Projects
Statistical inference in varying coefficient models with censored data Hasselt University
Statistical inference in varying coefficient models with censored data Hasselt University
Post-selection inference in advanced statistical models KU Leuven
In this thesis the effects of model selection will be investigated for a class of advanced statistical models that go beyond the classical linear regression models. The models may contain a low or high number of variables for which a selection procedure takes place. Inference methods will be developed that are valid in the sense that they take the randomness induced by the variable selection step into account.
Statistical methodology for fraud detection KU Leuven
Fraud detection has important applications in many fields of society and daily life, such as fraud detection of medical insurance funds to help governments protect the 'life-saving money' of people, fraud detection of international trade data to avoid tariff losses, fraud detection of credit card transactions to help banks identify risks, and so on. With the accumulation of data in various fields, the use of statistical methods has gradually ...
Statistical inference of multivariate data with both additive and multiplicative measurement errors. KU Leuven
Statistical analysis not only requires correctly specified statistical models but also data of good quality. However, in many fields, quantities are often measured with error, making statistical methods implemented on error-prone data in need of special adjustments. In the literature on measurement error problems, measurement error models are often assumed to be either additive or multiplicative. In previous work, we consider the case when ...
Robust statistical inference for the chain-ladder method KU Leuven
Stochastic claims reserving in non-life insurance is a major actuarial issue and there is a growing awareness that modern statistical techniques should be used when calculating the overall outstanding claims reserve (i.e. the money that a company should set aside). A very broad literature is available concerning deterministic and stochastic models for forecasting future claims. To model the uncertainty of these claims reserves estimates, the ...
Statistical methods to estimate infectious disease parameters and individual heterogeneity using multivariate serological data Hasselt University
Statistical inference for varying coefficient functions and qualitative constraints Hasselt University
A Statistical Framework for the Analysis of Ecological Data Collected via Citizen Science KU Leuven
Recent global biodiversity declines have prompted increased investments in research towards the understanding of ecosystem dynamics and spatio-temporal trends in species distributions. These complex natural phenomena necessitate the long-term assessment of geographically expansive regions, for which citizen science is considered to be a cost-effective data collection approach. However, study protocols are often absent in citizen science, or ...