Prof Muhammad Nur Aidi: Spatial Method is More Powerful in Describing Environmental and Health Problems in Indonesia

According to the Permanent Professor of the Faculty of Mathematics and Natural Sciences (FMIPA) IPB University, Prof Muhammad Nur Aidi, the estimation model of spatial statistics is more powerful than non-spatial statistical models. Especially in describing problems in the fields of poverty, disease and the environment.

He conveyed this in his presentation entitled The Use of Spatial Statistical Estimation Models in the Context of Environmental and Health Problems in Indonesia at the Online Professor's Pre Oration Press Conference (17/6) online.

“Problems (poverty, disease and the environment) that exist in Indonesia are always related to the amount and how it is distributed in the territory of Indonesia, as well as the factors that are thought to be the cause. The search for the causal factors, the number of events, the pattern of distribution and the alleged occurrence (poverty, disease and environmental pollution) will be more powerful if use a spatial statistical estimation model," explained the expert on Statistical Modeling of IPB University.

This spatial statistical estimation model is divided into three form. There are point data, lattice data and continuous data. This point data describes the existence of an object in space, usually calculated in a count value. For example, data on the distribution of disease, distribution of the poor and others.

Meanwhile, continuous data in space is data in which at every position in the space the data value is always obtained. The last is lattice data, namely data in the form of areas. This data is generally in the form of regional boundaries. For example, data on the number of people affected by Dengue Hemorrhagic Fever (DHF) per district.

“Spatial statistical estimation model for point objects is powerful enough to study the distribution of TB disease, filariasis, DHF and the factors that influence them. Spatial statistical estimation model for continuous data is able to estimate pollution values, pollution patterns, pollution locations, and pollution volumes. And the estimation model of spatial statistics for lattice data is able to predict the factors that influence the response variables, both locally and globally with a high level of accuracy. Especially in cases of malaria,  Dengue Hemorrhagic Fever (DHF), TB, stunting, and those related to the environment. Such as forest fires, climate and poverty," explained the IPB University lecturer from the Statistics Department.

From the results of this study, Prof Nur Aidi concluded that the estimation model of spatial statistics can be used properly to explain the behavior of objects in spatial space. Whether it's data in the form of points, in the form of areas (lattice data) or continuous space.

“Spatial statistical estimation models for point objects can be used effectively to identify patterns of object distribution, such as the distribution of disease, the distribution of the poor and others. Spatial statistical estimation models for continuous data in space are very good for estimating the value and position of points in a space, such as air pollution, water pollution, location elevation data, oxygen content data in water, soil and air and others. And the estimation model of spatial statistics for lattice-shaped data is very well used to find factors that affect response variables, both local and global factors," he said. (Zul) (IAAS/AML)

Published Date : 17-Jun-2021

Resource Person : Prof Muhammad Nur Aidi

Keyword : Spatial Data, Statistics, Statistical Modeling, IPB University, FMIPA