Simultaneous Confidence Interval Estimation

Roy, Sasanka; Bose, R. C.

doi:10.1214/aoms/1177728912

Cited by 257 publications

(68 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspection of the means (reported in Table 2), but that this difference did not vary in the five subgroups, as indicated by the fact that none of the interactions, involving sector effect, was significant. In order to find the sector responsible for the difference, the mean scores on the five sectors were compared with one another using the method described by Roy and Bose (1953). Comparisons were performed both on the pool of all subjects, and separately on each of the five subgroups.…”

mentioning

confidence: 99%

Colour imperception in unilateral hemisphere-damaged patients.

Scotti¹,

Spinnler²

1970

Journal of Neurology, Neurosurgery & Psychiatry

View full text Add to dashboard Cite

mentioning

confidence: 99%

Colour imperception in unilateral hemisphere-damaged patients.

Scotti¹,

Spinnler²

1970

Journal of Neurology, Neurosurgery & Psychiatry

View full text Add to dashboard Cite

“…The outcome of the third multivariate hypothesis showed that there was a highly significant difference (P < 0f0001) among the performance of the four brain-damaged subgroups, a finding that inspection of the means of Table 1 suggests to be due mainly to the elective impairment of the right hemisphere subgroup with VFD. In order to verify this point, the scores of the four brain-damaged subgroups and the combined score of the control group were compared with each other by the multiple comparison method of Roy and Bose (1953). Since, at the level of the third multivariate hypothesis, no interaction of a first or higher order with testing modality, the position of the model and the angular score were found significantly to affect the intergroup difference, the multiple comparisons were carried out on the means and not on the set of the eight scores obtained by each group.…”

Section: Methodsmentioning

confidence: 99%

Judgment of spatial orientation in patients with focal brain damage

Renzi

Faglioni

Scotti

1971

Journal of Neurology, Neurosurgery & Psychiatry

100

View full text Add to dashboard Cite

Normal subjects reproduced the orientation of the rod on the horizontal plane with a constant error which was found to be dependent on the position of the model. Clockwise deviations were made when the model was on the left and counterclockwise deviations when the model was on the right. The constant error was present in left brain-damaged patients too, while it was not significantly different from zero in right brain-damaged patients. A systematic error was also found on the vertical plane and it consisted in the tendency to stop the rod below the level of the standard.Findings derived from clinical case study and experimental research support the view that there is both a regional and a hemispheric specialization of the cerebral cortex for spatial functions in the sense that impairment in these functions is associated more closely with damage to posterior than to anterior areas of the brain and of the right more than of the left hemisphere. The evidence, however, is not entirely consistent.

show abstract

“…The reason this result is useful is that one dimensional confidence regions (i.e. confidence intervals or domain of marginals) of a particular measure can be efficiently computed as opposed to simultaneous (multidimensional) confidence regions which are much harder to exactly compute [Roy and Bose 1953;Sison and Glaz 1995]. One easy way of obtaining confidence intervals for commonly used measures would be by using standard formulas.…”

Section: Derivation and Efficient Parameter Estimation Of The Boundmentioning

confidence: 99%

Bounds on the moments for an ensemble of random decision trees

Dhurandhar¹

2014

Knowl Inf Syst

View full text Add to dashboard Cite

An ensemble of random decision trees is a popular classification technique, especially known for its ability to scale to large domains. In this paper, we provide an efficient strategy to compute bounds on the moments of the generalization error computed over all datasets of a particular size drawn from an underlying distribution, for this classification technique. Being able to estimate these moments can help us gain insights into the performance of this model. As we will see in the experimental section these bounds tend to be significantly tighter than the state-of-the-art Breiman's bounds based on strength and correlation and hence, more useful in practice.

show abstract

Simultaneous Confidence Interval Estimation

Cited by 257 publications

References 2 publications

Colour imperception in unilateral hemisphere-damaged patients.

Colour imperception in unilateral hemisphere-damaged patients.

Judgment of spatial orientation in patients with focal brain damage

Bounds on the moments for an ensemble of random decision trees

Contact Info

Product

Resources

About