Unbiased population size estimation with design based geometric sampling
M. Cruz, J. González Villa
The sizing of a finite population is a common problem in ecological and social sciences. Manual counting on images is tedious, while automatic computer recognition methods are biased and are known to fail for large populations. We proposed (Cruz et al. 2015) a design unbiased method, based on geometric sampling with a uniform random test system of quadrats. The observed number of units times the sampling period of the test system is an unbiased estimator of the population size. By Monte Carlo resampling of manually annotated images, the relative standard error of the size estimates was found to range between 5-10%. We also developed a theoretical variance predictor based on a single superimposition of the test system. The source code and software of the method are available at http://countem.unican.es. We also discuss why the ratio method based on a stationary model may be expected to be generally biased and less efficient than design based sampling for bounded and finite populations.
Palabras clave / Keywords: particle counting, geometric sampling, stereology, population size estimation
Programado
Sesión V05 Bioestadística
1 de junio de 2018 16:00
Sala 4
Otros trabajos en la misma sesión
J. Espasandín Domínguez, C. Cadarso Suárez, G. Marra, R. Radice, F. Gude
S. Pérez Fernández, P. Martínez Camblor, N. Corral Blanco
R. Alonso Sanz, M. C. Pardo Llorente
Últimas noticias
-
04/06/18
Certificados -
13/04/18
Resumen del programa y Programa detallado -
22/03/18
Descuentos en medios de trasporte para congresistas y acompañantes -
01/02/18
Ampliación del plazo de tarifa superreducida -
19/01/18
Ampliación de plazos -
15/01/18
Programación para el día 29 de mayo -
15/01/18
Conferenciantes plenarios -
12/01/18
Sede: Palacio de Congresos -
24/12/17
Sesión plenaria en memoria del Profesor Pedro Gil -
24/12/17
Corrección bases del Premio Ramiro Melendreras
