O small test population has to give results that are

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: the variation • isolate the sensory response to factors of interest • minimize extraneous influences • control sample preparation and presentation • screen and train participants (sometimes) Accuracy • validity • ability of a test to obtain a true measure • predictive validity – do the test results predict what would occur in another situation? o small test population has to give results that are predictive of the larger population Sensitivity • a test cannot miss important differences that are present – it must detect these • minimize error variance • need enough measurements for statistical estimates • avoid false negatives • avoid type II error • minimize beta risk Avoid False Positives • finding a positive result when none is pr...
View Full Document

This document was uploaded on 03/09/2014.

Ask a homework question - tutors are online