By Fatima Qureshy
In any measurement system, there are two factors that decide the relevance of data measured: accuracy and precision. So, what is the difference between these two, let’s find out!
Accuracy:
- Accuracy is the proximity (closeness) of measurement results to the true value.
- Therefore, it is the validity of a measurement. If a measurement is not valid, we say it is ‘biased’
- Bias is a systematic error that skews the observation to one side of the truth.
- e.g., a zero error in a measuring scale will affect all the measured values, plus or minus a certain bias that will be the zero error. In order to remove that bias, we correct the zero error.
- Similarly, if in a case control study, all cases are selected from a cancer hospital and controls are general population, the findings will be biased because the cancer hospital patients experienced the long-term circumstances distinctly different from the general population.
- Therefore, a systematic error or a design flaw, reduces the accuracy.
Precision
- If repeated measurements of a characteristic in the same individual under identical conditions produce similar results, we would say that the measurement is precise/reliable.
- It is the reliability of a measurement, meaning that we can make sure that a measured value can be reproduced by the same method and it will be close to the first measured value.
- Therefore, in a set of precise measurements, there is an absence of random variation. The more the precision of a test, the less is the standard deviation.
- A random error reduces the precision. It could be due to a processing error or due to a person’s negligence. A random error would be reduced by making sure to take multiple values, maybe by different people, so it is precise. Precision is really the reproducibility of the same value of measurement.
EXAMPLE QUESTION:
- Four students conducted an experiment to calculate the density of Iron(7.87 g/cm³). Which of the following data is accurate but not precise?
