Search

Sampling a rare and clustered trait in a finite population is challenging: traditional sampling designs usually require a large sample size in order to obtain reasonably accurate estimates, resulting in a considerable investment of resources in front of the detection of a small number of cases. A notable example is the case of WHO’s tuberculosis (TB) prevalence surveys, crucial for countries that bear a high TB burden, the prevalence of cases being still less than 1%. In the latest WHO guidelines, spatial patterns are not explicitly accounted for, with the risk of missing a large number of cases; moreover, cost and logistic constraints can pose further problems. After reviewing the methodology in use by WHO, the use of adaptive and sequential approaches is discussed as natural alternatives to improve over the limits of the current practice. A simulation study is presented to highlight possible advantages and limitations of these alternatives, and an integrated approach, combining both adaptive and sequential features in a single sampling strategy is advocated as a promising methodological perspective.

Worldwide, monthly CPIs are mostly calculated as weighted averages of price relatives with fixed base weights. The main source of estimation of CPI weights are National Accounts, whose complexity in terms of data collection, estimation of aggregates and validation procedures leads to several months of delay in the release of the figures. This ends up in a non completely consistent Laspeyres formula since the weights do not refer to the same period as the base prices do, being older by one year and then corrected by the elapsed inflation. In this paper we propose to forecast CPI weights via a compositional VAR model, to obtain more updated weights and, consequently, a more updated measure of inflation through CPIs.

Sampling a rare and clustered trait in a finite population is challenging: traditional sampling designs usually require a large sample size in order to obtain reasonably accurate estimates, resulting in a considerable investment of resources in front of the detection of a small number of cases. A notable example is the case of WHO’s tuberculosis (TB) prevalence surveys, crucial for countries that bear a high TB burden, the prevalence of cases being still less than 1%. In the latest WHO guidelines, spatial patterns are not explicitly accounted for, with the risk of missing a large number of cases; moreover, cost and logistic constraints can pose further problems. After reviewing the methodology in use by WHO, the use of adaptive and sequential approaches is discussed as natural alternatives to improve over the limits of the current practice. A simulation study is presented to highlight possible advantages and limitations of these alternatives, and an integrated approach, combining both adaptive and sequential features in a single sampling strategy is advocated as a promising methodological perspective.

We show how to handle the information which is acquired in a dynamic framework when there are multiple items in a survey collected on the same individuals at different time occasions. The response variables are commonly measured on an ordinal scale and the data may show a non-monotone missing pattern. The underlying phenomenon which is related to the interest of the survey may be modelled by a latent stochastic process. The latter having dependences according to a Markov structure is able to capture the heterogeneity of the response behaviour and to account for the measurement errors that naturally arise in the survey. The maximum likelihood estimation of the model parameters allows us to handle the missing data and to take advantage of the information provided by those individuals not showing complete responses. In a similar way, it is possible to consider a counterfactual framework in which the outcomes of interest are not directly observable even for the selected treatment. Such a flexible modelling approach is illustrated with two examples based on real data.

In response-adaptive designs for clinical trials the probability to assign patients to treatments depends on previous patients’ allocations and responses. Some of these designs are based on urn models to construct randomized procedures for the allocation of the subjects to treatments and to incorporate information on treatment performances. In particular, we consider the class of randomly reinforced urn (RRU) models in which the proportion of subjects allocated to the superior treatment converges to one as the sample size increases to infinity. For this reason, RRU designs are not able to target any desired allocation proportion to satisfy different optimality criteria. To address this issue, we propose a new adaptive randomly reinforced urn (ARRU) design in which the allocation proportion converge to desired values defined as functions of the response distribution. In addition, we establish the convergence rate and a central limit theoremfor the allocation proportion in both the cases of equal and different responses means.

We show how to handle the information which is acquired in a dynamic framework when there are multiple items in a survey collected on the same individuals at different time occasions. The response variables are commonly measured on an ordinal scale and the data may show a non-monotone missing pattern. The underlying phenomenon which is related to the interest of the survey may be modelled by a latent stochastic process. The latter having dependences according to a Markov structure is able to capture the heterogeneity of the response behaviour and to account for the measurement errors that naturally arise in the survey. The maximum likelihood estimation of the model parameters allows us to handle the missing data and to take advantage of the information provided by those individuals not showing complete responses. In a similar way, it is possible to consider a counterfactual framework in which the outcomes of interest are not directly observable even for the selected treatment. Such a flexible modelling approach is illustrated with two examples based on real data.

The population ageing has become a global and worldwide phenomenon. Especially in Italy this process is strong and incontestable. In this scenario the work force ageing and the challenges that make urgent to find tools and measures to manage the oldest people can give to the “applied demographer” a significant role. Moving from the definition of active ageing we illustrate skills, activities and suggestions that a demographer could easily share with human resource managers interested in promoting strategies and policies enhancing employability and productivity of older workers. We report real experiences with ABB Italia, SOL Group and Italcementi. We finally give details on AMO (Age Management Observatory).

One popular approach to small area estimation when data are spatially correlated is to employ Simultaneous Autoregressive (SAR) random effects models to define the Spatial Empirical Best Linear Unbiased Predictor (SEBLUP). See Singh et al. (2005) and Pratesi and Salvati (2008). SAR models allow for spatial correlation in the error structure. An alternative approach that incorporates the spatial information in the regression model is to use Geographically Weighted Regression (GWR). See Brunsdon et al. (1996) and Fotheringham et al. (1997). GWR extends the traditional regression model by characterising the relationship between the outcome variable and the covariates via local rather than global parameters. In this paper we investigate GWR-based small area estimation under the M-quantile modelling approach (Chambers and Tzavidis, 2006). In particular, we integrate the concepts of outlier-robust small area estimation and borrowing strength over space within a unified modelling framework by specifying an M-quantile GWR model that is a local model for the M-quantiles of the conditional distribution of the outcome variable given the covariates. This model is then used to define an outlier-robust predictor of the small area characteristic of interest that also accounts for spatial association in the data. An additional important spin-off from applying the M-quantile GWR small area model is more efficient synthetic estimation for out of sample areas. We demonstrate the usefulness of this framework through both model-based as well as design-based simulation, with the latter based on a realistic survey data set. The paper concludes with an application to environmental data for predicting average levels of the Acid Neutralizing Capacity at 8-digit Hydrologic Unit Code level in the Northeast states of the U.S.A.

One popular approach to small area estimation when data are spatially correlated is to employ Simultaneous Autoregressive (SAR) random effects models to define the Spatial Empirical Best Linear Unbiased Predictor (SEBLUP). See Singh et al. (2005) and Pratesi and Salvati (2008). SAR models allow for spatial correlation in the error structure. An alternative approach that incorporates the spatial information in the regression model is to use Geographically Weighted Regression (GWR). See Brunsdon et al. (1996) and Fotheringham et al. (1997). GWR extends the traditional regression model by characterising the relationship between the outcome variable and the covariates via local rather than global parameters. In this paper we investigate GWR-based small area estimation under the M-quantile modelling approach (Chambers and Tzavidis, 2006). In particular, we integrate the concepts of outlier-robust small area estimation and borrowing strength over space within a unified modelling framework by specifying an M-quantile GWR model that is a local model for the M-quantiles of the conditional distribution of the outcome variable given the covariates. This model is then used to define an outlier-robust predictor of the small area characteristic of interest that also accounts for spatial association in the data. An additional important spin-off from applying the M-quantile GWR small area model is more efficient synthetic estimation for out of sample areas. We demonstrate the usefulness of this framework through both model-based as well as design-based simulation, with the latter based on a realistic survey data set. The paper concludes with an application to environmental data for predicting average levels of the Acid Neutralizing Capacity at 8-digit Hydrologic Unit Code level in the Northeast states of the U.S.A.

In small area estimation direct survey estimates that rely only on area-specific data can exhibit large sampling variability due to small sample sizes at the small area level. Efficient small area estimates can be constructed using explicit linking models that borrow information from related areas. The most popular class of models for this purpose are models that include random area effects. Estimation for these models typically assumes that the random area effects are uncorrelated. In many situations, however, it is reasonable to assume that the effects of neighbouring areas are correlated. Models that extend conventional random effects models to account for spatial correlation between the small areas have been recently proposed in literature. A new semi-parametric approach to small area estimation is based on the use of M-quantile models. Unlike traditional random effects models, M-quantile models do not depend on strong distributional assumptions and are robust to the presence of outliers. In its current form, however, the M-quantile approach to small area estimation does not allow for spatially correlated area effects. The aim of this paper is to extend the M-quantile approach to account for such spatial correlation between small areas.

In small area estimation direct survey estimates that rely only on area-specific data can exhibit large sampling variability due to small sample sizes at the small area level. Efficient small area estimates can be constructed using explicit linking models that borrow information from related areas. The most popular class of models for this purpose are models that include random area effects. Estimation for these models typically assumes that the random area effects are uncorrelated. In many situations, however, it is reasonable to assume that the effects of neighbouring areas are correlated. Models that extend conventional random effects models to account for spatial correlation between the small areas have been recently proposed in literature. A new semi-parametric approach to small area estimation is based on the use of M-quantile models. Unlike traditional random effects models, M-quantile models do not depend on strong distributional assumptions and are robust to the presence of outliers. In its current form, however, the M-quantile approach to small area estimation does not allow for spatially correlated area effects. The aim of this paper is to extend the M-quantile approach to account for such spatial correlation between small areas.