Chance, Bias & Confounding
Precision
Validity
Random Error
Statistical Interference: The aim is to draw conclusions about the population based on our sample
Controlling RE
Validity is the degree to which the inferences drawn from the study are warranted.
Increasing Sample Size = Increases Precision
Precision gives as a margin between which we have some confidence our source population parameter sits within, based on our sample estimate
- Bias will always be there, we need to MINIMISE it as best we can
Internal Validity: This refers to how well the study has been conducted
External Validity: This is the extent to which the results obtained from the sample in the study can be generalised
- Lack of Precision
-Caused by Chance
- Sample may not be completely representative of our source population
When the observed value of a sample differs form the true population (due to chance alone)
- efficient study design that maximises information
- precise instruments
- repeating a measuremenT
- adequate sample size