Application of a Multivariate Technique to Ecological Survey

1962 ◽  
Vol 50 (1) ◽  
pp. 1 ◽  
Author(s):  
D. J. Harberd
1977 ◽  
Vol 12 (1) ◽  
pp. 51-76
Author(s):  
B. Bobée ◽  
D. Cluis ◽  
A. Tessier

Abstract A water quality sampling programme for James Bay territory established in a previous study has been carried out for the Department of Natural Resources of the Province of Quebec. The network is composed of 5 base-stations, sampled every fortnight to determine the variability with time of the parameters and 16 satellite-stations, sampled five times yearly with a view to determine the spatial variability. The data (major ions and certain nutrients) gathered during the 1974–1975 field survey are subjected to an analysis by a multivariate technique (correspondence analysis) in addition to certain classical statistical methods. The latter have shown that the mean values obtained at satellite stations were representative of the annual mean. In addition, the results permit the determination for a given parameter, of the relationship between stations and, for a given station, the relationship between parameters. In both cases, the formulation of predictive equations was attempted. An overall evaluation of the data by correspondence analysis has permitted: - a more precise definition of the qualitative behaviour of the different sub-basins of the James Bay territory and characterization of their waters;- a proof of the existence of gradual concentration changes in both East-West and North-South directions. Within the original objectives of the network, the results of the study have led to the following recommendations: - to continue synchronised samplings;- to transform a base station with a low information content into a satellite station;- to create a new base station in the eastern part of the territory.


2021 ◽  
pp. 001946622098702
Author(s):  
Swati Prasad ◽  
Ravi Kiran ◽  
Rakesh Kumar Sharma

This study covers the gender-wise analysis of how behavioural factors and socio-economic factors along with the level of financial literacy influence investment decisions of Indian retail investors. Equally pertinent is to understand that will it have a different influence and bearing on males and females. Multivariate technique partial least squares-structural equation modelling (PLS-SEM) has been applied to develop the model and analyse the results. The study used a structured questionnaire for collecting data from retail investors. The findings of PLS-SEM show that in both genders, behavioural factors, socio-economic factors and financial literacy factors significantly affect investment decisions. However, the findings demonstrate that for women investors, the model is more effective. This study may be useful for prospective fund managers as, in many earlier studies, women are considered to be risk aversive. The results demonstrate that there is a need to target women, and the scenario today is not similar to the pre-existing ones. JEL Classification: G110, G4


1993 ◽  
Vol 140 (9) ◽  
pp. 2519-2525 ◽  
Author(s):  
Bertil I. Paålsson ◽  
Eva Öberg

Ecology ◽  
1940 ◽  
Vol 21 (2) ◽  
pp. 273
Author(s):  
Constance E. Hartt ◽  
W. Robyns ◽  
S. H. Lamb
Keyword(s):  

2021 ◽  
pp. 1-20
Author(s):  
Dennis Rosenberg ◽  
Galit Nimrod

Abstract Various factors determine the use of media in later life. Nevertheless, spatial inequalities among older media users have been accorded little attention in academic research. This study aimed to explore differences in variety (number) and intensity (duration) of both traditional and new media use among older adults residing in various types of localities. Data were obtained from the second wave of the ACT (Ageing + Communication + Technology) cross-national survey, comprising 7,927 internet users aged 60 and over from seven countries. The statistical analyses used in the study were chi-square and analysis of variance tests, and linear regression as a multivariate technique. The results indicated that spatial differences concern variety of media use to a greater extent than its intensity, especially with regard to use of traditional media via new devices. Overall, residents of large cities exhibited greater variety and intensity of media use than did their counterparts from smaller localities, especially rural ones. These findings supported the social stratification hypothesis – according to which individuals from more-privileged social backgrounds have better media literacy, use media to a greater extent and benefit from its use more than people from disadvantaged groups. The findings should be considered by practitioners and policy makers.


Euphytica ◽  
2021 ◽  
Vol 217 (6) ◽  
Author(s):  
Daniel Soares Ferreira ◽  
Guilherme Bravin Canal ◽  
Moyses Nascimento ◽  
Ana Carolina Campana Nascimento ◽  
João Marcos Soares Ferreira ◽  
...  

1996 ◽  
Vol 26 (5) ◽  
pp. 810-818 ◽  
Author(s):  
Gordon D. Nigh ◽  
Vera Sit

Forest height–age models are used in forest management to estimate height and (or) site index. It is useful to know the bias and precision of these models in order to evaluate their applicability. Methods are available for validating the models; however, many problems exist with the methods because of a lack of independence in the data and nonconstant error variance across a range of ages. A validation procedure is presented that overcomes these problems by using a multivariate technique (random coefficients) to model the structure of the errors associated with the models. Confidence intervals for bias and precision can then be constructed based on the error structure. This method of validation was demonstrated on the white spruce (Piceaglauca (Moench) Voss) height–age model for British Columbia, Canada. The preliminary validation showed the model to be unbiased for estimating both height and site index; however, its precision was poor.


Sign in / Sign up

Export Citation Format

Share Document