Linked Life Data

2366144

Source:http://linkedlifedata.com/resource/pubmed/id/2366144

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
6
pubmed:dateCreated
1990-8-16
pubmed:abstractText
The assessment of relationships between site-specific variables has been a matter of controversy because of the claim that periodontal sites within individuals can be used as independent observations in statistical models. One problem with this approach is the unreliability of the calculated Type I and Type II error rates. Another problem is that such inappropriate analysis may prohibit a correct assessment of causal relationships between site-specific variables. The host-factor can act as an effect modifier and modulate the magnitude of the site-specific effects and/or the host-factor can act as a confounder by superimposing a patient-effect on the studied site-specific effects leading to bias. As a result, site-specific biological mechanisms of disease progression may be misinterpreted. Sites can be used as the experimental unit of analysis, but the sampling design from which the site-specific data originated should not be ignored.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
D
pubmed:status
MEDLINE
pubmed:month
Jun
pubmed:issn
0022-3492
pubmed:author
pubmed:issnType
Print
pubmed:volume
61
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
368-72
pubmed:dateRevised
2007-11-15
pubmed:meshHeading
pubmed:year
1990
pubmed:articleTitle
Assessment of relationships between site-specific variables.
pubmed:affiliation
Department of Biostatistics, University of Michigan, Ann Arbor.
pubmed:publicationType
Journal Article