1993
DOI: 10.1002/1097-0142(19931001)72:7<2075::aid-cncr2820720704>3.0.co;2-#
|View full text |Cite
|
Sign up to set email alerts
|

Influences on inferences. Effect of errors in data on statistical evaluation

Abstract: Background. Inadvertent random and systemic errors introduced into data sets and manipulation of data are well‐defined sources of discrepancies in statistical evaluation of clinical trials. In this study, the authors show the influence of errors on the widely used statistical result, P values. Methods. Using data from a retrospective study of patients with Hodgkin disease treated at the University of Minnesota between 1970 and 1984 and observed to 1988, we introduced various errors into the data to study the i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
6
0

Year Published

1996
1996
2023
2023

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 13 publications
(6 citation statements)
references
References 14 publications
0
6
0
Order By: Relevance
“…The results and inferences of many statistical analyses are extremely sensitive to misclassification, omission, manipulation of data, and error (22). However, bias appears unlikely to explain our findings.…”
Section: Discussionmentioning
confidence: 65%
“…The results and inferences of many statistical analyses are extremely sensitive to misclassification, omission, manipulation of data, and error (22). However, bias appears unlikely to explain our findings.…”
Section: Discussionmentioning
confidence: 65%
“…Large amounts of data typically have numerous data entry errors and duplicate entries about a variable, and it is difficult to identify which item in a data set contains faulty entry. These errors or duplicate entries affect the reliability and results of a study (Levitt, Aeppli, Potish, Lee, & Nierengarten, 1993). Certain models identify equivalent items using a complex, domain-dependent process (Hernández & Stolfo, 1998); however, they are difficult to implement in large-scale assessment research because data files may lack characteristic domain properties.…”
Section: Discussionmentioning
confidence: 99%
“…Moreover, data errors could result in opposite conclusions. In a clinical study comparing the effect of two treatment protocols on patients with Hodgkin’s disease, Levitt et al (1993) demonstrated that omission of one select patient from one treatment group ( n = 37) changed the comparison results from statistical insignificance to significance.…”
Section: Why Do We Care About Data Acquisition and Preprocessing?mentioning
confidence: 99%