Data analysis
Filter results by
Search HelpKeyword(s)
Type
Results
All (3)
All (3) ((3 results))
- 1. Producing Hours Worked for the SNA in Order to Measure Productivity: The Canadian Experience ArchivedSurveys and statistical programs – Documentation: 15-206-X2006004Description:
This paper provides a brief description of the methodology currently used to produce the annual volume of hours worked consistent with the System of National Accounts (SNA). These data are used for labour input in the annual and quarterly measures of labour productivity, as well as in the annual measures of multifactor productivity. For this purpose, hours worked are broken down by educational level and age group, so that changes in the composition of the labour force can be taken into account. They are also used to calculate hourly compensation and the unit labour cost and for simulations of the SNA Input-Output Model; as such, they are integrated as labour force inputs into most SNA satellite accounts (i.e., environment, tourism).
Release date: 2006-10-27 - Articles and reports: 12-001-X20050029048Description:
We consider a problem in which an analysis is needed for categorical data from a single two-way table with partial classification (i.e., both item and unit nonresponses). We assume that this is the only information available. A Bayesian methodology permits modeling different patterns of missingness under ignorability and nonignorability assumptions. We construct a nonignorable nonresponse model which is obtained from the ignorable nonresponse model via a model expansion using a data-dependent prior; the nonignorable nonresponse model robustifies the ignorable nonresponse model. A multinomial-Dirichlet model, adjusted for the nonresponse, is used to estimate the cell probabilities, and a Bayes factor is used to test for association. We illustrate our methodology using data on bone mineral density and family income. A sensitivity analysis is used to assess the effects of the data-dependent prior. The ignorable and nonignorable nonresponse models are compared using a simulation study, and there are subtle differences between these models.
Release date: 2006-02-17 - 3. On the correlation structure of sample units ArchivedArticles and reports: 12-001-X20050029050Description:
In this paper we make explicit some distributional properties of sample units, not usually found in the literature; in particular, their correlation structure and the fact that it does not depend on arbitrarily assigned population indices. Such properties are relevant to a number of estimation procedures, whose efficiency would benefit from making explicit reference to them.
Release date: 2006-02-17
Data (0)
Data (0) (0 results)
No content available at this time.
Analysis (2)
Analysis (2) ((2 results))
- Articles and reports: 12-001-X20050029048Description:
We consider a problem in which an analysis is needed for categorical data from a single two-way table with partial classification (i.e., both item and unit nonresponses). We assume that this is the only information available. A Bayesian methodology permits modeling different patterns of missingness under ignorability and nonignorability assumptions. We construct a nonignorable nonresponse model which is obtained from the ignorable nonresponse model via a model expansion using a data-dependent prior; the nonignorable nonresponse model robustifies the ignorable nonresponse model. A multinomial-Dirichlet model, adjusted for the nonresponse, is used to estimate the cell probabilities, and a Bayes factor is used to test for association. We illustrate our methodology using data on bone mineral density and family income. A sensitivity analysis is used to assess the effects of the data-dependent prior. The ignorable and nonignorable nonresponse models are compared using a simulation study, and there are subtle differences between these models.
Release date: 2006-02-17 - 2. On the correlation structure of sample units ArchivedArticles and reports: 12-001-X20050029050Description:
In this paper we make explicit some distributional properties of sample units, not usually found in the literature; in particular, their correlation structure and the fact that it does not depend on arbitrarily assigned population indices. Such properties are relevant to a number of estimation procedures, whose efficiency would benefit from making explicit reference to them.
Release date: 2006-02-17
Reference (1)
Reference (1) ((1 result))
- 1. Producing Hours Worked for the SNA in Order to Measure Productivity: The Canadian Experience ArchivedSurveys and statistical programs – Documentation: 15-206-X2006004Description:
This paper provides a brief description of the methodology currently used to produce the annual volume of hours worked consistent with the System of National Accounts (SNA). These data are used for labour input in the annual and quarterly measures of labour productivity, as well as in the annual measures of multifactor productivity. For this purpose, hours worked are broken down by educational level and age group, so that changes in the composition of the labour force can be taken into account. They are also used to calculate hourly compensation and the unit labour cost and for simulations of the SNA Input-Output Model; as such, they are integrated as labour force inputs into most SNA satellite accounts (i.e., environment, tourism).
Release date: 2006-10-27
- Date modified: