1982
DOI: 10.1111/j.1600-0528.1982.tb00392.x
|View full text |Cite
|
Sign up to set email alerts
|

Number of independent variables in the regression based prediction of oral health

Abstract: The effects of the optimistic bias of R2 on oral health data were investigated by means of a cross validation study in which the number of predictors in a regression model was manipulated. The use of too many predictors increased positive bias and reduced the true predictive quality of a regression model and should be avoided through the use of appropriate stepwise procedures.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
2
0

Year Published

1991
1991
1993
1993

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 1 publication
0
2
0
Order By: Relevance
“…The independent variables entering the multiple regression analyses have been selected on the basis of their theoretical importance in order to minimize positive bias and reduced predictive quality of the regression mode! (Lavstedt & Ekiund 1975, Cohen & Cecil 1982, Rise 1984. The coefficient of determination reported in the multiple regression analysis with B/R as the dependent variable is high (-R'^67%); /^ of the variance of B/R is thus explained by the selected independent variables.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…The independent variables entering the multiple regression analyses have been selected on the basis of their theoretical importance in order to minimize positive bias and reduced predictive quality of the regression mode! (Lavstedt & Ekiund 1975, Cohen & Cecil 1982, Rise 1984. The coefficient of determination reported in the multiple regression analysis with B/R as the dependent variable is high (-R'^67%); /^ of the variance of B/R is thus explained by the selected independent variables.…”
Section: Discussionmentioning
confidence: 99%
“…The predictive relationship between an oral health-dependent variable (for instance, alveolar bone level) and a number of independent variables or predictors such as those mentioned above may be studied using multiple regression analyses (Lavstedt & Eklund 1975, Rise 1984, Bergstrom & Ehasson 1987, Papapanou et al 1988. To avoid increased positive bias and reduced predictive quality of the regression model, the independent variables entering the multiple regression equation must be carefully selected on the basis of their theoretical importance (Cohen & Cecil 1982).…”
mentioning
confidence: 99%