Call us now:
У среду 15.4. 2026. у 14:15 часова, у сали 843, Апостолос Бацидис (Универзитет у Јањини, Департман за математику) ће одржати предавање
Biased samples and weighted distributions: modeling, statistical inference and
applications
Abstract: In numerous scientific domains, including environmental, meteorological, and biomedical research, the probability of observing a unit from a population is frequently proportional to a known non-negative weight, giving rise to a weight-biased sampling mechanism. If this mechanism is ignored, the resulting sample may lead to biased estimators, distorted inference, and ultimately suboptimal decisions. In this seminar, we highlight how weighted distributions offer a coherent framework not only for characterizing the induced bias but also for deriving adjustment methodologies that restore validity to inference procedures. In this context, various problems of statistical inference will be discussed, following a demonstration of the necessity for their study through the lens of real-world problems. Finally, several applications will be presented to illustrate the practical utility and effectiveness of these methodologies.
Related references
Batsidis, A., Tzavelas, G., and Economou, P. (2025). Inference under multivariate
size-biased sampling. Journal of Applied Statistics,15;52(10):1968-1983.
Batsidis, A., Georgakis, A. and Economou, P. (2026). Two-sample problem using a
random and a biased sample. Enviromental and Ecological Statistics. Accepted.
Economou, P., Tzavelas, G., and Batsidis, A. (2020). Robust inference under r-size
biased sampling without replacement from finite population. Journal of Applied
Statistics, 47, 2808-2824.
P. Economou, A. Batsidis, G. Tzavelas and D. Bagkavos (2021). Hypothesis testing
for the population mean and variance based on r-size biased samples. Statistics,
55:4, 894-924.
Tzavelas, G., Batsidis, A. and Economou, P. (2024) Size Biased Frechet Distribution:
Properties and Statistical Inference. J Stat Theory Appl 23, 456-479.
Economou, P., Batsidis, A., Tzavelas, G., Alexopoulos, P. and ADNI (2020).
Berkson’s paradox and weighted distributions: An application to Alzheimer’s disease.
Biometrical Journal, 62, 238-249.
Предавање је могуће пратити и онлајн, путем линка
https://zoom.us/j/96862208366?pwd=MzJkO96zYg7NFwojuS9b4fo6c6BVG4.1
Meeting ID: 968 6220 8366
Passcode: 375663