@article{messer2026_117558,
  title = {Gradient boosting for hierarchical data in small area estimation},
  author = {Messer, Paul and Schmid, Timo},
  year = {2026},
  pages = {1-29},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-117558x},
  url = {https://fis.uni-bamberg.de/handle/uniba/117558},
  language = {eng},
  abstract = {Small Area Estimation (SAE) combines survey data with auxiliary sources such as administrative records, census data, or alternative datasets that typically offer broader coverage. By integrating these sources, SAE enhances the accuracy of (direct) survey estimates. To account for the hierarchical structure of survey data, model-based SAE methods often rely on Linear Mixed Models (LMMs). However, the distributional (e.g., normality) and structural (e.g., linearity) assumptions of LMMs may not always hold in practice, and the accuracy of model-based SAE depends on the validity of these assumptions. To address these limitations, we propose a Mixed Effect Gradient Boosting (MEGB) approach, which combines the flexibility of gradient boosting machines with the ability of mixed models to account for hierarchical data structures. MEGB extends standard gradient boosting by incorporating random effects, allowing it to capture unobserved heterogeneity across domains while retaining a nonparametric framework that models nonlinearities and interactions in the data. MEGB supports the derivation of area-level means from unit-level data and uses a nonparametric bootstrap to estimate the Mean Squared Error (MSE). Its performance is assessed through a model-based simulation study, comparing MEGB to established estimators, and further demonstrated using real-world data. The results suggest that MEGB offers promising area mean estimates and may outperform existing SAE methods in various scenarios.},
  keywords = {Expectation–maximization algorithm, Ensemble learning, Mixed-effects modeling, Nonparametric bootstrap, Uncertainty quantification, Unit-level models}
}

@article{messer2026_117557,
  title = {Gradient boosting for hierarchical data in small area estimation},
  author = {Messer, Paul and Schmid, Timo},
  year = {2026},
  journal = {Statistics and computing},
  volume = {36},
  number = {5, 218},
  pages = {1-29},
  publisher = {Springer Science + Business Media B.V},
  address = {Dordrecht [u.a.]},
  issn = {1573-1375},
  doi = {10.1007/s11222-026-10970-1},
  url = {https://fis.uni-bamberg.de/handle/uniba/117557},
  language = {eng},
  abstract = {Small Area Estimation (SAE) combines survey data with auxiliary sources such as administrative records, census data, or alternative datasets that typically offer broader coverage. By integrating these sources, SAE enhances the accuracy of (direct) survey estimates. To account for the hierarchical structure of survey data, model-based SAE methods often rely on Linear Mixed Models (LMMs). However, the distributional (e.g., normality) and structural (e.g., linearity) assumptions of LMMs may not always hold in practice, and the accuracy of model-based SAE depends on the validity of these assumptions. To address these limitations, we propose a Mixed Effect Gradient Boosting (MEGB) approach, which combines the flexibility of gradient boosting machines with the ability of mixed models to account for hierarchical data structures. MEGB extends standard gradient boosting by incorporating random effects, allowing it to capture unobserved heterogeneity across domains while retaining a nonparametric framework that models nonlinearities and interactions in the data. MEGB supports the derivation of area-level means from unit-level data and uses a nonparametric bootstrap to estimate the Mean Squared Error (MSE). Its performance is assessed through a model-based simulation study, comparing MEGB to established estimators, and further demonstrated using real-world data. The results suggest that MEGB offers promising area mean estimates and may outperform existing SAE methods in various scenarios.},
  keywords = {Expectation–maximization algorithm, Ensemble learning, Mixed-effects modeling, Nonparametric bootstrap, Uncertainty quantification, Unit-level models}
}

@article{frink2026_116849,
  title = {Small area estimation with generalized random forests : estimating poverty rates in Mexico},
  author = {Frink, Nicolas and Schmid, Timo and Würz, Nora},
  year = {2026},
  journal = {Journal of the Royal Statistical Society: Series A, Statistics in society},
  number = {Online-First},
  publisher = {Oxford University Press},
  address = {Oxford},
  issn = {1467-985X},
  doi = {10.1093/jrsssa/qnag092},
  url = {https://fis.uni-bamberg.de/handle/uniba/116849},
  language = {eng}
}

@article{krennmair2026_108854,
  title = {Analysing Opportunity Cost of Care Work using Mixed Effects Random Forests under Aggregated Auxiliary Data},
  author = {Krennmair, Patrick and Würz, Nora and Schmid, Timo},
  year = {2026},
  journal = {Journal of the Royal Statistical Society. Series C, Applied statistics},
  volume = {75},
  number = {1},
  pages = {1-20},
  publisher = {Oxford University Press},
  address = {Kettering ; Cary, NC ; Tokyo},
  issn = {1467-9876},
  doi = {10.1093/jrsssc/qlaf031},
  url = {https://fis.uni-bamberg.de/handle/uniba/108854},
  language = {eng}
}

@article{edochie2025_111678,
  title = {Small Area Estimation of Poverty in Four West African Countries by Integrating Survey and Geospatial Data},
  author = {Edochie, Ifeanyi and Newhouse, David and Tzavidis, Nikos and Schmid, Timo and Foster, Elizabeth and Hernandez, Angela Luna and Ouedraogo, Aissatou and Sanoh, Aly and Savadogo, Aboudrahyme},
  year = {2025},
  pages = {96-124},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-111678x},
  url = {https://fis.uni-bamberg.de/handle/uniba/111678},
  language = {eng},
  abstract = {The paper presents methodology to generate experimental small area estimates (SAE) of poverty in four West African countries: Chad, Guinea, Mali, and Niger. Due to the absence of recent census data in the four countries, household level survey data are integrated with grid-level geospatial data, which are used as covariates in model-based estimation. Leveraging geospatial data enables reporting of poverty estimates more frequently at disaggregated administrative levels and makes estimation feasible in areas for which survey data are not available. The paper leverages the availability of a recent census in Burkina Faso for evaluation purposes. Estimates obtained with the same survey instruments and candidate geospatial covariates as the other four countries are compared against estimates obtained using recent census data and an empirical best predictor under a unit level model. For Burkina Faso, estimates obtained using geospatial data are highly correlated with the census-based ones in sampled areas but moderately correlated in non-sampled areas. The results demonstrate that in the absence of recent census data, small area estimation with publicly available geospatial covariates is feasible, can lead to large efficiency improvements compared to direct estimation, and improve the timeliness of small area estimates.},
  keywords = {headcount poverty rates, nested error regression model, geospatial covariates, empirical best predictor}
}

@article{dawber2025_110536,
  title = {Experimental UK Regional Consumer Price Inflation with Model-Based Expenditure Weights},
  author = {Dawber, James and Würz, Nora and Smith, Paul A. and Flower, Tanya and Thomas, Heledd and Schmid, Timo and Tzavidis, Nikos},
  year = {2025},
  pages = {213–237},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-110536x},
  url = {https://fis.uni-bamberg.de/handle/uniba/110536},
  language = {deu},
  abstract = {Like many other countries, the United Kingdom (UK) produces a national consumer price index (CPI) to measure inflation. Presently, CPI measures are not produced for regions within the UK. It is believed that, using only available data sources, a regional CPI would not be precise or reliable enough as an official statistic, primarily because the regional partitioning of the data makes sample sizes too small. We investigate this claim by producing experimental regional CPIs using publicly available price data, and deriving expenditure weights from the Living Costs and Food survey. We detail the methods and challenges of developing a regional CPI and evaluate its reliability. We then assess whether model-based methods such as smoothing and small area estimation significantly improve the measures. We find that a regional CPI can be produced with available data sources, however it appears to be excessively volatile over time, mainly due to the weights. Smoothing and small area estimation improve the reliability of the regional CPI series to some extent but they remain too volatile for regional policy use. This research provides a valuable framework for the development of a more viable regional CPI measure for the UK in the future.},
  keywords = {CPI conceptual framework, basket of goods and services, small area estimation, Fay-Herriot models}
}

@article{runge2025_110603,
  title = {Small Area with Multiply Imputed Survey Data},
  author = {Runge, Marina and Schmid, Timo},
  year = {2025},
  pages = {507-533},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-110603x},
  url = {https://fis.uni-bamberg.de/handle/uniba/110603},
  language = {eng},
  abstract = {In this article, we propose a framework for small area estimation with multiply imputed survey data. Many statistical surveys suffer from (a) high nonresponse rates due to sensitive questions and response burden and (b) too small sample sizes to allow for reliable estimates on (unplanned) disaggregated levels due to budget constraints. One way to deal with missing values is to replace them by several plausible/imputed values based on a model. Small area estimation, such as the model by Fay and Herriot, is applied to estimate regionally disaggregated indicators when direct estimates are imprecise. The framework presented tackles simultaneously multiply imputed values and imprecise direct estimates. In particular, we extend the general class of transformed Fay-Herriot models to account for the additional uncertainty from multiple imputation. We derive three special cases of the Fay-Herriot model with particular transformations and provide point and mean squared error estimators. Depending on the case, the mean squared error is estimated by analytic solutions or resampling methods. Comprehensive simulations in a controlled environment show that the proposed methodology leads to reliable and precise results in terms of bias and mean squared error. The methodology is illustrated by a real data example using European wealth data.},
  keywords = {Fay-Herriot model, mean squared error, multiple imputation, nonresponse, survey statistics}
}

@article{schmid2025_110314,
  title = {Editorial},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2025},
  pages = {59–61},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-110314x},
  url = {https://fis.uni-bamberg.de/handle/uniba/110314},
  language = {deu},
  abstract = {-},
  keywords = {-}
}

@article{zwick2025_110313,
  title = {Editorial},
  author = {Zwick, Markus and Schmid, Timo},
  year = {2025},
  pages = {1-3},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-110313x},
  url = {https://fis.uni-bamberg.de/handle/uniba/110313},
  language = {deu},
  abstract = {-},
  keywords = {-}
}

@article{frink2025_109919,
  title = {Small area prediction of counts under machine learning-type mixed models},
  author = {Frink, Nicolas and Schmid, Timo},
  year = {2025},
  pages = {1-16},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-109919x},
  url = {https://fis.uni-bamberg.de/handle/uniba/109919},
  language = {eng},
  abstract = {Small area estimation methods are proposed that use generalized tree-based machine learning techniques to improve the estimation of disaggregated means in small areas using discrete survey data. Specifically, two existing approaches based on random forests - the Generalized Mixed Effects Random Forest (GMERF) and a Mixed Effects Random Forest (MERF) - are extended to accommodate count outcomes, addressing key challenges such as overdispersion. Additionally, three bootstrap methodologies designed to assess the reliability of point estimators for area-level means are evaluated. The numerical analysis shows that the MERF, which does not assume a Poisson distribution to model the mean behavior of count data, excels in scenarios of severe overdispersion. Conversely, the GMERF performs best under conditions where Poisson distribution assumptions are moderately met. In a case study using real-world data from the state of Guerrero, Mexico, the proposed methods effectively estimate area-level means while capturing the uncertainty inherent in overdispersed count data. These findings highlight their practical applicability for small area estimation.},
  keywords = {Bootstrap, Generalized linear mixed models, Overdispersed count data, Random forest, Small area estimation}
}

@article{koebe2025_109866,
  title = {Releasing survey microdata with exact cluster locations and additional privacy safeguards},
  author = {Koebe, Till and Arias‐Salazar, Alejandra and Schmid, Timo},
  year = {2025},
  pages = {1-13},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-109866x},
  url = {https://fis.uni-bamberg.de/handle/uniba/109866},
  language = {eng},
  abstract = {Household survey programs around the world publish fine-granular georeferenced microdata to support research on the interdependence of human livelihoods and their surrounding environment. To safeguard the respondents’ privacy, micro-level survey data is usually (pseudo)-anonymized through deletion or perturbation procedures such as obfuscating the true location of data collection. This, however, poses a challenge to emerging approaches that augment survey data with auxiliary information on a local level. Here, we propose an alternative microdata dissemination strategy that leverages the utility of the original microdata with additional privacy safeguards through synthetically generated data using generative models. We back our proposal with experiments using data from the 2011 Costa Rican census and satellite-derived auxiliary information. Our strategy reduces the respondents’ re-identification risk for any number of disclosed attributes by 60–80\% even under re-identification attempts.},
  keywords = {survey microdata}
}

@article{frink2025_108853,
  title = {Small area prediction of counts under machine learning-type mixed models},
  author = {Frink, Nicolas and Schmid, Timo},
  year = {2025},
  journal = {Computational Statistics \& Data Analysis},
  volume = {211},
  number = {108218},
  pages = {1-16},
  publisher = {Elsevier Science},
  address = {Amsterdam},
  issn = {0167-9473},
  doi = {10.1016/j.csda.2025.108218},
  url = {https://fis.uni-bamberg.de/handle/uniba/108853},
  language = {eng},
  abstract = {Small area estimation methods are proposed that use generalized tree-based machine learning techniques to improve the estimation of disaggregated means in small areas using discrete survey data. Specifically, two existing approaches based on random forests - the Generalized Mixed Effects Random Forest (GMERF) and a Mixed Effects Random Forest (MERF) - are extended to accommodate count outcomes, addressing key challenges such as overdispersion. Additionally, three bootstrap methodologies designed to assess the reliability of point estimators for area-level means are evaluated. The numerical analysis shows that the MERF, which does not assume a Poisson distribution to model the mean behavior of count data, excels in scenarios of severe overdispersion. Conversely, the GMERF performs best under conditions where Poisson distribution assumptions are moderately met. In a case study using real-world data from the state of Guerrero, Mexico, the proposed methods effectively estimate area-level means while capturing the uncertainty inherent in overdispersed count data. These findings highlight their practical applicability for small area estimation.},
  keywords = {Bootstrap, Generalized linear mixed models, Overdispersed count data, Random forest, Small area estimation}
}

@article{erfurth2025_106603,
  title = {Kernel density smoothing of composite spatial data on administrative area level},
  author = {Erfurth, Kerstin and Groß, Marcus and Rendtel, Ulrich and Schmid, Timo},
  year = {2025},
  pages = {25-49},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1066039},
  url = {https://fis.uni-bamberg.de/handle/uniba/106603},
  language = {eng},
  abstract = {Composite spatial data on administrative area level are often presented by maps. The aim is to detect regional differences in the concentration of subpopulations, like elderly persons, ethnic minorities, low-educated persons, voters of a political party or persons with a certain disease. Thematic collections of such maps are presented in different atlases. The standard presentation is by Choropleth maps where each administrative unit is represented by a single value. These maps can be criticized under three aspects: the implicit assumption of a uniform distribution within the area, the instability of the resulting map with respect to a change of the reference area and the discontinuities of the maps at the borderlines of the reference areas which inhibit the detection of regional clusters. In order to address these problems we use a density approach in the construction of maps. This approach does not enforce a local uniform distribution. It does not depend on a specifc choice of area reference system and there are no discontinuities in the displayed maps. A standard estimation procedure of densities are Kernel density estimates. However, these estimates need the geo-coordinates of the single units which are not at disposal as we have only access to the aggregates of some area system. To overcome this hurdle, we use a statistical simulation concept. This can be interpreted as a Simulated Expectation Maximisation (SEM) algorithm of Celeux et al (1996). We simulate observations from the current density estimates which are consistent with the aggregation information (S-step). Then we apply the Kernel density estimator to the simulated sample which gives the next density estimate (E-Step).
This concept has been f rst applied for grid data with rectangular areas, see Groß et al (2017), for the display of ethnic minorities. In a second application we demonstrated the use of this approach for the so-called “change of support” (Bradley et al 2016) problem. Here Groß et al (2020) used the SEM algorithm to recalculate case numbers between non-hierarchical administrative area systems. Recently Rendtel et al (2021) applied the SEM algorithm to display spatial-temporal clusters of Corona infections in Germany. Here we present three modif cations of the basic SEM algorithm: 1) We introduce a boundary correction which removes the underestimation of kernel density estimates at the borders of the population area. 2) We recognize unsettled areas, like lakes, parks and industrial areas, in the computation of the kernel density. 3) We adapt the SEM algorithm for the computation of local percentages which are important especially in voting analysis. We evaluate our approach against several standard maps by means of the local voting register with known addresses. In the empirical part we apply our approach for the display of voting results for the 2016 election of the Berlin parliament. We contrast our results against Choropleth maps and show new possibilities for reporting spatial voting results.},
  keywords = {Spatial data, Administrative areas, Choropleths, Kernel density estimation, Voting atlases}
}

@article{koebe2025_106925,
  title = {Intercensal updating using structure‐preserving methods and satellite imagery},
  author = {Koebe, Till and Arias‐Salazar, Alejandra and Rojas‐Perilla, Natalia and Schmid, Timo},
  year = {2025},
  pages = {1-27},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1069251},
  url = {https://fis.uni-bamberg.de/handle/uniba/106925},
  language = {eng},
  abstract = {Censuses are fundamental building blocks of most modern-day societies, yet collected every 10 years at best. We propose an extension of the widely popular census updating technique structure-preserving estimation by incorporating auxiliary information in order to take ongoing subnational population shifts into account. We apply our method by incorporating satellite imagery as additional source to derive annual small-area updates of multidimensional poverty indicators from 2013 to 2020 for a population at risk: female-headed households in Senegal. We evaluate the performance of our proposal using data from two different census periods.},
  keywords = {multidimensional poverty, official statistics, small-area estimation, SPREE}
}

@article{edochie2025_105797,
  title = {Small Area Estimation of Poverty in Four West African Countries by Integrating Survey and Geospatial Data},
  author = {Edochie, Ifeanyi and Newhouse, David and Tzavidis, Nikos and Schmid, Timo and Foster, Elizabeth and Hernandez, Angela Luna and Ouedraogo, Aissatou and Sanoh, Aly and Savadogo, Aboudrahyme},
  year = {2025},
  journal = {Journal of Official Statistics},
  volume = {41},
  number = {1},
  pages = {96-124},
  publisher = {Sage},
  address = {London},
  issn = {2001-7367},
  doi = {10.1177/0282423x241284890},
  url = {https://fis.uni-bamberg.de/handle/uniba/105797},
  language = {eng},
  abstract = {The paper presents methodology to generate experimental small area estimates (SAE) of poverty in four West African countries: Chad, Guinea, Mali, and Niger. Due to the absence of recent census data in the four countries, household level survey data are integrated with grid-level geospatial data, which are used as covariates in model-based estimation. Leveraging geospatial data enables reporting of poverty estimates more frequently at disaggregated administrative levels and makes estimation feasible in areas for which survey data are not available. The paper leverages the availability of a recent census in Burkina Faso for evaluation purposes. Estimates obtained with the same survey instruments and candidate geospatial covariates as the other four countries are compared against estimates obtained using recent census data and an empirical best predictor under a unit level model. For Burkina Faso, estimates obtained using geospatial data are highly correlated with the census-based ones in sampled areas but moderately correlated in non-sampled areas. The results demonstrate that in the absence of recent census data, small area estimation with publicly available geospatial covariates is feasible, can lead to large efficiency improvements compared to direct estimation, and improve the timeliness of small area estimates.},
  keywords = {headcount poverty rates, nested error regression model, geospatial covariates, empirical best predictor}
}

@article{hadam2024_98448,
  title = {Estimating regional unemployment with mobile network data for Functional Urban Areas in Germany},
  author = {Hadam, Sandra and Würz, Nora and Kreutzmann, Ann-Kristin and Schmid, Timo},
  year = {2024},
  pages = {205-233},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-984480},
  url = {https://fis.uni-bamberg.de/handle/uniba/98448},
  language = {eng},
  abstract = {The ongoing growth of cities due to better job opportunities is leading to increased labour-related commuter flows in several countries. On the one hand, an increasing number of people commute and move to the cities, but on the other hand, the labour market indicates higher unemployment rates in urban areas than in the surrounding areas. We investigate this phenomenon on regional level by an alternative definition of unemployment rates in which commuting behaviour is integrated. We combine data from the Labour Force Survey with dynamic mobile network data by small area models for the federal state North Rhine-Westphalia in Germany. From a methodical perspective, we use a transformed Fay–Herriot model with bias correction for the estimation of unemployment rates and propose a parametric bootstrap for the mean squared error estimation that includes the bias correction. The performance of the proposed methodology is evaluated in a case study based on official data and in model-based simulations. The results in the application show that unemployment rates (adjusted by commuters) in German cities are lower than traditional official unemployment rates indicate.},
  keywords = {Bias correction, Fay–Herriot model, Mean squared error, Small area estimation, Unemployment rates}
}

@article{harmening2024_94974,
  title = {A Framework for Producing Small Area Estimates Based on Area-Level Models in R},
  author = {Harmening, Sylvia and Kreutzmann, Ann-Kristin and Schmidt, Sören and Salvati, Nicola and Schmid, Timo},
  year = {2024},
  pages = {316-341},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-949743},
  url = {https://fis.uni-bamberg.de/handle/uniba/94974},
  language = {eng},
  abstract = {The R package emdi facilitates the estimation of regionally disaggregated indicators using small area estimation methods and provides tools for model building, diagnostics, presenting, and exporting the results. The package version 1.1.7 includes unit-level small area models that rely on access to micro data. The area-level model by Fay and Herriot (1979) and various extensions have been added to the package since the release of version 2.0.0. These extensions include (a) area-level models with back-transformations, (b) spatial and robust extensions, (c) adjusted variance estimation methods, and (d) area-level models that account for measurement errors. Corresponding mean squared error estimators are implemented for assessing the uncertainty. User-friendly tools like a stepwise variable selection, model diagnostics, benchmarking options, high quality maps and results exportation options enable a complete analysis procedure. The functionality of the package is illustrated by examples based on synthetic data for Austrian districts.},
  keywords = {Area-Level Models in R}
}

@misc{sonning2024_95382,
  title = {Latent-variable modeling of ordinal outcomes in language data analysis},
  author = {Sönning, Lukas and Krug, Manfred and Vetter, Fabian and Schmid, Timo and Leucht, Anne and Messer, Paul},
  year = {2024},
  pages = {1-22},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-953824},
  url = {https://fis.uni-bamberg.de/handle/uniba/95382},
  language = {eng},
  abstract = {In empirical work, ordinal variables are typically analyzed using means based on numeric scores assigned to categories. While this strategy has met with justified criticism in the methodological literature, it also generates simple and informative data summaries, a standard often not met by statistically more adequate procedures. Motivated by a survey of how ordered variables are dealt with in language research, we draw attention to an un(der)used latent-variable approach to ordinal data modeling, an alternative perspective on the most widely used form of ordered regression, the cumulative model. Since the latent-variable approach is not mentioned in statistical textbooks for linguists and does not feature in any of the studies in our survey, we believe it is worthwhile to promote its benefits. To this end, we draw on questionnaire-based preference ratings by speakers of Maltese English, who indicated on a 5-point scale which of two synonymous expressions (e.g. package-parcel) they (tend to) use. We demonstrate that a latent-variable analysis affords nuanced and interpretable data summaries that can be visualized effectively, while at the same time avoiding limitations inherent in mean response models (e.g. distortions induced by floor and ceiling effects). The online supplementary materials include a tutorial for its implementation in R.},
  keywords = {Latent-variable modeling}
}

@article{sonning2024_95412,
  title = {Latent-Variable Modelling of Ordinal Outcomes in Language Data Analysis},
  author = {Sönning, Lukas and Krug, Manfred and Vetter, Fabian and Schmid, Timo and Leucht, Anne and Messer, Paul},
  year = {2024},
  journal = {Journal of quantitative linguistics : official journal of the International Quantitative Linguistics Association (IQLA)},
  volume = {31},
  number = {2},
  pages = {77-106},
  publisher = {Informa UK Limited},
  address = {London},
  issn = {1744-5035},
  doi = {10.1080/09296174.2024.2329448},
  url = {https://fis.uni-bamberg.de/handle/uniba/95412},
  language = {eng}
}

@misc{sonning2024_93359,
  title = {Latent-variable modeling of ordinal outcomes in language data analysis},
  author = {Sönning, Lukas and Krug, Manfred and Vetter, Fabian and Schmid, Timo and Leucht, Anne and Messer, Paul},
  year = {2024},
  pages = {1-22},
  publisher = {Center for Open Science},
  doi = {10.31219/osf.io/jhv6b},
  url = {https://fis.uni-bamberg.de/handle/uniba/93359},
  language = {eng},
  abstract = {In empirical work, ordinal variables are typically analyzed using means based on numeric scores assigned to categories. While this strategy has met with justified criticism in the methodological literature, it also generates simple and informative data summaries, a standard often not met by statistically more adequate procedures. Motivated by a survey of how ordered variables are dealt with in language research, we draw attention to an un(der)used latent-variable approach to ordinal data modeling, an alternative perspective on the most widely used form of ordered regression, the cumulative model. Since the latent-variable approach is not mentioned in statistical textbooks for linguists and does not feature in any of the studies in our survey, we believe it is worthwhile to promote its benefits. To this end, we draw on questionnaire-based preference ratings by speakers of Maltese English, who indicated on a 5-point scale which of two synonymous expressions (e.g. package-parcel) they (tend to) use. We demonstrate that a latent-variable analysis affords nuanced and interpretable data summaries that can be visualized effectively, while at the same time avoiding limitations inherent in mean response models (e.g. distortions induced by floor and ceiling effects). The online supplementary materials include a tutorial for its implementation in R.},
  keywords = {Latent-variable modeling}
}

@article{hadam2024_92359,
  title = {Estimating regional unemployment with mobile network data for Functional Urban Areas in Germany},
  author = {Hadam, Sandra and Würz, Nora and Kreutzmann, Ann-Kristin and Schmid, Timo},
  year = {2024},
  journal = {Statistical methods \& applications},
  volume = {33},
  number = {1},
  pages = {205-233},
  publisher = {Springer},
  address = {Berlin},
  issn = {1618-2510},
  doi = {10.1007/s10260-023-00722-0},
  url = {https://fis.uni-bamberg.de/handle/uniba/92359},
  language = {eng},
  abstract = {The ongoing growth of cities due to better job opportunities is leading to increased labour-related commuter flows in several countries. On the one hand, an increasing number of people commute and move to the cities, but on the other hand, the labour market indicates higher unemployment rates in urban areas than in the surrounding areas. We investigate this phenomenon on regional level by an alternative definition of unemployment rates in which commuting behaviour is integrated. We combine data from the Labour Force Survey with dynamic mobile network data by small area models for the federal state North Rhine-Westphalia in Germany. From a methodical perspective, we use a transformed Fay–Herriot model with bias correction for the estimation of unemployment rates and propose a parametric bootstrap for the mean squared error estimation that includes the bias correction. The performance of the proposed methodology is evaluated in a case study based on official data and in model-based simulations. The results in the application show that unemployment rates (adjusted by commuters) in German cities are lower than traditional official unemployment rates indicate.},
  keywords = {Bias correction, Fay–Herriot model, Mean squared error, Small area estimation, Unemployment rates}
}

@article{koebe2023_108611,
  title = {Releasing survey microdata with exact cluster locations and additional privacy safeguards},
  author = {Koebe, Till and Arias‐Salazar, Alejandra and Schmid, Timo},
  year = {2023},
  journal = {Humanities and Social Sciences Communications},
  volume = {10},
  number = {220},
  pages = {1-13},
  publisher = {Springer Nature},
  address = {London},
  issn = {2662-9992},
  doi = {10.1057/s41599-023-01694-y},
  url = {https://fis.uni-bamberg.de/handle/uniba/108611},
  language = {eng},
  abstract = {Household survey programs around the world publish fine-granular georeferenced microdata to support research on the interdependence of human livelihoods and their surrounding environment. To safeguard the respondents’ privacy, micro-level survey data is usually (pseudo)-anonymized through deletion or perturbation procedures such as obfuscating the true location of data collection. This, however, poses a challenge to emerging approaches that augment survey data with auxiliary information on a local level. Here, we propose an alternative microdata dissemination strategy that leverages the utility of the original microdata with additional privacy safeguards through synthetically generated data using generative models. We back our proposal with experiments using data from the 2011 Costa Rican census and satellite-derived auxiliary information. Our strategy reduces the respondents’ re-identification risk for any number of disclosed attributes by 60–80\% even under re-identification attempts.},
  keywords = {survey microdata}
}

@article{runge2023_95823,
  title = {Small Area with Multiply Imputed Survey Data},
  author = {Runge, Marina and Schmid, Timo},
  year = {2023},
  journal = {Journal of Official Statistics},
  volume = {39},
  number = {4},
  pages = {507-533},
  publisher = {Sage Publishing},
  address = {Thousand Oaks, California},
  issn = {0282-423X},
  doi = {10.2478/jos-2023-0024},
  url = {https://fis.uni-bamberg.de/handle/uniba/95823},
  language = {eng},
  abstract = {In this article, we propose a framework for small area estimation with multiply imputed survey data. Many statistical surveys suffer from (a) high nonresponse rates due to sensitive questions and response burden and (b) too small sample sizes to allow for reliable estimates on (unplanned) disaggregated levels due to budget constraints. One way to deal with missing values is to replace them by several plausible/imputed values based on a model. Small area estimation, such as the model by Fay and Herriot, is applied to estimate regionally disaggregated indicators when direct estimates are imprecise. The framework presented tackles simultaneously multiply imputed values and imprecise direct estimates. In particular, we extend the general class of transformed Fay-Herriot models to account for the additional uncertainty from multiple imputation. We derive three special cases of the Fay-Herriot model with particular transformations and provide point and mean squared error estimators. Depending on the case, the mean squared error is estimated by analytic solutions or resampling methods. Comprehensive simulations in a controlled environment show that the proposed methodology leads to reliable and precise results in terms of bias and mean squared error. The methodology is illustrated by a real data example using European wealth data.},
  keywords = {Fay-Herriot model, mean squared error, multiple imputation, nonresponse, survey statistics}
}

@article{harmening2023_92478,
  title = {A Framework for Producing Small Area Estimates Based on Area-Level Models in R},
  author = {Harmening, Sylvia and Kreutzmann, Ann-Kristin and Schmidt, Sören and Salvati, Nicola and Schmid, Timo},
  year = {2023},
  journal = {The R Journal},
  volume = {15},
  number = {1},
  pages = {316-341},
  publisher = {The R Foundation},
  address = {Frederiksberg},
  issn = {2073-4859},
  doi = {10.32614/rj-2023-039},
  url = {https://fis.uni-bamberg.de/handle/uniba/92478},
  language = {eng},
  abstract = {The R package emdi facilitates the estimation of regionally disaggregated indicators using small area estimation methods and provides tools for model building, diagnostics, presenting, and exporting the results. The package version 1.1.7 includes unit-level small area models that rely on access to micro data. The area-level model by Fay and Herriot (1979) and various extensions have been added to the package since the release of version 2.0.0. These extensions include (a) area-level models with back-transformations, (b) spatial and robust extensions, (c) adjusted variance estimation methods, and (d) area-level models that account for measurement errors. Corresponding mean squared error estimators are implemented for assessing the uncertainty. User-friendly tools like a stepwise variable selection, model diagnostics, benchmarking options, high quality maps and results exportation options enable a complete analysis procedure. The functionality of the package is illustrated by examples based on synthetic data for Austrian districts.},
  keywords = {Area-Level Models in R}
}

@article{schmid2023_59713,
  title = {Editorial Heft 1, 2023: Vorwort der Herausgeber},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2023},
  pages = {1-3},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-597132},
  url = {https://fis.uni-bamberg.de/handle/uniba/59713},
  language = {deu},
  abstract = {-},
  keywords = {Datenerfassung}
}

@article{schmid2023_59677,
  title = {Editorial Heft 1, 2023: Vorwort der Herausgeber},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2023},
  journal = {AStA Wirtschafts- und Sozialstatistisches Archiv},
  volume = {17},
  number = {1},
  pages = {1-3},
  publisher = {Springer Nature},
  address = {Berlin},
  issn = {1863-8163},
  doi = {10.1007/s11943-023-00319-9},
  url = {https://fis.uni-bamberg.de/handle/uniba/59677},
  language = {deu},
  abstract = {-},
  keywords = {Datenerfassung}
}

@article{lee2023_58402,
  title = {Variable selection using conditional AIC for linear mixed models with data-driven transformations},
  author = {Lee, Yeonjoo and Schmid, Timo and Rojas‐Perilla, Natalia and Runge, Marina},
  year = {2023},
  pages = {1-17},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-584026},
  url = {https://fis.uni-bamberg.de/handle/uniba/58402},
  language = {eng},
  abstract = {When data analysts use linear mixed models, they usually encounter two practical problems: (a) the true model is unknown and (b) the Gaussian assumptions of the errors do not hold. While these problems commonly appear together, researchers tend to treat them individually by (a) finding an optimal model based on the conditional Akaike information criterion (cAIC) and (b) applying transformations on the dependent variable. However, the optimal model depends on the transformation and vice versa. In this paper, we aim to solve both problems simultaneously. In particular, we propose an adjusted cAIC by using the Jacobian of the particular transformation such that various model candidates with differently transformed data can be compared. From a computational perspective, we propose a step-wise selection approach based on the introduced adjusted cAIC. Model-based simulations are used to compare the proposed selection approach to alternative approaches. Finally, the introduced approach is applied to Mexican data to estimate poverty and inequality indicators for 81 municipalities.},
  keywords = {Box-Cox transformation, Empirical best predictor, Indicators, Small area estimation}
}

@article{wurz2023_58282,
  title = {Estimating regional income indicators under transformations and access to limited population auxiliary information},
  author = {Würz, Nora and Schmid, Timo and Tzavidis, Nikos},
  year = {2023},
  pages = {1679-1706},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-582821},
  url = {https://fis.uni-bamberg.de/handle/uniba/58282},
  language = {eng},
  abstract = {Spatially disaggregated income indicators are typically estimated by using model-based methods that assume access to auxiliary information from population micro-data. In many countries like Germany and the UK population micro-data are not publicly available. In this work we propose small area methodology when only aggregate population-level auxiliary information is available. We use data-driven transformations of the response to satisfy the parametric assumptions of the used models. In the absence of population micro-data, appropriate bias-corrections for small area prediction are needed. Under the approach we propose in this paper, aggregate statistics (means and covariances) and kernel density estimation are used to resolve the issue of not having access to population micro-data. We further explore the estimation of the mean squared error using the parametric bootstrap. Extensive model-based and design-based simulations are used to compare the proposed method to alternative methods. Finally, the proposed methodology is applied to the 2011 Socio-Economic Panel and aggregate census information from the same year to estimate the average income for 96 regional planning regions in Germany.},
  keywords = {census, density estimation, official statistics, small area estimation, unit-level models}
}

@article{schmid2023_58270,
  title = {Flexible domain prediction using mixed effects random forests},
  author = {Schmid, Timo and Krennmair, Patrick},
  year = {2023},
  volume = {71},
  number = {5},
  pages = {1865-1894},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-582701},
  url = {https://fis.uni-bamberg.de/handle/uniba/58270},
  language = {eng},
  abstract = {This paper promotes the use of random forests as versatile tools for estimating spatially disaggregated indicators in the presence of small area-specific sample sizes. Small area estimators are predominantly conceptualised within the regression-setting and rely on linear mixed models to account for the hierarchical structure of the survey data. In contrast, machine learning methods offer non-linear and non-parametric alternatives, combining excellent predictive performance and a reduced risk of model-misspecification. Mixed effects random forests combine advantages of regression forests with the ability to model hierarchical dependencies. This paper provides a coherent framework based on mixed effects random forests for estimating small area averages and proposes a non-parametric bootstrap estimator for assessing the uncertainty of the estimates. We illustrate advantages of our proposed methodology using Mexican income-data from the state Nuevo León. Finally, the methodology is evaluated in model-based and design-based simulations comparing the proposed methodology to traditional regression-based approaches for estimating small area averages.},
  keywords = {mean squared error, official statistics, small area estimation, tree-based methods}
}

@article{schmid2023_57985,
  title = {Editorial : Vorwort der Herausgeber},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2023},
  pages = {167–170},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  issn = {1863-8163},
  urn = {urn:nbn:de:bvb:473-irb-579855},
  url = {https://fis.uni-bamberg.de/handle/uniba/57985},
  language = {deu},
  abstract = {Nicht verfügbar
Not available},
  keywords = {Statistik, Wirtschaft}
}

@article{lee2023_57600,
  title = {Variable selection using conditional AIC for linear mixed models with data-driven transformations},
  author = {Lee, Yeonjoo and Schmid, Timo and Rojas‐Perilla, Natalia and Runge, Marina},
  year = {2023},
  journal = {Statistics and computing},
  volume = {33},
  number = {1},
  pages = {1-17},
  publisher = {Springer Science + Business Media B.V},
  address = {Dordrecht [u.a.]},
  issn = {1573-1375},
  doi = {10.1007/s11222-022-10198-9},
  url = {https://fis.uni-bamberg.de/handle/uniba/57600},
  language = {eng},
  abstract = {When data analysts use linear mixed models, they usually encounter two practical problems: (a) the true model is unknown and (b) the Gaussian assumptions of the errors do not hold. While these problems commonly appear together, researchers tend to treat them individually by (a) finding an optimal model based on the conditional Akaike information criterion (cAIC) and (b) applying transformations on the dependent variable. However, the optimal model depends on the transformation and vice versa. In this paper, we aim to solve both problems simultaneously. In particular, we propose an adjusted cAIC by using the Jacobian of the particular transformation such that various model candidates with differently transformed data can be compared. From a computational perspective, we propose a step-wise selection approach based on the introduced adjusted cAIC. Model-based simulations are used to compare the proposed selection approach to alternative approaches. Finally, the introduced approach is applied to Mexican data to estimate poverty and inequality indicators for 81 municipalities.},
  keywords = {Box-Cox transformation, Empirical best predictor, Indicators, Small area estimation}
}

@article{schmid2022_57984,
  title = {Editorial : Vorwort der Herausgeber},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2022},
  journal = {AStA Wirtschafts- und Sozialstatistisches Archiv},
  volume = {16},
  number = {3-4},
  pages = {167-170},
  publisher = {Springer},
  address = {Berlin ; Heidelberg},
  issn = {1863-8163},
  doi = {10.1007/s11943-022-00315-5},
  url = {https://fis.uni-bamberg.de/handle/uniba/57984},
  language = {deu},
  abstract = {Nicht verfügbar
Not available},
  keywords = {Statistik, Wirtschaft}
}

@article{schmid2022_55976,
  title = {Vorwort der Herausgeber},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2022},
  pages = {1-4},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-559761},
  url = {https://fis.uni-bamberg.de/handle/uniba/55976},
  language = {deu},
  abstract = {Nicht verfügbar
Not available},
  keywords = {Grundschulversorgung, COVID-19-Pandemie, Berliner Wahldaten, Übersterblichkeit, Räumliche Daten, Deutschen Arbeitsmarkt}
}

@article{schmid2022_57459,
  title = {Flexible domain prediction using mixed effects random forests},
  author = {Schmid, Timo and Krennmair, Patrick},
  year = {2022},
  journal = {Journal of the Royal Statistical Society. Series C, Applied statistics},
  volume = {71},
  number = {5},
  pages = {1865-1894},
  publisher = {Wiley-Blackwell},
  address = {London},
  issn = {1467-9876},
  doi = {10.1111/rssc.12600},
  url = {https://fis.uni-bamberg.de/handle/uniba/57459},
  language = {eng},
  abstract = {This paper promotes the use of random forests as versatile tools for estimating spatially disaggregated indicators in the presence of small area-specific sample sizes. Small area estimators are predominantly conceptualised within the regression-setting and rely on linear mixed models to account for the hierarchical structure of the survey data. In contrast, machine learning methods offer non-linear and non-parametric alternatives, combining excellent predictive performance and a reduced risk of model-misspecification. Mixed effects random forests combine advantages of regression forests with the ability to model hierarchical dependencies. This paper provides a coherent framework based on mixed effects random forests for estimating small area averages and proposes a non-parametric bootstrap estimator for assessing the uncertainty of the estimates. We illustrate advantages of our proposed methodology using Mexican income-data from the state Nuevo León. Finally, the methodology is evaluated in model-based and design-based simulations comparing the proposed methodology to traditional regression-based approaches for estimating small area averages.},
  keywords = {mean squared error, official statistics, small area estimation, tree-based methods}
}

@article{wurz2022_57458,
  title = {Estimating regional income indicators under transformations and access to limited population auxiliary information},
  author = {Würz, Nora and Schmid, Timo and Tzavidis, Nikos},
  year = {2022},
  journal = {Journal of the Royal Statistical Society. Series A, Statistics in society},
  volume = {185},
  number = {4},
  pages = {1679-1706},
  publisher = {Wiley-Blackwell},
  address = {London},
  issn = {1467-985X},
  doi = {10.1111/rssa.12913},
  url = {https://fis.uni-bamberg.de/handle/uniba/57458},
  language = {eng},
  abstract = {Spatially disaggregated income indicators are typically estimated by using model-based methods that assume access to auxiliary information from population micro-data. In many countries like Germany and the UK population micro-data are not publicly available. In this work we propose small area methodology when only aggregate population-level auxiliary information is available. We use data-driven transformations of the response to satisfy the parametric assumptions of the used models. In the absence of population micro-data, appropriate bias-corrections for small area prediction are needed. Under the approach we propose in this paper, aggregate statistics (means and covariances) and kernel density estimation are used to resolve the issue of not having access to population micro-data. We further explore the estimation of the mean squared error using the parametric bootstrap. Extensive model-based and design-based simulations are used to compare the proposed method to alternative methods. Finally, the proposed methodology is applied to the 2011 Socio-Economic Panel and aggregate census information from the same year to estimate the average income for 96 regional planning regions in Germany.},
  keywords = {census, density estimation, official statistics, small area estimation, unit-level models}
}

@article{walter2022_55983,
  title = {Iterative Kernel Density Estimation Applied to Grouped Data : Estimating Poverty and Inequality Indicators from the German Microcensus},
  author = {Walter, Paul and Groß, Marcus and Schmid, Timo and Weimer, Katja},
  year = {2022},
  pages = {599-635},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-559830},
  url = {https://fis.uni-bamberg.de/handle/uniba/55983},
  language = {eng},
  abstract = {The estimation of poverty and inequality indicators based on survey data is trivial as long as the variable of interest (e.g., income or consumption) is measured on a metric scale. However, estimation is not directly possible, using standard formulas, when the income variable is grouped due to confidentiality constraints or in order to decrease item nonresponse. We propose an iterative kernel density algorithm that generates metric pseudo samples from the grouped variable for the estimation of indicators. The corresponding standard errors are estimated by a non-parametric bootstrap that accounts for the additional uncertainty due to the grouping. The algorithm enables the use of survey weights and household equivalence scales. The proposed method is applied to the German Microcensus for estimating the regional distribution of poverty and inequality in Germany.},
  keywords = {Direct estimation, Interval-censored data, non-parametric estimation, OECD scale, prediction}
}

@article{schmid2022_55975,
  title = {Vorwort der Herausgeber},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2022},
  journal = {AStA Wirtschafts- und Sozialstatistisches Archiv},
  volume = {16},
  number = {1},
  pages = {1-4},
  publisher = {Springer},
  address = {Berlin ; Heidelberg},
  issn = {1863-8163},
  doi = {10.1007/s11943-022-00304-8},
  url = {https://fis.uni-bamberg.de/handle/uniba/55975},
  language = {deu},
  abstract = {Nicht verfügbar
Not available},
  keywords = {Grundschulversorgung, COVID-19-Pandemie, Berliner Wahldaten, Übersterblichkeit, Räumliche Daten, Deutschen Arbeitsmarkt}
}

@article{walter2022_55652,
  title = {Iterative Kernel Density Estimation Applied to Grouped Data : Estimating Poverty and Inequality Indicators from the German Microcensus},
  author = {Walter, Paul and Groß, Marcus and Schmid, Timo and Weimer, Katja},
  year = {2022},
  journal = {Journal of Official Statistics : JOS},
  volume = {38},
  number = {2},
  pages = {599-635},
  publisher = {de Gruyter},
  address = {Berlin},
  issn = {2001-7367},
  doi = {10.2478/jos-2022-0027},
  url = {https://fis.uni-bamberg.de/handle/uniba/55652},
  language = {eng},
  abstract = {The estimation of poverty and inequality indicators based on survey data is trivial as long as the variable of interest (e.g., income or consumption) is measured on a metric scale. However, estimation is not directly possible, using standard formulas, when the income variable is grouped due to confidentiality constraints or in order to decrease item nonresponse. We propose an iterative kernel density algorithm that generates metric pseudo samples from the grouped variable for the estimation of indicators. The corresponding standard errors are estimated by a non-parametric bootstrap that accounts for the additional uncertainty due to the grouping. The algorithm enables the use of survey weights and household equivalence scales. The proposed method is applied to the German Microcensus for estimating the regional distribution of poverty and inequality in Germany.},
  keywords = {Direct estimation, Interval-censored data, non-parametric estimation, OECD scale, prediction}
}

@article{walter2022_54774,
  title = {Domain prediction with grouped income data},
  author = {Walter, Paul and Groß, Marcus and Schmid, Timo and Tzavidis, Nikos},
  year = {2022},
  pages = {1501-1523},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-547742},
  url = {https://fis.uni-bamberg.de/handle/uniba/54774},
  language = {eng},
  abstract = {One popular small area estimation method for estimating poverty and inequality indicators is the empirical best predictor under the unit-level nested error regression model with a continuous dependent variable. However, parameter estimation is more challenging when the response variable is grouped due to data confidentiality concerns or concerns about survey response burden. The work in this paper proposes methodology that enables fitting a nested error regression model when the dependent variable is grouped. Model parameters are then used for small area prediction of finite population parameters of interest. Model fitting in the case of a grouped response variable is based on the use of a stochastic expectation–maximization algorithm. Since the stochastic expectation–maximization algorithm relies on the Gaussian assumptions of the unit-level error terms, adaptive transformations are incorporated for handling departures from normality. The estimation of the mean squared error of the small area parameters is facilitated by a parametric bootstrap that captures the additional uncertainty due to the grouping mechanism and the possible use of adaptive transformations. The empirical properties of the proposed methodology are assessed by using model-based simulations and its relevance is illustrated by estimating deprivation indicators for municipalities in the Mexican state of Chiapas.},
  keywords = {data confidentiality, interval-censored data, nested error regression model, small area estimation, survey response burden}
}

@article{dawber2022_53876,
  title = {Experimental UK Regional Consumer Price Inflation with Model-Based Expenditure Weights},
  author = {Dawber, James and Würz, Nora and Smith, Paul A. and Flower, Tanya and Thomas, Heledd and Schmid, Timo and Tzavidis, Nikos},
  year = {2022},
  journal = {Journal of Official Statistics},
  volume = {38},
  number = {1},
  pages = {213-237},
  publisher = {de Gruyter},
  address = {Berlin},
  issn = {2001-7367},
  doi = {10.2478/jos-2022-0010},
  url = {https://fis.uni-bamberg.de/handle/uniba/53876},
  language = {deu},
  abstract = {Like many other countries, the United Kingdom (UK) produces a national consumer price index (CPI) to measure inflation. Presently, CPI measures are not produced for regions within the UK. It is believed that, using only available data sources, a regional CPI would not be precise or reliable enough as an official statistic, primarily because the regional partitioning of the data makes sample sizes too small. We investigate this claim by producing experimental regional CPIs using publicly available price data, and deriving expenditure weights from the Living Costs and Food survey. We detail the methods and challenges of developing a regional CPI and evaluate its reliability. We then assess whether model-based methods such as smoothing and small area estimation significantly improve the measures. We find that a regional CPI can be produced with available data sources, however it appears to be excessively volatile over time, mainly due to the weights. Smoothing and small area estimation improve the reliability of the regional CPI series to some extent but they remain too volatile for regional policy use. This research provides a valuable framework for the development of a more viable regional CPI measure for the UK in the future.},
  keywords = {CPI conceptual framework, basket of goods and services, small area estimation, Fay-Herriot models}
}

@article{koebe2022_53875,
  title = {Intercensal updating using structure‐preserving methods and satellite imagery},
  author = {Koebe, Till and Arias‐Salazar, Alejandra and Rojas‐Perilla, Natalia and Schmid, Timo},
  year = {2022},
  journal = {Journal of the Royal Statistical Society : Series A, Statistics in society},
  volume = {185},
  number = {Supplement 2},
  pages = {1-27},
  publisher = {Oxford University Press},
  address = {London},
  issn = {1467-985X},
  doi = {10.1111/rssa.12802},
  url = {https://fis.uni-bamberg.de/handle/uniba/53875},
  language = {eng},
  abstract = {Censuses are fundamental building blocks of most modern-day societies, yet collected every 10 years at best. We propose an extension of the widely popular census updating technique structure-preserving estimation by incorporating auxiliary information in order to take ongoing subnational population shifts into account. We apply our method by incorporating satellite imagery as additional source to derive annual small-area updates of multidimensional poverty indicators from 2013 to 2020 for a population at risk: female-headed households in Senegal. We evaluate the performance of our proposal using data from two different census periods.},
  keywords = {multidimensional poverty, official statistics, small-area estimation, SPREE}
}

@article{schmid2021_105832,
  title = {Editorial},
  author = {Schmid, Timo and Zwick, Markus},
  year = {2021},
  journal = {Wirtschafts- und sozialstatistisches Archiv : ASTA ; eine Zeitschrift der Deutschen Statistischen Gesellschaft},
  volume = {15},
  number = {2},
  pages = {59-61},
  publisher = {Springer},
  address = {Berlin ; Heidelberg},
  issn = {1863-8155},
  doi = {10.1007/s11943-021-00291-2},
  url = {https://fis.uni-bamberg.de/handle/uniba/105832},
  language = {deu},
  abstract = {-},
  keywords = {-}
}

@article{zwick2021_105831,
  title = {Editorial},
  author = {Zwick, Markus and Schmid, Timo},
  year = {2021},
  journal = {Wirtschafts- und sozialstatistisches Archiv : ASTA ; eine Zeitschrift der Deutschen Statistischen Gesellschaft},
  volume = {15},
  number = {1},
  pages = {1-3},
  publisher = {Springer},
  address = {Berlin ; Heidelberg},
  issn = {1863-8155},
  doi = {10.1007/s11943-021-00283-2},
  url = {https://fis.uni-bamberg.de/handle/uniba/105831},
  language = {deu},
  abstract = {-},
  keywords = {-}
}

@article{erfurth2021_53874,
  title = {Kernel density smoothing of composite spatial data on administrative area level},
  author = {Erfurth, Kerstin and Groß, Marcus and Rendtel, Ulrich and Schmid, Timo},
  year = {2021},
  journal = {AStA Wirtschafts- und Sozialstatistisches Archiv},
  volume = {16},
  number = {1},
  pages = {25-49},
  publisher = {Heidelberg : Springer},
  address = {Berlin},
  issn = {1863-8163},
  doi = {10.1007/s11943-021-00298-9},
  url = {https://fis.uni-bamberg.de/handle/uniba/53874},
  language = {eng},
  abstract = {Composite spatial data on administrative area level are often presented by maps. The aim is to detect regional differences in the concentration of subpopulations, like elderly persons, ethnic minorities, low-educated persons, voters of a political party or persons with a certain disease. Thematic collections of such maps are presented in different atlases. The standard presentation is by Choropleth maps where each administrative unit is represented by a single value. These maps can be criticized under three aspects: the implicit assumption of a uniform distribution within the area, the instability of the resulting map with respect to a change of the reference area and the discontinuities of the maps at the borderlines of the reference areas which inhibit the detection of regional clusters. In order to address these problems we use a density approach in the construction of maps. This approach does not enforce a local uniform distribution. It does not depend on a specifc choice of area reference system and there are no discontinuities in the displayed maps. A standard estimation procedure of densities are Kernel density estimates. However, these estimates need the geo-coordinates of the single units which are not at disposal as we have only access to the aggregates of some area system. To overcome this hurdle, we use a statistical simulation concept. This can be interpreted as a Simulated Expectation Maximisation (SEM) algorithm of Celeux et al (1996). We simulate observations from the current density estimates which are consistent with the aggregation information (S-step). Then we apply the Kernel density estimator to the simulated sample which gives the next density estimate (E-Step).
This concept has been f rst applied for grid data with rectangular areas, see Groß et al (2017), for the display of ethnic minorities. In a second application we demonstrated the use of this approach for the so-called “change of support” (Bradley et al 2016) problem. Here Groß et al (2020) used the SEM algorithm to recalculate case numbers between non-hierarchical administrative area systems. Recently Rendtel et al (2021) applied the SEM algorithm to display spatial-temporal clusters of Corona infections in Germany. Here we present three modif cations of the basic SEM algorithm: 1) We introduce a boundary correction which removes the underestimation of kernel density estimates at the borders of the population area. 2) We recognize unsettled areas, like lakes, parks and industrial areas, in the computation of the kernel density. 3) We adapt the SEM algorithm for the computation of local percentages which are important especially in voting analysis. We evaluate our approach against several standard maps by means of the local voting register with known addresses. In the empirical part we apply our approach for the display of voting results for the 2016 election of the Berlin parliament. We contrast our results against Choropleth maps and show new possibilities for reporting spatial voting results.},
  keywords = {Spatial data, Administrative areas, Choropleths, Kernel density estimation, Voting atlases}
}

@article{kreutzmann2021_52219,
  title = {The Fay–Herriot model for multiply imputed data with an application to regional wealth estimation in Germany},
  author = {Kreutzmann, Ann-Kristin and Marek, Philipp and Runge, Marina and Salvati, Nicola and Schmid, Timo},
  year = {2021},
  journal = {Journal of applied statistics},
  volume = {49},
  number = {13},
  pages = {3278-3299},
  publisher = {Taylor \& Francis},
  address = {Abingdon [u.a.]},
  issn = {0266-4763},
  doi = {10.1080/02664763.2021.1941805},
  url = {https://fis.uni-bamberg.de/handle/uniba/52219},
  language = {eng}
}

@article{walter2021_52207,
  title = {Domain prediction with grouped income data},
  author = {Walter, Paul and Groß, Marcus and Schmid, Timo and Tzavidis, Nikos},
  year = {2021},
  journal = {Journal of the Royal Statistical Society. Series A, Statistics in society},
  volume = {184},
  number = {4},
  pages = {1501-1523},
  publisher = {Wiley-Blackwell},
  address = {London},
  issn = {0964-1998},
  doi = {10.1111/rssa.12736},
  url = {https://fis.uni-bamberg.de/handle/uniba/52207},
  language = {eng},
  abstract = {One popular small area estimation method for estimating poverty and inequality indicators is the empirical best predictor under the unit-level nested error regression model with a continuous dependent variable. However, parameter estimation is more challenging when the response variable is grouped due to data confidentiality concerns or concerns about survey response burden. The work in this paper proposes methodology that enables fitting a nested error regression model when the dependent variable is grouped. Model parameters are then used for small area prediction of finite population parameters of interest. Model fitting in the case of a grouped response variable is based on the use of a stochastic expectation–maximization algorithm. Since the stochastic expectation–maximization algorithm relies on the Gaussian assumptions of the unit-level error terms, adaptive transformations are incorporated for handling departures from normality. The estimation of the mean squared error of the small area parameters is facilitated by a parametric bootstrap that captures the additional uncertainty due to the grouping mechanism and the possible use of adaptive transformations. The empirical properties of the proposed methodology are assessed by using model-based simulations and its relevance is illustrated by estimating deprivation indicators for municipalities in the Mexican state of Chiapas.},
  keywords = {data confidentiality, interval-censored data, nested error regression model, small area estimation, survey response burden}
}

@article{gro2020_52223,
  title = {Switching Between Different Non-Hierachical Administrative Areas via Simulated Geo-Coordinates : A Case Study for Student Residents in Berlin},
  author = {Groß, Marcus and Kreutzmann, Ann-Kristin and Rendtel, Ulrich and Schmid, Timo and Tzavidis, Nikos},
  year = {2020},
  journal = {Journal of official statistics : JOS},
  volume = {36},
  number = {2},
  pages = {297-314},
  publisher = {de Gruyter},
  address = {Berlin},
  issn = {2001-7367},
  doi = {10.2478/jos-2020-0016},
  url = {https://fis.uni-bamberg.de/handle/uniba/52223},
  language = {eng}
}

@article{steorts2020_52221,
  title = {Smoothing and Benchmarking for Small Area Estimation},
  author = {Steorts, Rebecca C. and Schmid, Timo and Tzavidis, Nikos},
  year = {2020},
  journal = {International statistical review : a journal of the International Statistical Institute and its associations},
  volume = {88},
  number = {3},
  pages = {580-598},
  publisher = {Wiley-Blackwell},
  address = {Oxford ; Malden, Mass.},
  issn = {0306-7734},
  doi = {10.1111/insr.12373},
  url = {https://fis.uni-bamberg.de/handle/uniba/52221},
  language = {eng}
}

@article{halbmeier2019_52226,
  title = {The fayherriot command for estimating small-area indicators},
  author = {Halbmeier, Christoph and Kreutzmann, Ann-Kristin and Schmid, Timo and Schröder, Carsten},
  year = {2019},
  journal = {The Stata journal},
  volume = {19},
  number = {3},
  pages = {626-644},
  publisher = {Sage Publishing},
  address = {Thousand Oaks, Calif.},
  issn = {1536-867X},
  doi = {10.1177/1536867X19874238},
  url = {https://fis.uni-bamberg.de/handle/uniba/52226},
  language = {eng}
}

@article{borgoni2019_52225,
  title = {Analysing radon accumulation in the home by flexible M-quantile mixed effect regression},
  author = {Borgoni, R. and Carcagní, A. and Salvati, N. and Schmid, Timo},
  year = {2019},
  volume = {33},
  number = {2},
  pages = {375-394},
  issn = {1436-3240},
  doi = {10.1007/s00477-018-01643-1},
  url = {https://fis.uni-bamberg.de/handle/uniba/52225},
  language = {deu}
}

@article{kreutzmann2019_52224,
  title = {The R Package emdi for Estimating and Mapping Regionally Disaggregated Indicators},
  author = {Kreutzmann, Ann-Kristin and Pannier, Sörenm and Rojas‐Perilla, Natalia and Schmid, Timo and Templ, Matthias and Tzavidis, Nikos},
  year = {2019},
  journal = {Journal of statistical software},
  volume = {91},
  number = {7},
  pages = {1–33},
  address = {Los Angeles, Calif.},
  issn = {1548-7660},
  doi = {10.18637/jss.v091.i07},
  url = {https://fis.uni-bamberg.de/handle/uniba/52224},
  language = {eng}
}

@article{rojasperilla2019_52220,
  title = {Data-driven transformations in small area estimation},
  author = {Rojas‐Perilla, Natalia and Pannier, Sörenm and Schmid, Timo and Tzavidis, Nikos},
  year = {2019},
  journal = {Journal of the Royal Statistical Society. Series A, Statistics in society},
  volume = {183},
  number = {1},
  pages = {121-148},
  publisher = {Wiley-Blackwe},
  address = {Oxfordl},
  issn = {0964-1998},
  doi = {10.1111/rssa.12488},
  url = {https://fis.uni-bamberg.de/handle/uniba/52220},
  language = {eng}
}

@article{tzavidis2018_52227,
  title = {From start to finish : a framework for the production of small area official statistics},
  author = {Tzavidis, Nikos and Zhang, Li‐Chun and Luna, Angela and Schmid, Timo and Rojas‐Perilla, Natalia},
  year = {2018},
  journal = {Journal of the Royal Statistical Society. Series A, Statistics in society},
  volume = {181},
  number = {4},
  pages = {927-979},
  publisher = {Wiley-Blackwell},
  address = {Oxford},
  issn = {0964-1998},
  doi = {10.1111/rssa.12364},
  url = {https://fis.uni-bamberg.de/handle/uniba/52227},
  language = {eng}
}

@misc{baldermann2018_52229,
  title = {Robust Small Area Estimation under Spatial Non-stationarity},
  author = {Baldermann, Claudia and Salvati, Nicola and Schmid, Timo},
  year = {2018},
  volume = {86},
  number = {1},
  pages = {136-159},
  issn = {0306-7734},
  doi = {10.1111/insr.12245},
  url = {https://fis.uni-bamberg.de/handle/uniba/52229},
  language = {deu}
}

@misc{borgoni2018_52228,
  title = {Modelling the distribution of health-related quality of life of advanced melanoma patients in a longitudinal multi-centre clinical trial using M-quantile random effects regression},
  author = {Borgoni, Riccardo and Del Bianco, Paola and Salvati, Nicola and Schmid, Timo and Tzavidis, Nikos},
  year = {2018},
  volume = {27},
  number = {2},
  pages = {549-563},
  issn = {0962-2802},
  doi = {10.1177/0962280216636651},
  url = {https://fis.uni-bamberg.de/handle/uniba/52228},
  language = {eng}
}

@misc{gro2017_52231,
  title = {Estimating the density of ethnic minorities and aged people in Berlin: multivariate kernel density estimation applied to sensitive georeferenced administrative data protected via measurement error},
  author = {Groß, Marcus and Rendtel, Ulrich and Schmid, Timo and Schmon, Sebastian and Tzavidis, Nikos},
  year = {2017},
  volume = {180},
  number = {1},
  pages = {161-183},
  issn = {0964-1998},
  doi = {10.1111/rssa.12179},
  url = {https://fis.uni-bamberg.de/handle/uniba/52231},
  language = {deu}
}

@misc{schmid2017_52230,
  title = {Constructing sociodemographic indicators for national statistical institutes by using mobile phone data: estimating literacy rates in Senegal},
  author = {Schmid, Timo and Bruckschen, Fabian and Salvati, Nicola and Zbiranski, Till},
  year = {2017},
  volume = {180},
  number = {4},
  pages = {1163-1190},
  issn = {0964-1998},
  doi = {10.1111/rssa.12305},
  url = {https://fis.uni-bamberg.de/handle/uniba/52230},
  language = {deu}
}

@misc{warnholz2016_52234,
  title = {Simulation Tools for Small Area Estimation: Introducing the R-package saeSim},
  author = {Warnholz, Sebastian and Schmid, Timo},
  year = {2016},
  volume = {45},
  number = {1},
  pages = {55-69},
  issn = {1026-597X},
  doi = {10.17713/ajs.v45i1.89},
  url = {https://fis.uni-bamberg.de/handle/uniba/52234},
  language = {deu}
}

@misc{tzavidis2016_52233,
  title = {Longitudinal analysis of the strengths and difficulties questionnaire scores of the Millennium Cohort Study children in England using M-quantile random-effects regression},
  author = {Tzavidis, Nikos and Salvati, Nicola and Schmid, Timo and Flouri, Eirini and Midouhas, Emily},
  year = {2016},
  volume = {179},
  number = {2},
  pages = {427-452},
  issn = {0964-1998},
  doi = {10.1111/rssa.12126},
  url = {https://fis.uni-bamberg.de/handle/uniba/52233},
  language = {eng}
}

@misc{schmid2016_52232,
  title = {Outlier Robust Small-Area Estimation Under Spatial Correlation},
  author = {Schmid, Timo and Tzavidis, Nikos and Münnich, Ralf and Chambers, Ray},
  year = {2016},
  volume = {43},
  number = {3},
  pages = {806-826},
  issn = {0303-6898},
  doi = {10.1111/sjos.12205},
  url = {https://fis.uni-bamberg.de/handle/uniba/52232},
  language = {deu}
}

@misc{schmid2013_52235,
  title = {Spatial robust small area estimation},
  author = {Schmid, Timo and Münnich, Ralf},
  year = {2013},
  volume = {55},
  number = {3},
  pages = {653-670},
  issn = {0932-5026},
  doi = {10.1007/s00362-013-0517-y},
  url = {https://fis.uni-bamberg.de/handle/uniba/52235},
  language = {deu}
}

