Statistics by subject – Statistical methods

Other available resources to support your research.

Help for sorting results
Browse our central repository of key standard concepts, definitions, data sources and methods.
Loading
Loading in progress, please wait...
All (20)

All (20) (20 of 20 results)

  • Articles and reports: 12-001-X198500214402
    Description:

    A methodology has been developed for producing population estimates by single years of age and sex for small areas (census divisions and census metropolitan areas). To assure reliability, the estimates by single years of age are grouped into five years and only these grouped data are recomended for dissemination. They are based on the age-sex composition of population from the last census, births by sex, deaths by single years of age and sex, estimates of migration by age and sex, and counts of family allowance recipients in the age group 1-14 years.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214379
    Description:

    In Canada, provincial and federal demographers have attempted to use various sets of administrative data to estimate migration flows. This paper presents the development of intra-provincial migration estimates using driver’s licence data in Ontario. An evaluation of these migration estimates has been carried out by comparing with those derived from the income tax data by Statistics Canada. Both files provide equally good and complimentary estimates of intra-provincial migration.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214380
    Description:

    This paper examines the use of administrative files from Alberta’s Health Care Insurance Plans combined with Vital Statistics data as inputs for estimating population. Results, which are presented and compared with Census data, indicate that Health Care data can be used to produce accurate population estimates at the provincial level and for smaller areas such as census divisions and municipalities.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214636
    Description:

    There are many people called statisticians who carry out a very diverse set of activities which are labelled statistics. As part of the invited address at the 1985 meeting of the Statistical Society of Canada, the author presents his views and discusses the nature of the relationships between the different types of statisticians.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214403
    Description:

    Statistics Canada’s current methodologies forestimating the population of census divisions and census metropolitan areas are the regression-nested and component methods. This paper presents the experience with these estimates for the period 1981 to 1985, focusing on problems encountered with the input data on family allowance recipients.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214378
    Description:

    Twelve administrative data files are reviewed to determine if some of them could be used to derive migration data, in case the universality of the currently used family allowance files be limited, as a result of federal legislation.

    It is found that none of the twelve files have strengths and weaknesses strictly comparable to those of the family allowance files. Further developments of the Health Care, and to a lesser extent the Old Age Security files are highly recommended.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214376
    Description:

    This study purports to assess whether there are temporal relationships between Unemployment Insurance Beneficiaries, Total Unemployment, Job Losers and Job Leavers in Canada using univariate and multivariate time series methods. The results indicate that during 1975-82 the Unemployment Insurance Beneficiaries series leads: (1) Total Unemployment by one month and (2) Job Leavers by two months. On the other hand, there are evidence of a feedback relationship between Unemployment Insurance Beneficiaries and Job Losers.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214374
    Description:

    In this paper estimation of multiple characters in multiple frame surveys has been investigated. The gain due to two character study in a common survey, over separate surveys for individual characters, has been obtained. Cost comparison is also made between two character multi frame survey and two character single frame survey.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214401
    Description:

    This paper describes a method of producing current age/sex specific population estimates for small areas utilizing as inputs total population estimates, birth and death data and estimates of historical residual net migration. An evaluation based on the 1981 Census counts for census divisions and school districts in British Columbia is presented.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214400
    Description:

    The accuracy of small area population estimates derived from a regression based model is heavily dependent on the ability of the indicator data selected to accurately reflect population change. Hence, prior knowledge as to the characteristics of the administrative data used as potential population indicators in a regression model is important. This report summarizes the strengths and weaknesses associated with the use of residential hydro accounts in the British Columbia regression based population estimation model.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214375
    Description:

    This paper analyzes the revisions of eight seasonally adjusted labour force series during recession and non-recession periods. The four seasonal adjustment methods applied are X-11 and X-11-ARIMA using either concurrent or forecast seasonal factors. The series are seasonally adjusted with these four methodologies according to both a multiplicative and an additive decomposition model. The results indicate that the X-11-ARIMA concurrent adjustment yields the smallest revisions both during recession and non-recession periods regardless of the decomposition model used.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214372
    Description:

    The use of a multivariate clustering algorithm to perform stratification for the Labour Force Survey is described. The algorithm developed by Friedman and Rubin (1967) is modified to allow the formation of geographically contiguous strata and to delineate heterogeneous but compact primary sampling units (PSUs) within these strata. Studies dealing with stratification variables, stratification robustness over time, and type of stratification are described.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214377
    Description:

    Thirty basic principles of questionnaire design are presented covering the content, wording, format, and testing of questionnaires. The extent to which the questionnaire is an integral part of the survey is emphasized as is consideration of its relationship with other aspects of survey design.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214373
    Description:

    In the first part of the paper a review of the historical literature concerning microfilmed manuscript census records is given. Several types of sampling designs have been used ranging in complexity from cluster and stratified random sampling to stratified two-stage cluster sampling. In the second part, a method is given to create a public use sample tape of the 1881 Census of Canada. This work was part of a pilot project for Public Archives of Canada and was carried out by the Social Science Computing Laboratory of the University of Western Ontario. The pilot project was designed to determine the merit and technical and economic feasibility of developing machine readable products from microfilm copies of the 1881 Census of Canada.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500114359
    Description:

    Unit and item nonresponse almost always occur in surveys and censuses. The larger its size the larger its potential effect will be on survey estimates. It is, therefore, important to cope with it at every stage where they can be affected. At varying degrees the size of nonresponse can be coped with at design, field and processing stages. The nonresponse problems have an impact on estimation formulas for various statistics as a result of imputations and weight adjustments along with survey weights in the estimates of means, totals, or other statistics. The formulas may be decomposed into components that include response errors, the effect of weight adjustment for unit nonresponse, and the effect of substitution for nonresponse. The impacts of the design, field, and processing stages on the components of the estimates are examined.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114367
    Description:

    The synthetic estimator (SYN) has been traditionally used to estimate characteristics of small domains. Although it has the advantage of a small variance, it can be seriously biased in some small domains which depart in structure from the overall domains. Särndal (1981) introduced the regression estimator (REG) in the context of domain estimation. This estimator is nearly unbiased, however, it has two drawbacks; (i) its variance can be considerable in some small domains and (ii) it can take on negative values in situations that do not allow such values.

    In this paper, we report on a compromise estimator which strikes a balance between the two estimators SYN and REG. This estimator, called the modified regression estimator (MRE), has the advantage of a considerably reduced variance compared to the REG estimator and has a smaller Mean Squared Error than the SYN estimator in domains where the latter is badly biased. The MRE estimator eliminates the drawback with negative values mentioned above. These results are supported by a Monte Carlo study involving 500 samples.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114366
    Description:

    This study is mainly concerned with an evaluation of the forecasting performance of a set of the most often applied ARIMA models. These models were fitted to a sample of two hundred seasonal time series chosen from eleven sectors of the Canadian economy. The performance of the models was judged according to eight variable criteria, namely: average forecast error for the last three years, the chi-square statistic for the randomness of the residuals, the presence of small parameters, overdifferencing, underdifferencing, correlation between the parameters, stationarity and invertibility. Overall and conditional rankings of the models are obtained and graphs are presented.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114371
    Description:

    This paper presents an overview of the methodology used in the processing of the 1981 Census of Agriculture data. The edit and imputation techniques are stressed, with emphasis on the multivariate search algorithm. A brief evaluation of the system’s performance is given.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114365
    Description:

    The cost-variance optimization of the design of the Canadian Labour Force Survey was carried out in two steps. First, the sample designs were optimized for each of the two major area types, the Self-Representing (SR) and the Non-Self-Representing (NSR) areas. Cost models were developed and parameters estimated from a detailed field study and by simulation, while variances were estimated using data from the Census of Population. The scope of the optimization included the allocation of sample to the two stages in the SR design, and the consideration of two alternatives to the old design in NSR areas. The second stage of optimization was the allocation of sample to SR and NSR areas.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114364
    Description:

    Conventional methods of inference in survey sampling are critically examined. The need for conditioning the inference on recognizable subsets of the population is emphasized. A number of real examples involving random sample sizes are presented to illustrate inferences conditional on the realized sample configuration and associated difficulties. The examples include the following: estimation of (a) population mean under simple random sampling; (b) population mean in the presence of outliers; (c) domain total and domain mean; (d) population mean with two-way stratification; (e) population mean in the presence of non-responses; (f) population mean under general designs. The conditional bias and the conditional variance of estimators of a population mean (or a domain mean or total), and the associated confidence intervals, are examined.

    Release date: 1985-06-14

Data (0)

Data (0) (0 results)

Your search for "" found no results in this section of the site.

You may try:

Analysis (20)

Analysis (20) (20 of 20 results)

  • Articles and reports: 12-001-X198500214402
    Description:

    A methodology has been developed for producing population estimates by single years of age and sex for small areas (census divisions and census metropolitan areas). To assure reliability, the estimates by single years of age are grouped into five years and only these grouped data are recomended for dissemination. They are based on the age-sex composition of population from the last census, births by sex, deaths by single years of age and sex, estimates of migration by age and sex, and counts of family allowance recipients in the age group 1-14 years.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214379
    Description:

    In Canada, provincial and federal demographers have attempted to use various sets of administrative data to estimate migration flows. This paper presents the development of intra-provincial migration estimates using driver’s licence data in Ontario. An evaluation of these migration estimates has been carried out by comparing with those derived from the income tax data by Statistics Canada. Both files provide equally good and complimentary estimates of intra-provincial migration.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214380
    Description:

    This paper examines the use of administrative files from Alberta’s Health Care Insurance Plans combined with Vital Statistics data as inputs for estimating population. Results, which are presented and compared with Census data, indicate that Health Care data can be used to produce accurate population estimates at the provincial level and for smaller areas such as census divisions and municipalities.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214636
    Description:

    There are many people called statisticians who carry out a very diverse set of activities which are labelled statistics. As part of the invited address at the 1985 meeting of the Statistical Society of Canada, the author presents his views and discusses the nature of the relationships between the different types of statisticians.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214403
    Description:

    Statistics Canada’s current methodologies forestimating the population of census divisions and census metropolitan areas are the regression-nested and component methods. This paper presents the experience with these estimates for the period 1981 to 1985, focusing on problems encountered with the input data on family allowance recipients.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214378
    Description:

    Twelve administrative data files are reviewed to determine if some of them could be used to derive migration data, in case the universality of the currently used family allowance files be limited, as a result of federal legislation.

    It is found that none of the twelve files have strengths and weaknesses strictly comparable to those of the family allowance files. Further developments of the Health Care, and to a lesser extent the Old Age Security files are highly recommended.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214376
    Description:

    This study purports to assess whether there are temporal relationships between Unemployment Insurance Beneficiaries, Total Unemployment, Job Losers and Job Leavers in Canada using univariate and multivariate time series methods. The results indicate that during 1975-82 the Unemployment Insurance Beneficiaries series leads: (1) Total Unemployment by one month and (2) Job Leavers by two months. On the other hand, there are evidence of a feedback relationship between Unemployment Insurance Beneficiaries and Job Losers.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214374
    Description:

    In this paper estimation of multiple characters in multiple frame surveys has been investigated. The gain due to two character study in a common survey, over separate surveys for individual characters, has been obtained. Cost comparison is also made between two character multi frame survey and two character single frame survey.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214401
    Description:

    This paper describes a method of producing current age/sex specific population estimates for small areas utilizing as inputs total population estimates, birth and death data and estimates of historical residual net migration. An evaluation based on the 1981 Census counts for census divisions and school districts in British Columbia is presented.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214400
    Description:

    The accuracy of small area population estimates derived from a regression based model is heavily dependent on the ability of the indicator data selected to accurately reflect population change. Hence, prior knowledge as to the characteristics of the administrative data used as potential population indicators in a regression model is important. This report summarizes the strengths and weaknesses associated with the use of residential hydro accounts in the British Columbia regression based population estimation model.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214375
    Description:

    This paper analyzes the revisions of eight seasonally adjusted labour force series during recession and non-recession periods. The four seasonal adjustment methods applied are X-11 and X-11-ARIMA using either concurrent or forecast seasonal factors. The series are seasonally adjusted with these four methodologies according to both a multiplicative and an additive decomposition model. The results indicate that the X-11-ARIMA concurrent adjustment yields the smallest revisions both during recession and non-recession periods regardless of the decomposition model used.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214372
    Description:

    The use of a multivariate clustering algorithm to perform stratification for the Labour Force Survey is described. The algorithm developed by Friedman and Rubin (1967) is modified to allow the formation of geographically contiguous strata and to delineate heterogeneous but compact primary sampling units (PSUs) within these strata. Studies dealing with stratification variables, stratification robustness over time, and type of stratification are described.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214377
    Description:

    Thirty basic principles of questionnaire design are presented covering the content, wording, format, and testing of questionnaires. The extent to which the questionnaire is an integral part of the survey is emphasized as is consideration of its relationship with other aspects of survey design.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500214373
    Description:

    In the first part of the paper a review of the historical literature concerning microfilmed manuscript census records is given. Several types of sampling designs have been used ranging in complexity from cluster and stratified random sampling to stratified two-stage cluster sampling. In the second part, a method is given to create a public use sample tape of the 1881 Census of Canada. This work was part of a pilot project for Public Archives of Canada and was carried out by the Social Science Computing Laboratory of the University of Western Ontario. The pilot project was designed to determine the merit and technical and economic feasibility of developing machine readable products from microfilm copies of the 1881 Census of Canada.

    Release date: 1985-12-16

  • Articles and reports: 12-001-X198500114359
    Description:

    Unit and item nonresponse almost always occur in surveys and censuses. The larger its size the larger its potential effect will be on survey estimates. It is, therefore, important to cope with it at every stage where they can be affected. At varying degrees the size of nonresponse can be coped with at design, field and processing stages. The nonresponse problems have an impact on estimation formulas for various statistics as a result of imputations and weight adjustments along with survey weights in the estimates of means, totals, or other statistics. The formulas may be decomposed into components that include response errors, the effect of weight adjustment for unit nonresponse, and the effect of substitution for nonresponse. The impacts of the design, field, and processing stages on the components of the estimates are examined.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114367
    Description:

    The synthetic estimator (SYN) has been traditionally used to estimate characteristics of small domains. Although it has the advantage of a small variance, it can be seriously biased in some small domains which depart in structure from the overall domains. Särndal (1981) introduced the regression estimator (REG) in the context of domain estimation. This estimator is nearly unbiased, however, it has two drawbacks; (i) its variance can be considerable in some small domains and (ii) it can take on negative values in situations that do not allow such values.

    In this paper, we report on a compromise estimator which strikes a balance between the two estimators SYN and REG. This estimator, called the modified regression estimator (MRE), has the advantage of a considerably reduced variance compared to the REG estimator and has a smaller Mean Squared Error than the SYN estimator in domains where the latter is badly biased. The MRE estimator eliminates the drawback with negative values mentioned above. These results are supported by a Monte Carlo study involving 500 samples.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114366
    Description:

    This study is mainly concerned with an evaluation of the forecasting performance of a set of the most often applied ARIMA models. These models were fitted to a sample of two hundred seasonal time series chosen from eleven sectors of the Canadian economy. The performance of the models was judged according to eight variable criteria, namely: average forecast error for the last three years, the chi-square statistic for the randomness of the residuals, the presence of small parameters, overdifferencing, underdifferencing, correlation between the parameters, stationarity and invertibility. Overall and conditional rankings of the models are obtained and graphs are presented.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114371
    Description:

    This paper presents an overview of the methodology used in the processing of the 1981 Census of Agriculture data. The edit and imputation techniques are stressed, with emphasis on the multivariate search algorithm. A brief evaluation of the system’s performance is given.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114365
    Description:

    The cost-variance optimization of the design of the Canadian Labour Force Survey was carried out in two steps. First, the sample designs were optimized for each of the two major area types, the Self-Representing (SR) and the Non-Self-Representing (NSR) areas. Cost models were developed and parameters estimated from a detailed field study and by simulation, while variances were estimated using data from the Census of Population. The scope of the optimization included the allocation of sample to the two stages in the SR design, and the consideration of two alternatives to the old design in NSR areas. The second stage of optimization was the allocation of sample to SR and NSR areas.

    Release date: 1985-06-14

  • Articles and reports: 12-001-X198500114364
    Description:

    Conventional methods of inference in survey sampling are critically examined. The need for conditioning the inference on recognizable subsets of the population is emphasized. A number of real examples involving random sample sizes are presented to illustrate inferences conditional on the realized sample configuration and associated difficulties. The examples include the following: estimation of (a) population mean under simple random sampling; (b) population mean in the presence of outliers; (c) domain total and domain mean; (d) population mean with two-way stratification; (e) population mean in the presence of non-responses; (f) population mean under general designs. The conditional bias and the conditional variance of estimators of a population mean (or a domain mean or total), and the associated confidence intervals, are examined.

    Release date: 1985-06-14

Reference (0)

Reference (0) (0 results)

Your search for "" found no results in this section of the site.

You may try:

Date modified: