Essays about: "statistics inference"

Showing result 11 - 15 of 47 essays containing the words statistics inference.

  1. 11. Spatial Statistical Modelling of Insurance Claim Frequency

    University essay from Lunds universitet/Matematisk statistik

    Author : Daniel Faller; [2022]
    Keywords : Insurance risk; claim frequency; Markov chain Monte Carlo MCMC ; Riemann manifold Metropolis adjusted Langevin algorithm MMALA ; spatial statistics; Gaussian Markov random field GMRF ; preconditioned Crank Nicolson Langevin algorithm pCNL ; Gibbs sampling; Bayesian hierarchical modelling; high dimensional; shrinkage prior; horseshoe prior; regularisation.; Mathematics and Statistics;

    Abstract : In this thesis a fully Bayesian hierarchical model that estimates the number of aggregated insurance claims per year for non-life insurances is constructed using Markov chain Monte Carlo based inference with Riemannian Langevin diffusion. Some versions of the model incorporate a spatial effect, viewed as the relative spatial insurance risk that originates from a policyholder's geographical location and where the relative spatial insurance risk is modelled as a continuous spatial field. READ MORE

  3. 12. Multi-Camera Multi-Person Tracking Using Reinforcement Learning

    University essay from Lunds universitet/Matematik LTH

    Author : Axel Kärrholm; Linus Rickman; [2022]
    Keywords : Multi-Camera Multi-Object Tracking; Reinforcement Learning; Computer Vision; Machine Learning; Object Detection; Mathematics and Statistics;

    Abstract : The problem of multi-object-tracking in a network of cameras is an interesting and non-trivial problem. Given videos from a number of cameras the goal of Multi-Camera Multi-Object Tracking (MCMOT) is to find the full visible trajectory of each pedestrian from the videos as the pedestrians move across cameras. READ MORE

  4. 13. Land of the Rising Women? Estimating the Effect of Gender Culture on Regional Variations in Female Labour Force Participation in Japan

    University essay from Handelshögskolan i Stockholm/Institutionen för nationalekonomi

    Author : Rasmus Salén; Jakob Ringberg; [2022]
    Keywords : female labor force participation; gender culture; regional differences; instrumental variable estimation; latent variable;

    Abstract : This paper analyses the explanatory power of differences in gender culture on persistent regional variations in female labour force participation across Japan. The phenomenon is scarcely studied, and establishing causality has never been the subject of research. READ MORE

  5. 14. The Extended Maximum Likelihood Estimation for Monotone Probability Mass Function with Application using Forensic Data

    University essay from Lunds universitet/Matematisk statistik

    Author : Tiancheng Ma; [2022]
    Keywords : Statistical Inference Statistics Maximum Likelihood Estimation Non-parametric Estimation; Mathematics and Statistics;

    Abstract : This paper presents solutions to the modelling of frequency data of species labels, but the data is incomplete in the sense that some rarely-occurring species labels give zero observed frequency. The data can be modelled by a monotone probability function with parameters to be estimated, and yet, due to the order constraints and the incomplete data, using conventional parameter estimation methods will cause trouble. READ MORE

  6. 15. Evaluation of Probabilistic Programming Frameworks

    University essay from Uppsala universitet/Statistiska institutionen

    Author : Carl Munkby; [2022]
    Keywords : Computational statistics; Bayesian statistics; Probabilistic programming; Probabilistic modelling; Stan; TensorFlow Probability; Pyro; NumPyro; Markov Chain Monte Carlo; Hamiltonian Monte Carlo; NUTS;

    Abstract : In recent years significant progress has been made in the area of Probabilistic Programming, contributing to a considerably easier workflow for quantitative research in many fields. However, as new Probabilistic Programming Frameworks (PPFs) are continuously being created and developed, there is a need for finding ways of evaluating and benchmarking these frameworks. READ MORE