Keyword search
Filter results by
Search HelpKeyword(s)
Subject
Type
Year of publication
Survey or statistical program
Results
All (15)
All (15) (0 to 10 of 15 results)
- Articles and reports: 11-522-X202100100012Description: The modernization of price statistics by National Statistical Offices (NSO) such as Statistics Canada focuses on the adoption of alternative data sources that include the near-universe of all products sold in the country, a scale that requires machine learning classification of the data. The process of evaluating classifiers to select appropriate ones for production, as well as monitoring classifiers once in production, needs to be based on robust metrics to measure misclassification. As commonly utilized metrics, such as the Fß-score may not take into account key aspects applicable to prices statistics in all cases, such as unequal importance of categories, a careful consideration of the metric space is necessary to select appropriate methods to evaluate classifiers. This working paper provides insight on the metric space applicable to price statistics and proposes an operational framework to evaluate and monitor classifiers, focusing specifically on the needs of the Canadian Consumer Prices Index and demonstrating discussed metrics using a publicly available dataset.
Key Words: Consumer price index; supervised classification; evaluation metrics; taxonomy
Release date: 2021-11-05 - Articles and reports: 62F0014M2020016Description:
A summary of methodological treatments as applied to the August 2020 CPI in response to the effects of the COVID-19 pandemic on price collection, price availability, and business closures.
Release date: 2020-09-16 - Articles and reports: 62F0014M2020011Description:
A summary of methodological treatments as applied to the June 2020 CPI in response to the effects of the COVID-19 pandemic on price collection, price availability, and business closure.
Release date: 2020-07-22 - Articles and reports: 62F0014M2020009Description:
A summary of methodological treatments as applied to the May 2020 CPI in response to the effects of the COVID-19 pandemic on price collection, price availability, and business closures.
Release date: 2020-06-17 - 5. Low Income Lines, 2012-2013 ArchivedArticles and reports: 75F0002M2014003Description:
In order to provide a holographic or complete picture of low income, Statistics Canada uses three complementary low income lines: the Low Income Cut-offs (LICOs), the Low Income Measures (LIMs) and the Market Basket Measure (MBM). While the first two lines were developed by Statistics Canada, the MBM is based on concepts developed by Employment and Social Development Canada. Though these measures differ from one another, they give a generally consistent picture of low income status over time. None of these measures is the best. Each contributes its own perspective and its own strengths to the study of low income, so that cumulatively, the three provide a better understanding of the phenomenon of low income as a whole. These measures are not measures of poverty, but strictly measures of low income.
Release date: 2014-12-10 - Articles and reports: 75F0002M2009002Description:
Low income cut-offs (LICOs) are income thresholds, determined by analysing family expenditure data, below which families will devote a larger share of income to the necessities of food, shelter and clothing than the average family would. To reflect differences in the costs of necessities among different community and family sizes, LICOs are defined for five categories of community size and seven of family size.
Low income measures (LIMs), on the other hand, are strictly relative measures of low income, set at 50% of adjusted median family income. These measures are categorized according to the number of adults and children present in families, reflecting the economies of scale inherent in family size and composition. This publication incorporates a detailed description of the methods used to arrive at both measurements. It also explains how base years are defined and how LICOs are updated using the Consumer Price Index.
Release date: 2009-06-03 - Articles and reports: 75F0002M2008006Geography: Province or territoryDescription:
Comparisons of low income between regions may have impacts on policy choices. However, it is often argued that rankings of distributions are not robust and that they are also quite sensitive to methods of defining low income. This paper avoids these problems by using a stochastic dominance approach to compare regional low income profiles in Canada without arbitrarily specifying a low-income line. This analysis is carried out for the 10 provinces using the Survey of Labour and Income Dynamics for 2000. Robustness of the results is also verified with respect to different choices of spatial price deflators and equivalence scales. The extent to which the findings are sensitive to the choice of an absolute or a relative concept of low income is also examined. We show that, in most cases, dominance relations can be determined and regional low income can be ordered for a wide range of low-income lines. We also show that dominance results are robust to the choice of equivalence scales, while rank reversal occurs when alternative cost-of-living deflators are used. Switching from an absolute to a relative low-income concept only affects low-income rankings for Ontario, Quebec and the Prairie provinces, but not in the case of other provinces. Nevertheless, for all scales, we find that low income is greatest in British Columbia.
Release date: 2008-10-09 - Articles and reports: 12-001-X20060029554Description:
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.
Release date: 2006-12-21 - Surveys and statistical programs – Documentation: 62F0026M2005005Description:
This discussion paper reviews the previous research into the subject of presenting historical time series and comparisons in constant dollars for the Survey of Household Spending (SHS), and its predecessor the Family Expenditure Survey (FAMEX). It examines two principal methods of converting spending data into constant dollars. The purpose of this discussion paper is to show interested parties how the two methods differ in complexity of implementation and interpretation.
Release date: 2005-07-15 - Articles and reports: 75F0002M2004001Description:
The purpose of this document is to describe the detailed methodology and assumptions behind the construction of the market basket measure (MBM) of low income. Also this document will raise some issues and highlight some data limitations related to the MBM.
The MBM represents the cost of a basket that includes a nutritious diet, clothing and footwear, shelter, transportation, and other necessary goods and services (such as personal care items or household supplies).
The MBM methodology was developed by the Federal/Provincial/Territorial Working Group on Social Development Research and Information for Human Resources Development Canada (HRDC).
Release date: 2004-02-04
Data (0)
Data (0) (0 results)
No content available at this time.
Analysis (13)
Analysis (13) (0 to 10 of 13 results)
- Articles and reports: 11-522-X202100100012Description: The modernization of price statistics by National Statistical Offices (NSO) such as Statistics Canada focuses on the adoption of alternative data sources that include the near-universe of all products sold in the country, a scale that requires machine learning classification of the data. The process of evaluating classifiers to select appropriate ones for production, as well as monitoring classifiers once in production, needs to be based on robust metrics to measure misclassification. As commonly utilized metrics, such as the Fß-score may not take into account key aspects applicable to prices statistics in all cases, such as unequal importance of categories, a careful consideration of the metric space is necessary to select appropriate methods to evaluate classifiers. This working paper provides insight on the metric space applicable to price statistics and proposes an operational framework to evaluate and monitor classifiers, focusing specifically on the needs of the Canadian Consumer Prices Index and demonstrating discussed metrics using a publicly available dataset.
Key Words: Consumer price index; supervised classification; evaluation metrics; taxonomy
Release date: 2021-11-05 - Articles and reports: 62F0014M2020016Description:
A summary of methodological treatments as applied to the August 2020 CPI in response to the effects of the COVID-19 pandemic on price collection, price availability, and business closures.
Release date: 2020-09-16 - Articles and reports: 62F0014M2020011Description:
A summary of methodological treatments as applied to the June 2020 CPI in response to the effects of the COVID-19 pandemic on price collection, price availability, and business closure.
Release date: 2020-07-22 - Articles and reports: 62F0014M2020009Description:
A summary of methodological treatments as applied to the May 2020 CPI in response to the effects of the COVID-19 pandemic on price collection, price availability, and business closures.
Release date: 2020-06-17 - 5. Low Income Lines, 2012-2013 ArchivedArticles and reports: 75F0002M2014003Description:
In order to provide a holographic or complete picture of low income, Statistics Canada uses three complementary low income lines: the Low Income Cut-offs (LICOs), the Low Income Measures (LIMs) and the Market Basket Measure (MBM). While the first two lines were developed by Statistics Canada, the MBM is based on concepts developed by Employment and Social Development Canada. Though these measures differ from one another, they give a generally consistent picture of low income status over time. None of these measures is the best. Each contributes its own perspective and its own strengths to the study of low income, so that cumulatively, the three provide a better understanding of the phenomenon of low income as a whole. These measures are not measures of poverty, but strictly measures of low income.
Release date: 2014-12-10 - Articles and reports: 75F0002M2009002Description:
Low income cut-offs (LICOs) are income thresholds, determined by analysing family expenditure data, below which families will devote a larger share of income to the necessities of food, shelter and clothing than the average family would. To reflect differences in the costs of necessities among different community and family sizes, LICOs are defined for five categories of community size and seven of family size.
Low income measures (LIMs), on the other hand, are strictly relative measures of low income, set at 50% of adjusted median family income. These measures are categorized according to the number of adults and children present in families, reflecting the economies of scale inherent in family size and composition. This publication incorporates a detailed description of the methods used to arrive at both measurements. It also explains how base years are defined and how LICOs are updated using the Consumer Price Index.
Release date: 2009-06-03 - Articles and reports: 75F0002M2008006Geography: Province or territoryDescription:
Comparisons of low income between regions may have impacts on policy choices. However, it is often argued that rankings of distributions are not robust and that they are also quite sensitive to methods of defining low income. This paper avoids these problems by using a stochastic dominance approach to compare regional low income profiles in Canada without arbitrarily specifying a low-income line. This analysis is carried out for the 10 provinces using the Survey of Labour and Income Dynamics for 2000. Robustness of the results is also verified with respect to different choices of spatial price deflators and equivalence scales. The extent to which the findings are sensitive to the choice of an absolute or a relative concept of low income is also examined. We show that, in most cases, dominance relations can be determined and regional low income can be ordered for a wide range of low-income lines. We also show that dominance results are robust to the choice of equivalence scales, while rank reversal occurs when alternative cost-of-living deflators are used. Switching from an absolute to a relative low-income concept only affects low-income rankings for Ontario, Quebec and the Prairie provinces, but not in the case of other provinces. Nevertheless, for all scales, we find that low income is greatest in British Columbia.
Release date: 2008-10-09 - Articles and reports: 12-001-X20060029554Description:
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.
Release date: 2006-12-21 - Articles and reports: 75F0002M2004001Description:
The purpose of this document is to describe the detailed methodology and assumptions behind the construction of the market basket measure (MBM) of low income. Also this document will raise some issues and highlight some data limitations related to the MBM.
The MBM represents the cost of a basket that includes a nutritious diet, clothing and footwear, shelter, transportation, and other necessary goods and services (such as personal care items or household supplies).
The MBM methodology was developed by the Federal/Provincial/Territorial Working Group on Social Development Research and Information for Human Resources Development Canada (HRDC).
Release date: 2004-02-04 - 10. Recent Developments in the Low Income Cut-offs ArchivedArticles and reports: 75F0002M2001003Description:
This paper outlines the results of an investigation into three aspects of the low income cut-offs: the behaviour of a proposed 'annually updated' low income series, the addition of payroll taxes, and the restructuring of the matrix of 35 cut-offs.
Release date: 2001-07-13
Reference (2)
Reference (2) ((2 results))
- Surveys and statistical programs – Documentation: 62F0026M2005005Description:
This discussion paper reviews the previous research into the subject of presenting historical time series and comparisons in constant dollars for the Survey of Household Spending (SHS), and its predecessor the Family Expenditure Survey (FAMEX). It examines two principal methods of converting spending data into constant dollars. The purpose of this discussion paper is to show interested parties how the two methods differ in complexity of implementation and interpretation.
Release date: 2005-07-15 - 2. User Guide - Survey of Household Spending, 2000 ArchivedSurveys and statistical programs – Documentation: 62F0026M2001004Geography: Province or territoryDescription:
This guide presents information of interest to users of data from the Survey of Household Spending. Data are collected via personal interview conducted in January, February and March after the reference year using a paper questionnaire. Information is gathered about the spending habits, dwelling characteristics and household equipment of Canadian households during the reference year. The survey covers private households in the ten provinces. (The three territories are surveyed every second year starting in 2001.)
This guide includes definitions of survey terms and variables, as well as descriptions of survey methodology and data quality. There is also a section describing the various statistics that can be created using expenditure data (e.g., budget share, market share, and aggregates).
Release date: 2001-12-12
- Date modified: