Sampling Standards in Retail Measurement

Retail measurement services providers maintain global standards for sampling error, reflecting the acceptable tolerance level of error, at specified level of confidence, for their retail audits. For instance, Nielsen’s global standard for sampling error, set at 90% level of confidence and applicable to categories that are available in 80% of the universe, is as follows:

National Market ± 3% of sales level

Major Market Breakdowns/Channels ± 6% of sales level

Minor Market Breakdowns ± 6 to 10% of sales level

According to this standard, the sample should be configured such that for a national market, the probability that estimated sales value will lie within ± 3% of actual value is 90%.

Note also that accuracy standards are dependent on the availability of the category being measured. If it is available only in a small proportion of stores, the effective sample for the category is much lower, and that adversely impacts the sampling error for sales estimate. Hence the stipulation above, that the global standard applies to categories that are present in at least 80% of the universe of stores.