored.
Release date: 2014-12-01
5. Survey Sampling In Official Statistics - Some Thoughts On Directions Archived
Articles and reports: 11-522-X201300014251
Description:
I present a modeller's perspective on the current status quo in official statistics surveys-based inference. In doing so, I try to identify the strengths and weaknesses of the design and model-based inferential positions that survey sampling, at least as far as the official statistics world is concerned, finds itself at present. I close with an example from adaptive survey design that illustrates why taking a model-based perspective (either frequentist or Bayesian) represents the best way for official statistics to avoid the debilitating 'inferential schizophrenia' that seems inevitable if current methodologies are applied to the emerging information requirements of today's world (and possibly even tomorrow's).
Release date: 2014-10-31
6. What Big Data May Mean for Surveys Archived
Articles and reports: 11-522-X201300014272
Description:
Two converging trends raise questions about the future of large-scale probability surveys conducted by or for National Statistical Institutes (NSIs). First, increasing costs and rising rates of nonresponse potentially threaten the cost-effectiveness and inferential value of surveys. Second, there is growing interest in Big Data as a replacement for surveys. There are many different types of Big Data, but the primary focus here is on data generated through social media. This paper supplements and updates an earlier paper on the topic (Couper, 2013). I review some of the concerns about Big Data, particularly from the survey perspective. I argue that there is a role for both high-quality surveys and big data analytics in the work of NSIs. While Big Data is unlikely to replace high-quality surveys, I believe the two methods can serve complementary functions. I attempt to identify some of the criteria that need to be met, and questions that need to be answered, before Big Data can be used for reliable population-based inference.
Release date: 2014-10-31
7. Study of the “product” sampling scheme as illustrated by the ELFE survey Archived
Articles and reports: 11-522-X201300014286
Description:
The Étude Longitudinale Française depuis l’Enfance (ELFE) [French longitudinal study from childhood on], which began in 2011, involves over 18,300 infants whose parents agreed to participate when they were in the maternity hospital. This cohort survey, which will track the children from birth to adulthood, covers the many aspects of their lives from the perspective of social science, health and environmental health. In randomly selected maternity hospitals, all infants in the target population, who were born on one of 25 days distributed across the four seasons, were chosen. This sample is the outcome of a non-standard sampling scheme that we call product sampling. In this survey, it takes the form of the cross-tabulation between two independent samples: a sampling of maternity hospitals and a sampling of days. While it is easy to imagine a cluster effect due to the sampling of maternity hospitals, one can also imagine a cluster effect due to the sampling of days. The scheme’s time dimension therefore cannot be ignored if the desired estimates are subject to daily or seasonal variation. While this non-standard scheme can be viewed as a particular kind of two-phase design, it needs to be defined within a more specific framework. Following a comparison of the product scheme with a conventional two-stage design, we propose variance estimators specially formulated for this sampling scheme. Our ideas are illustrated with a simulation study.
Release date: 2014-10-31
8. Demosim's Population Projection Model: Updates and New Developments Archived
Articles and reports: 11-522-X201300014289
Description:
This paper provides an overview of the main new features that will be added to the forthcoming version of the Demosim microsimulation projection model based on microdata from the 2011 National Household Survey. The paper first describes the additions to the base population, namely new variables, some of which are added to the National Household Survey data by means of data linkage. This is followed by a brief description of the methods being considered for the projection of language variables, citizenship and religion as examples of the new features for events simulated by the model.
Release date: 2014-10-31
9. Two approaches to linking census and hospital data Archived
Articles and reports: 82-003-X201401014098
Geography: Province or territory
Description:
This study compares registry and non-registry approaches to linking 2006 Census of Population data for Manitoba and Ontario to Hospital data from the Discharge Abstract Database.
Release date: 2014-10-15
10. Estimates of Cross-border Shopping, 2006 to 2012 Archived
Articles and reports: 13-604-M2014076
Description:
This article provides estimates on the value of cross-border shopping in the United States from 2006 to 2012, on an annual and quarterly basis. The study provides detailed values for overnight and same-day spending in the United States, postal and courier imports and motor vehicle imports. Total cross-border expenditures are compared to the Canadian retail trade sales, to provide a basis of comparison on the magnitude of these expenditures. The extent to which cross-border spending varies with movements in the Canadian/United States exchange rate is also examined. The cross-border estimates are derived from the Canadian System of National Accounts and their underlying survey and administrative data sources. The estimates are based on three different scenarios (low, medium and high) with each scenario based on different statistical assumptions. The low scenario represents the lower-bound estimates for cross-border shopping, while the high scenario represents the upper-bound estimates. The medium scenario is based on assumptions deemed to be the most plausible. All assumptions reflect professional judgement and build upon previous analysis.
Release date: 2014-10-08

Journals and periodicals (0)

Journals and periodicals (0) (0 results)

No content available at this time.

Report a problem or mistake on this page

Date modified:: 2024-05-26