Dataset Information

Effectiveness of strategies to increase the validity of findings from association studies: size vs. replication.

ABSTRACT:

Background

The capacity of multiple comparisons to produce false positive findings in genetic association studies is abundantly clear. To address this issue, the concept of false positive report probability (FPRP) measures "the probability of no true association between a genetic variant and disease given a statistically significant finding". This concept involves the notion of prior probability of an association between a genetic variant and a disease, making it difficult to achieve acceptable levels for the FPRP when the prior probability is low. Increasing the sample size is of limited efficiency to improve the situation.

Methods

To further clarify this problem, the concept of true report probability (TRP) is introduced by analogy to the positive predictive value (PPV) of diagnostic testing. The approach is extended to consider the effects of replication studies. The formula for the TRP after k replication studies is mathematically derived and shown to be only dependent on prior probability, alpha, power, and number of replication studies.

Results

Case-control association studies are used to illustrate the TRP concept for replication strategies. Based on power considerations, a relationship is derived between TRP after k replication studies and sample size of each individual study. That relationship enables study designers optimization of study plans. Further, it is demonstrated that replication is efficient in increasing the TRP even in the case of low prior probability of an association and without requiring very large sample sizes for each individual study.

Conclusions

True report probability is a comprehensive and straightforward concept for assessing the validity of positive statistical testing results in association studies. By its extension to replication strategies it can be demonstrated in a transparent manner that replication is highly effective in distinguishing spurious from true associations. Based on the generalized TRP method for replication designs, optimal research strategy and sample size planning become possible.

SUBMITTER: Weitkunat R

PROVIDER: S-EPMC2896945 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveTo investigate the replication validity of biomedical association studies covered by newspapers.MethodsWe used a database of 4723 primary studies included in 306 meta-analysis articles. These studies associated a risk factor with a disease in three biomedical domains, psychiatry, neurology and four somatic diseases. They were classified into a lifestyle category (e.g. smoking) and a non-lifestyle category (e.g. genetic risk). Using the database Dow Jones Factiva, we investigated the newspaper coverage of each study. Their replication validity was assessed using a comparison with their corresponding meta-analyses.ResultsAmong the 5029 articles of our database, 156 primary studies (of which 63 were lifestyle studies) and 5 meta-analysis articles were reported in 1561 newspaper articles. The percentage of covered studies and the number of newspaper articles per study strongly increased with the impact factor of the journal that published each scientific study. Newspapers almost equally covered initial (5/39 12.8%) and subsequent (58/600 9.7%) lifestyle studies. In contrast, initial non-lifestyle studies were covered more often (48/366 13.1%) than subsequent ones (45/3718 1.2%). Newspapers never covered initial studies reporting null findings and rarely reported subsequent null observations. Only 48.7% of the 156 studies reported by newspapers were confirmed by the corresponding meta-analyses. Initial non-lifestyle studies were less often confirmed (16/48) than subsequent ones (29/45) and than lifestyle studies (31/63). Psychiatric studies covered by newspapers were less often confirmed (10/38) than the neurological (26/41) or somatic (40/77) ones. This is correlated to an even larger coverage of initial studies in psychiatry. Whereas 234 newspaper articles covered the 35 initial studies that were later disconfirmed, only four press articles covered a subsequent null finding and mentioned the refutation of an initial claim.ConclusionJournalists preferentially cover initial findings although they are often contradicted by meta-analyses and rarely inform the public when they are disconfirmed.

Project description:ContextThere are growing concerns about effect size inflation and replication validity of association studies, but few observational investigations have explored the extent of these problems.ObjectiveUsing meta-analyses to measure the reliability of initial studies and explore whether this varies across biomedical domains and study types (cognitive/behavioral, brain imaging, genetic and "others").MethodsWe analyzed 663 meta-analyses describing associations between markers or risk factors and 12 pathologies within three biomedical domains (psychiatry, neurology and four somatic diseases). We collected the effect size, sample size, publication year and Impact Factor of initial studies, largest studies (i.e., with the largest sample size) and the corresponding meta-analyses. Initial studies were considered as replicated if they were in nominal agreement with meta-analyses and if their effect size inflation was below 100%.ResultsNominal agreement between initial studies and meta-analyses regarding the presence of a significant effect was not better than chance in psychiatry, whereas it was somewhat better in neurology and somatic diseases. Whereas effect sizes reported by largest studies and meta-analyses were similar, most of those reported by initial studies were inflated. Among the 256 initial studies reporting a significant effect (p<0.05) and paired with significant meta-analyses, 97 effect sizes were inflated by more than 100%. Nominal agreement and effect size inflation varied with the biomedical domain and study type. Indeed, the replication rate of initial studies reporting a significant effect ranged from 6.3% for genetic studies in psychiatry to 86.4% for cognitive/behavioral studies. Comparison between eight subgroups shows that replication rate decreases with sample size and "true" effect size. We observed no evidence of association between replication rate and publication year or Impact Factor.ConclusionThe differences in reliability between biological psychiatry, neurology and somatic diseases suggest that there is room for improvement, at least in some subdomains.