7.2 reviews of evidence Flashcards
name 2 descriptive observational studies
ecological studies
cross sectional surveys
name 2 analytical observational studies
case control study
cohort study
what is a systemic review?
an overview of primary studies that use explicit and reproducible methods
what is a meta analysis?
a quantitative synthesis of the results of two or more primary studies that addressed the same hypothesis in the same way
what are the purposes of a meta analysis?
- to facilitate the synthesis of a large number of study results
- to systemically collate study results
- to reduce problems of interpretation due to variations in sampling
- to quantify effect sizes and their uncertainty as a pooled estimate
what quality criteria should be included in a meta analysis?
- compliation of complete set of studies
- identification of common variable or category definition
- standardised data extraction
- analysis allowing for sources of variation
what are the problems with meta analysis?
heterogeneity between studies
- modelling for variation (fixed Vs random effects)
- analysing the variation (sub group analysis)
variable quality of the studies
publication bias in selection of studies
what are the two approaches to calculating the pooled estimate Odds ration and its 95% null hypothesis?
fixed effect model - assumes that the studies are estimating exactly the same true effect size. There is one true effect and every study tries to measure that effect.
random effects model - assumes that the studies are estimating similar, but not the same, true effect size. many effects, with one true mean effect.
what is the standard confidence interval?
95%
what are some differences and similarities between fixed and random effect models for variation?
similar
- point estimates e.g odds ratio
different
- confidence interval is often wider in random effects than in fixed effect model
- weighting of studies is more equal between studies in the random effects model than in the fixed effect model
why can similar studies have different results?
- poor study design
- poor design protocol
- poor protocol implementation
how would you asses the quality of a study?
- allocation methods e.g randomisation
- blinding and outcome assessment
- patient attribution
- appropriate statistical analysis
what is publication bias?
studies with statistically significant or favourable results are more likely to be published than those studies with non statistically significant or ‘unfavourable’ results
what diagram can be used to view publication bias?
a funnel plot
- points less distributed = evidence of bias
it measures size of study against measure effect
how is a meta analysis displayed?
as a forest plot