Analysis

We propose a method for estimating the variance of estimators of changes over time, a method that takes account of all the components of these estimators: the sampling design, treatment of non-response, treatment of large companies, correlation of non-response from one wave to another, the effect of using a panel, robustification, and calibration using a ratio estimator. This method, which serves to determine the confidence intervals of changes over time, is then applied to the Swiss survey of value added.

The Internet's rapid and profound entry into our lives quite understandably makes people wonder how, both individually and collectively, we have been affected by it. When major shifts in technology use occur, utopian and dystopian views of their impact on society often abound, reflecting their disruptiveness and people's concerns. Given its complex uses, the Internet, both as a technology and as an environment, has had both beneficial and deleterious effects. Above all, though, it has had transformative effects.

Are Canadians becoming more isolated, more reclusive and less integrated in their communities as they use the Internet? Or, are they becoming more participatory and more integrated in their communities? In addition, do these communities still resemble traditional communities, or are they becoming more like social networks than cohesive groups?

To address these questions, this article organizes, analyzes and presents existing Canadian evidence. It uses survey results and research amassed by Statistics Canada and the Connected Lives project in Toronto to explore the role of the Internet in social engagement and the opportunities it represents for Canadians to be active citizens. It finds that Internet users are at least as socially engaged as non-users. They have large networks and frequent interactions with friends and family, although they tend to spend somewhat less in-person time and, of course, more time online. An appreciable number of Internet users are civically and politically engaged, using the Internet to find out about opportunities and make contact with others.

Small area prediction based on random effects, called EBLUP, is a procedure for constructing estimates for small geographical areas or small subpopulations using existing survey data. The total of the small area predictors is often forced to equal the direct survey estimate and such predictors are said to be calibrated. Several calibrated predictors are reviewed and a criterion that unifies the derivation of these calibrated predictors is presented. The predictor that is the unique best linear unbiased predictor under the criterion is derived and the mean square error of the calibrated predictors is discussed. Implicit in the imposition of the restriction is the possibility that the small area model is misspecified and the predictors are biased. Augmented models with one additional explanatory variable for which the usual small area predictors achieve the self-calibrated property are considered. Simulations demonstrate that calibrated predictors have slightly smaller bias compared to those of the usual EBLUP predictor. However, if the bias is a concern, a better approach is to use an augmented model with an added auxiliary variable that is a function of area size. In the simulation, the predictors based on the augmented model had smaller MSE than EBLUP when the incorrect model was used for prediction. Furthermore, there was a very small increase in MSE relative to EBLUP if the auxiliary variable was added to the correct model.

Traditionally administrative hospital discharge databases have been mainly used for administrative purposes. Recently, health services researchers and population health researchers have been using the databases for a wide variety of studies; in particular health care outcomes. Tools, such as comorbidity indexes, have been developed to facilitate this analysis. Every time the coding system for diagnoses and procedures is revised or a new one is developed, these comorbidity indexes need to be updated. These updates are important in maintaining consistency when trends are examined over time.

We propose a method for estimating the variance of estimators of changes over time, a method that takes account of all the components of these estimators: the sampling design, treatment of non-response, treatment of large companies, correlation of non-response from one wave to another, the effect of using a panel, robustification, and calibration using a ratio estimator. This method, which serves to determine the confidence intervals of changes over time, is then applied to the Swiss survey of value added.

The Internet's rapid and profound entry into our lives quite understandably makes people wonder how, both individually and collectively, we have been affected by it. When major shifts in technology use occur, utopian and dystopian views of their impact on society often abound, reflecting their disruptiveness and people's concerns. Given its complex uses, the Internet, both as a technology and as an environment, has had both beneficial and deleterious effects. Above all, though, it has had transformative effects.

Are Canadians becoming more isolated, more reclusive and less integrated in their communities as they use the Internet? Or, are they becoming more participatory and more integrated in their communities? In addition, do these communities still resemble traditional communities, or are they becoming more like social networks than cohesive groups?

To address these questions, this article organizes, analyzes and presents existing Canadian evidence. It uses survey results and research amassed by Statistics Canada and the Connected Lives project in Toronto to explore the role of the Internet in social engagement and the opportunities it represents for Canadians to be active citizens. It finds that Internet users are at least as socially engaged as non-users. They have large networks and frequent interactions with friends and family, although they tend to spend somewhat less in-person time and, of course, more time online. An appreciable number of Internet users are civically and politically engaged, using the Internet to find out about opportunities and make contact with others.

Small area prediction based on random effects, called EBLUP, is a procedure for constructing estimates for small geographical areas or small subpopulations using existing survey data. The total of the small area predictors is often forced to equal the direct survey estimate and such predictors are said to be calibrated. Several calibrated predictors are reviewed and a criterion that unifies the derivation of these calibrated predictors is presented. The predictor that is the unique best linear unbiased predictor under the criterion is derived and the mean square error of the calibrated predictors is discussed. Implicit in the imposition of the restriction is the possibility that the small area model is misspecified and the predictors are biased. Augmented models with one additional explanatory variable for which the usual small area predictors achieve the self-calibrated property are considered. Simulations demonstrate that calibrated predictors have slightly smaller bias compared to those of the usual EBLUP predictor. However, if the bias is a concern, a better approach is to use an augmented model with an added auxiliary variable that is a function of area size. In the simulation, the predictors based on the augmented model had smaller MSE than EBLUP when the incorrect model was used for prediction. Furthermore, there was a very small increase in MSE relative to EBLUP if the auxiliary variable was added to the correct model.

Traditionally administrative hospital discharge databases have been mainly used for administrative purposes. Recently, health services researchers and population health researchers have been using the databases for a wide variety of studies; in particular health care outcomes. Tools, such as comorbidity indexes, have been developed to facilitate this analysis. Every time the coding system for diagnoses and procedures is revised or a new one is developed, these comorbidity indexes need to be updated. These updates are important in maintaining consistency when trends are examined over time.