Skip to main content Accessibility help

We use cookies to distinguish you from other users and to provide you with a better experience on our websites. Close this message to accept cookies or find out how to manage your cookie settings.

Close cookie message
×
  1. Home
  2. Search

Refine search

Refine search

Access:
Content type:
Publication date:
Apply   From and To filters
Subject: Show more
Journals Show more
Publishers: Show more
Societies Show more
Series: Show more
Collections: Show more

Actions for selected content:

Select all | Deselect all
  • View selected items
  • Export citations
  • Download PDF (zip)
  • Save to Kindle
  • Save to Dropbox
  • Save to Google Drive

Save Search

You can save your searches here and later view and run them again in "My saved searches".

Please provide a title, maximum of 40 characters.
Cancel
×

2 results

  • 8 - Tree-Based Classification and Regression

  • John H. Maindonald, Statistics Research Associates, Wellington, New Zealand, W. John Braun, University of British Columbia, Okanagan, Jeffrey L. Andrews, University of British Columbia, Okanagan
  • Book:
    A Practical Guide to Data Analysis Using R
    Published online:
    11 May 2024
    Print publication:
    30 May 2024, pp 373-399

  • Summary

    Tree-based methods use methodologies that are radically different from those discussed in previous chapters. They are relatively easy to use and can be applied to a wide class of problems. As with many of the new machine learning methods, construction of a tree, or (in the random forest approach, trees) follows an algorithmic process. Single-tree methods occupy the first part this chapter. An important aspect of the methodology is the determining of error estimates. By building a large number of trees and using a voting process to make predictions, the random forests methodology that occupies the latter part of this chapter can often greatly improve on what can be achieved with a single tree. The methodology operates more as a black box, but with implementation details that are simpler to describe than for single- tree methods. In large sample classification problems, the methodology has often proved superior to other contenders.

  • Who eats four or more servings of fruit and vegetables per day? Multivariate classification tree analysis of data from the 1998 Survey of Lifestyle, Attitudes and Nutrition in the Republic of Ireland

  • Sharon Friel, John Newell, Cecily Kelleher
  • Journal:
    Public Health Nutrition / Volume 8 / Issue 2 / April 2005
    Published online by Cambridge University Press:
    02 January 2007, pp. 159-169
    • Article
      • You have access
    • PDF
    • Export citation
  • Objective

    To identify, using the novel application of multivariate classification trees, the socio-economic, sociodemographic and health-related lifestyle behaviour profile of adults who comply with the recommended 4 or more servings per day of fruit and vegetables.

    Design

    Cross-sectional 1998 Survey of Lifestyle, Attitudes and Nutrition.

    Setting

    Community-dwelling adults aged 18 years and over on the Republic of Ireland electoral register.

    Subjects

    Six thousand five hundred and thirty-nine (response rate 62%) adults responded to a self-administered postal questionnaire, including a semi-quantitative food-frequency questionnaire.

    Results

    The most important determining factor of compliance with the fruit and vegetable dietary recommendations was gender. A complex constellation of sociodemographic and socio-economic factors emerged for males whereas the important predictors of 4 or more servings of fruit and vegetable consumption among females were strongly socio-economic in nature. A separate algorithm was run to investigate the importance of health-related lifestyle and other dietary factors on compliance with the fruit and vegetable recommendations. Following an initial split on compliance with dairy recommendations, a combination of non-dietary behaviours showed a consistent pattern of healthier options more likely to lead to compliance with fruit and vegetable recommendations. There did, however, appear to be a compensatory element between the variables, particularly around smoking, suggesting the non-existence of an exclusive lifestyle for health risk.

    Conclusions

    Material and structural influences matter very much for females in respect to compliance with fruit and vegetable recommendations. For males, while these factors are important they appear to be mediated through other more socially contextual-type factors. Recognition of the role that each of these factors plays in influencing dietary habits of men and women has implications for the manner in which dietary strategies and policies are developed and implemented.