Bias

Abstract

Bias or tendentiousness is a introduction of systematic error to a sample or test, by selecting or encouraging results or answer in prejudice or preference of other. In other point of view is a deviation of the expected value of a statistical estimate form the quantity it estimates. A group of person or things containing of one kind than normal, therefore not giving far or accurate results. It's a term that define how far the statistical average is from the statistical calculated test parameter. This error appear when somebody is estimating.. This term is internationally knowed as bias. It is used to describe differece between the founded and the true. "Any effect in any stage of investigation or inference that tends to produce systematically differente results from the true (to distinguish from random error)." Some samples of bias: healthy selection bias, compliance selection bias, vigilance or diligence bias, survivor or natural bias. The double blind randomized clinical trial investigations is a good sample of how to reduce bias. Copyright - SBRA - Sociedade Brasileira de Reprodução Assistida.