| Autor: |
Jayasinghe, D. Y., Jayasinghe, C. L. |
| Zdroj: |
Sankhya B; May2022, Vol. 84 Issue 1, p79-105, 27p |
| Abstrakt: |
This study investigates how average adult human height distributions of various regions around the world have changed over time using a non-parametric approach. Performance of kernel density estimators (KDEs) were compared between various mixtures of Gaussian distributions created using different means, variances and mixing weights. The performance was evaluated for these mixtures using existing bandwidth selection methods, with various kernels and sample sizes and it was revealed for mixtures with distinct multi modes the Sheather & Jones method performed better in general among the considered. The results of this study also revealed that a better practical performance than Sheather & Jones can be achieved for relatively smaller samples from gaussian mixtures in general through a modified plug-in bandwidth. By applying the findings of the simulation analysis on data related to average adult human heights in different regions in the world for different cohorts, interesting observations on average adult human height distributions were made. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink