Time series models for beach pollution

Beach pollution was assessed visually by beach inspectors on a five-point ratings scale as 0, 1, 2, 3 or 4 corresponding to pollution levels of None, Low, Trace, Medium or High, respectively. The data consisted of 640 days of pollution ratings at 34 beaches in Sydney, Australia, together with concom...

Full description

Saved in:
Bibliographic Details
Published in:Environmental software Vol. 11; no. 1; pp. 25 - 33
Main Author: Jellett, P.M.
Format: Journal Article Conference Proceeding
Language:English
Published: Elsevier B.V 1996
Subjects:
Beaches
Computer programming languages
Computer software
contingency tables
Data reduction
Mathematical models
pollution
Pollution detection
Q1
ratings scale
survey data
Surveys
Time series
Time series analysis
Australia, New South Wales, Sydney
contingency tables
survey data
ratings scale
pollution
Time series
ISSN:0266-9838
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Beach pollution was assessed visually by beach inspectors on a five-point ratings scale as 0, 1, 2, 3 or 4 corresponding to pollution levels of None, Low, Trace, Medium or High, respectively. The data consisted of 640 days of pollution ratings at 34 beaches in Sydney, Australia, together with concomitant wind, rain, ocean current and temperature information. Development of statistically significant relationships between the more subjectively measured pollution data and the more objectively quantified physical variables not only served to explain the occurrence of pollution but lent credibility to the ratings scale itself as a useful measure of visual pollution. Methods for analysing qualitative data were combined with time series models to account for the influence of the physical variables, whose effects were subject to delay and dissipation over time. The GLIM statistical language is suitable for modelling ratings data. It is not generally used for time series modelling. Most commonly available time series software is not suitable for ratings data. The application here required a combination of the two methodologies. Special purpose models were formulated and then software written in the GLIM language to estimate time series models with the survey ratings scale data as the dependent variable and the physical data as the independent variables. The work also raises the possibility of developing forecasts for pollution-free days and led to the development of a new estimation scheme for time series models.
Bibliography:SourceType-Books-1
ObjectType-Book-1
content type line 25
ObjectType-Conference-2
ObjectType-Article-2
SourceType-Scholarly Journals-2
ObjectType-Feature-1
content type line 23
SourceType-Conference Papers & Proceedings-1
ObjectType-Conference-3
ObjectType-Feature-2
ObjectType-Conference Paper-1
ObjectType-Article-3
ISSN:0266-9838
DOI:10.1016/S0266-9838(96)00032-9