ANTC67H3 Chapter Notes - Chapter 3 (pg 51-60): Recall Bias, Observational Error, Confounding
Document Summary
Chapter 3 types of studies (pg 51-60) Sources of error can be random or systematic. Random error - when a value of the sample measurement diverges, due to chance alone, from that of the true population value. Sampling error happens when sample is too small therefore not representative of the populations variables. Reduce sampling error by increasing size of study. Reduce measurement error by stringent protocols, making individual measurements as precise as possible. Must be large enough for study to have sufficient statistical power to detect differences deemed important. Sample size calculations need the following data: Required level of statistical significant of the ability to detect a difference. Acceptable error, or chance of missing a real effect. Relative sizes of the groups being compared. In reality, sample size is determined by logistic and financial considerations. Ensuring that groups are of appropriate relative size (ex. case control 4:1)
