Reliability & Validity

A number of errors tend to influence a measurement. Thus, the general situation is:

M=C + E, where E= errors.

The smaller E is the percentage of M, the more accurate is the measurement.

The terms validity, reliability and measurement accuracy are often used interchangeably. Each does have a specific meaning based on the type of measurement error that is present. Measurement error can be either systematic or variable. A systematic error,also known as bias, is the one that occurs consistently. For example, a biased question will produce a measurement error. This type of error will be a systematic error.

A variable error is the one that occurs randomly when something is measured. For instance, if a respondent is in a bad mood, he/she will not respond in the desired manner. Therefore, resulting error would be variable error. This type of error happens less frequently.

The term reliability is used to refer the degree of variable error in a measurement. We define reliability as the extent to which a measurement is free of variable error.

Though validity includes both systematic and variable error but we define validity as the extent to which a measurement is free from systematic error.

Measurement accuracy is defied as the extent to which a measurement is free from systematic and variable error.