By now, many of us have seen the recent AT&T commercials featuring a man dressed in a suit asking a group of adorable small children seated around a table "Which is better…bigger or smaller?" Naturally, the children all respond with a resounding, unanimous "bigger!" The suited man then asks "What about a tree house? Would you rather have a bigger tree house or a smaller one?" The children unanimously respond again that they would prefer a larger tree house, primarily because they would like to have a disco and a large, flat screen television. Makes perfect sense, right?

Exactly what a representative sample is or what it looks like is completely dependent on your research objectives

A representative sample is just that…a sample that truly "represents" your target market or audience for your business. Exactly what a representative sample is or what it looks like is completely dependent on your research objectives and the specific information you hope to learn from the research results. Large-scale, specifically targeted quantitative studies may require a large, robust sample, particularly if many targets or subsections of the population are of interest. If the aim of the research is to cut the data by examining differences between multiple "subgroups," a large sample is likely necessary. On the other hand, if the research is more qualitative and aims to gather directional information for a product or brand, a large sample size is most likely not required and could in fact be detrimental.

Another potential issue with obtaining large samples is the issue of statistical significance. When comparing differences between groups with an inflated sample size, nearly EVERYTHING becomes statistically significant, which makes it difficult to interpret the statistics behind the research in a constructive manner. For example, with a large sample size, 50% of Group A may strongly agree with an attribute, while 51% of Group B strongly agrees with the same attribute. Due to an inflated sample size, the statistics may show that Group B agrees with the attribute significantly more than Group A, despite their being only a 1% difference between the two groups. What does this mean? Inflated sample sizes can often give us misleading results, suggesting that there are statistical differences between groups, despite the fact that these statistical differences may not be practical differences. Minimizing these discrepancies comes with determining an appropriate sample size that meets your objectives.

All in all, when it comes to the research process and sampling, bigger isn't always better. Determining the correct sample size is a crucial part of achieving your objectives and getting answers to the questions you need to know!