Tools of the Trade Flashcards
What is a sample?
A relatively small number of observations (or patients) from which we try to describe the whole population from which the sample has been taken. The sample is usually random.
Normally the mean is calculated for the sample and the confidence interval is used to describe the range within which we think the population mean lies.
What can be estimated from a sample?
The underlying risk in a population
What is a p-value?
The probability of obtaining the study result (relative risk, odds ratio etc.) if the null hypothesis is true.
What can you interpret from a p-value?
A p-value of <0.05 means that there is less than 5% chance of obtaining the study result if the null hypothesis is true, and so we would usually reject the null. The result is statistically significant.
A p-value of >0.05 is usually seen as providing insufficient evidence against the null hypothesis, so we accept the null.
What is odds?
Odds = probability / (1 – probability)
e.g. probability of being exposed/probability of being unexposed
What is relative risk?
Used as a measure of association between an exposure and disease. (quantifies magnitude)
It is the ratio of the incidence rate in the exposed group and the incidence rate in the non-exposed group.
What is attributable risk?
The difference between incidence in exposed and unexposed. (quantifies risk)
Incidence in exposed-incidence in unexposed
Especially useful in evaluating the impact of introduction or removal of risk factors.
What type of study can relative risk be calculated for? Why?
From cohort studies, since the incidence of disease in the exposed and non-exposed is known..
What is the odds ratio of exposure?
Ratio between two odds, e.g. the odds of exposure in the case divided by the odds of exposure in the controls.
What can be interpreted from an odds ratio?
An odds ratio of 1 = exposure is no more likely in the cases than controls
greater than 1 = exposure is more likely in the case group (which implies that exposure might increase the risk of the disease)
less than 1 = exposure is less likely in the case group (which implies that exposure might have a protective effect).
What is a confounding variable?
A factor that is associated with both the exposure and outcome of interest.
Common confounders include age, smoking, socio-economic deprivation.
How can you deal with confounding variables?
Stratification - at the analysis stage of a study, risks are calculated separately for each category of confounding variable, e.g. each age group and each sex separately.
Standardisation - at the analysis stage of a study. Used to produce a Standardised Mortality Ratio for example
Regression- at the analysis stage of a study - statistical modelling is used to control for one or many confounding variables.
How are odds ratios calculated?
Odds of disease in exposed/odds of disease in unexposed
Why can’t incidence be calculated in case-control studies?
Subjects are selected on the basis of their disease status (diseased and a control), not on the basis of exposure.
