Random
Random errors generate a deviation from the correct result due to chance alone. They lead to measurements that are imprecise in an unpredictable way, resulting in less certain conclusions (Gibson, 2005). Precision is reduced as the variability about the mean is increased; the mean or median values are unaffected. There are three sources of random error:
- Individual biological variation e.g. biochemical measurement
- Sampling error e.g. subset of a larger population only selected
- Measurement error e.g. estimation of portion sizes in a dietary assessment
Random, or chance error, generally affects a test’s reliability. Random errors may be reduced by (Rikli, 2000):
- increasing the number of measurements taken;
- the use of standardised measurement techniques;
- the rigorous and consistent training of research assistants undertaking assessments;
- rigorous standard operating procedures throughout the assessment process.
Examples of random variation in diet and physical activity measurement include:
- variation with time;
- problems associated with memory and recall;
- inadequate or confused explanations from the investigators;
- changes in behaviour due to the measurement procedure;
- dietary coding errors;
- error in estimating portion sizes;
- limitations within a nutrient database;
- improper calibration of instruments;
- inconsistent placements of instruments on the body;
- incorrect translations or coding of outcome data.
Example - Sources of variation in nutrient intakes among men in Shanghai, China
Example - Sources of variance in daily physical activity levels as measured by an accelerometer
References
Gibson R 2005
Principles of Nutritional Assessment
Oxford University Press, Oxford
Second Edition
Patterson P
Reliability, validity, and methodological response to the assessment of physical activity via self-report
Res Quart Exerc Sport. 2000; 71:15-20
Rikli RE
Reliability, validity, and methodological issues in assessing physical activity in older adults
Res Quart Exerc Sport. 2000; 71:89-96