We analyze the first representative series of individual measurements of the height of Swiss conscripts for the years . We find that average height followed a general upward time trend, but the economic downturn in the 1880s slowed down the increase in rural average-heights while the economic crisis subsequent to World War I had only a minor effect. Moreover, social-class affiliation was the most important determinant of differences in the biological standard of living, with class and regional disparities remaining constant, for the most part, during the observation period. Lower-class individuals' ability to overcome economic stress was limited, with the result that their biological standard of living, as reflected in the cyclicality of deviations from average height, was likely to be affected by cycles in economic activity. AbstractWe analyze the first representative series of individual measurements of the height of Swiss conscripts for the years 1875-1950. We find that average height followed a general upward time trend, but the economic downturn in the 1880s slowed down the increase in rural average-heights while the economic crisis subsequent to World War I had only a minor effect. Moreover, social-class affiliation was the most important determinant of differences in the biological standard of living, with class and regional disparities remaining constant, for the most part, during the observation period. Lower-class individuals' ability to overcome economic stress was limited, with the result that their biological standard of living, as reflected in the cyclicality of deviations from average height, was likely to be affected by cycles in economic activity.

Outlier nomination (detection) and robust regression are computationally hard problems. This is all the more true when the number of variables and observations grow rapidly. Among all candidate methods, the two BACON (blocked adaptive computationally efficient outlier nominators) algorithms of Billor et al. (2000) have favorable computational characteristics as they require only a few model evaluations irrespective of the sample size. This makes them popular algorithms for multivariate outlier nomination/detection and robust linear regression (at the time of writing Google Scholar reports more than 500 citations of the Billor et al. (2000) paper).wbacon is a package for the R statistical software (R Core Team, 2021). It is aimed at medium to large data sets that can possibly have (sampling) weights (e.g., data from complex survey samples). The package has a user-friendly R interface (with plotting methods, etc.) and is written mainly in the C language (with OpenMP support for parallelization; see OpenMP Architecture Review Board (2018)) for performance reasons. The BACON algorithmsTechnically, the BACON algorithms consist of the application of series of simple statistical estimation methods such as coordinate-wise means/medians, covariance matrix, Mahalanobis distances, or least squares regression on subsets of the data. The algorithms start from an initial small subset of non-outlying ("good") data and keep adding those observations to the subset whose distances (or discrepancies in the case of the regression algorithm) are smaller than a predefined threshold value. The algorithms terminate if the subset cannot be increased further. The observations not in the final subset are nominated as outliers. We follow Billor et al. (2000) and use the term "nomination" of outliers instead of "detection" to emphasize that the algorithms should not go beyond nominating observations as potential outliers. It is left to the analyst to finally label outlying observations as such.

Small area estimation is a topic of increasing importance in official statistics. Although the classical EBLUP method is useful for estimating the small area means efficiently under the normality assumptions, it can be highly influenced by the presence of outliers. Therefore, Sinha and Rao (2009; The Canadian Journal of Statistics) proposed robust estimators/predictors for a large class of unit- and area-level models. We confine attention to the basic unit-level model and discuss a related, but slightly different, robustification. In particular, we develop a fast algorithm that avoids inversion and multiplication of large matrices, and thus permits the user to apply the method to large datasets. In addition, we derive much simpler expressions of the boundedinfluence predicting equations to robustly predict the small-area means than Sinha and Rao (2009) did.

Inspired by the Dartmouth Atlas of Health Care, an early version of the Swiss Atlas of Health Care (SAHC) was released in 2017. The SAHC provides an intuitive visualization of regional variations of medical care delivery and thus allows for a broad diffusion of the contents. That is why the SAHC became widely accepted amongst health care stakeholders. In 2021, the relaunch of the SAHC was initiated to update as well as significantly expand the scope of measures depicted on the platform, also integrating indicators for outpatient care in order to better reflect the linkages between inpatient and outpatient health care provision. In the course of this relaunch, the statistical and technical aspects of the SAHC have been reviewed and updated. This paper presents the key aspects of the relaunch project and provides helpful insights for similar endeavors elsewhere.

No abstract