Statistics - True score (Classical test theory)

1 - About

The true score is the score the truth that we try to estimate.

(Classical test|True score) theory asserts that raw scores are influenced by:

  • bias,
  • chance error,
  • and true scores

3 - Formula

<MATH> \href{Raw Score}{Raw\,Score} = \href{True score}{True\,Score} + \href{bias}{Bias}+Error </MATH>

where:

  • True Score is the score in a perfect world
  • Bias is a systematic error. Example: An instrument that will always measure with the same difference. It has an effect on the entire distribution (It shift it right or left)
  • Error: is also known as Chance error, or random chance error (For example, measurement of body temperature, if someone drink a coffer before measuring its temperature)
data_mining/true_score.txt · Last modified: 2014/02/10 09:29 by gerardnico