4.2 Characteristics of a good sample: accuracy and precision

Characteristics of a good sample: accuracy and precision

  

Two conditions are appropriate for a census study. These are when a census is (1) feasible     (meaning when the population is small),  and (2) necessary (meaning  when the elements are quite different from each other.  However , there are several compelling reasons for sampling, including (1) lower cost, (2) greater accuracy of results, (3) greater speed of data collection, and (4) availability of population elements.

What is a good sample then? The ultimate test of a sample design is how well it represents the characteristics of the population it purports to represent. In measurement terms, the sample must be valid. Validity of a sample depends on two considerations:  accuracy and precision.

Accuracy is the degree to which bias is absent from the sample. When the sample is drawn properly, the measure of behaviour, attitudes, or knowledge (or the measurement variables) of some sample elements will be less than (thus, underestimate) the measure of those same variables drawn from the population. Also, the measure of the behavior, attitudes, or knowledge of other sample elements will be more than the population values (thus, overestimate them). Variations in these sample values offset each other, resulting in a sample value that is close to the population value. For these offsetting effects to occur, however, there must be enough elements in the sample, and they must be drawn in a way that favors neither overestimation nor underestimation.

Therefore , an accurate (unbiased) sample is one in which the underestimators offset the overestimators. Systematic variance has been defined as “the variation in measures due to some known or unknown influences that ‘cause’ the scores to lean in one direction more than another.”

Precision is measured by the standard error of estimate, a type of standard deviation measurement; the smaller the standard error of estimate, the higher is the precision of the sample. The ideal sample design produces a small standard error of estimate. However, not all types of sample design provide estimates of precision, and samples of the same size can produce different amounts of error.