Dataset Information

Excess relative risk as an effect measure in case-control studies of rare diseases.

ABSTRACT: Epidemiologists often use ratio-type indices (rate ratio, risk ratio and odds ratio) to quantify the association between exposure and disease. By comparison, less attention has been paid to effect measures on a difference scale (excess rate or excess risk). The excess relative risk (ERR) used primarily by radiation epidemiologists is of peculiar interest here, in that it involves both difference and ratio operations. The ERR index (but not the difference-type indices) is estimable in case-control studies. Using the theory of sufficient component cause model, the author shows that when there is no mechanistic interaction (no synergism in the sufficient cause sense) between the exposure under study and the stratifying variable, the ERR index (but not the ratio-type indices) in a rare-disease case-control setting should remain constant across strata and can therefore be regarded as a common effect parameter. By exploiting this homogeneity property, the related attributable fraction indices can also be estimated with greater precision. The author demonstrates the methodology (SAS codes provided) using a case-control dataset, and shows that ERR preserves the logical properties of the ratio-type indices. In light of the many desirable properties of the ERR index, the author advocates its use as an effect measure in case-control studies of rare diseases.

SUBMITTER: Lee WC

PROVIDER: S-EPMC4412639 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Excess relative risk as an effect measure in case-control studies of rare diseases.

Lee Wen-Chung WC

PloS one 20140101 4

Epidemiologists often use ratio-type indices (rate ratio, risk ratio and odds ratio) to quantify the association between exposure and disease. By comparison, less attention has been paid to effect measures on a difference scale (excess rate or excess risk). The excess relative risk (ERR) used primarily by radiation epidemiologists is of peculiar interest here, in that it involves both difference and ratio operations. The ERR index (but not the difference-type indices) is estimable in case-contro ...[more]

PMID: 25919483

Similar Datasets

Project description:Peripheral blood samples of patients with acute myocardial infarction were matched with those of control patients to identify possible differences in corresponding gene expression profiles. The controls were matched to cases based on gender, age, status of diabetes mellitus and smoking status. Six months cardiovascular survival status of the cases was used to identify two distinct subgroups among the cases. Linear models for microarray data (M-bM-^@M-^XlimmaM-bM-^@M-^Y) were employed to identify differential gene expression. Shrunken centroids technique helped in identifying the subsets of differentially expressed genes with predictive properties in independent samples. Predictive properties were evaluated using bootstrap sampling. Using the limma modeling with the log-fold change threshold of one (clinical significance) and StoreyM-bM-^@M-^Ys q-value approach (statistical significance), sixty transcripts were found to be both clinically and statistically differentially expressed among the cases not surviving the follow-up period relative to controls, while no such transcripts were observed among other surviving cases. The two subgroups of cases exhibited fourteen differentially expressed transcripts. Predictive modeling indicated sixteen out of sixty transcripts to best discriminate between the controls and cases who died during the follow-up period from cardiovascular causes, while for the surviving cases the already non-significant set of transcripts could not be further reduced. Eleven out of fourteen transcripts were found to best discriminate between the two groups of cases using shrunken centroids. The study identified genes, which were differentially expressed during the acute myocardial infarction, including those associated with short-term fatality of the cases. The genome-wide study used matched case-control design, with 97 samples of 90 patients in three disease groups. Matched control samples were used and several (7) technical replicates were performed.

Dataset Information

Excess relative risk as an effect measure in case-control studies of rare diseases.

Publications

Excess relative risk as an effect measure in case-control studies of rare diseases.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure