Representativeness of the sample

A sample is a set of data taken with the help of certain procedures from the general population for research analysis. Representativeness is the property of reproducing the idea of the whole in its part. Otherwise, it is possible to spread the notion of a part to the whole, which this part includes.

Representative sampling is an indicator that the sample should fully and reliably reflect the characteristics of the population of which it is a part. It can also be defined as a property of the sample to represent the characteristics of the general population that are essential from the point of view of the purpose of the research.

Let's assume that the general population is all pupils of the school (900 people from 30 classes, 30 people in each class). The object of research is the attitude of schoolchildren towards smoking. A sample set consisting of 90 students of only the upper grades will represent a much worse aggregate than a sample of the same 90 students, which would include 3 students from each class. The main reason is the unequal distribution by age. Thus, in the first case the representativeness of the sample will be low. In the second case - high.

In sociology, they say that there is a representativeness of the sample and its non-representativeness.

As an example of a non-representative sample, we can cite the classic case that occurred in 1936 in the US during the presidential election.

The "Literary digest" magazine, which previously had quite successfully predicted the results of previous elections, this time made a mistake in its forecasts, although it sent out several million written questions to subscribers, as well as to respondents they chose from phone books and from car registration lists. In 1/4 of the ballots that returned filled back, the votes were distributed as follows: 57% gave priority to the Republican candidate Alf Landon, and 41% preferred the current president - Democrat Franklin Roosevelt.

In fact, the election won F. Roosevelt, which scored almost 60% of the vote. The error of the "Literary digest" was as follows. They wanted to increase the representativeness of the sample . And since they knew that most of their subscribers refer themselves to Republicans, they decided to expand the sample at the expense of the respondents they selected from phone books and car registration lists. But they did not take into account the existing realities and actually selected more supporters of the Republicans, because in the Great Depression, cars and telephones could afford the middle and upper class. And this was mostly Republicans, not democrats.

There are different types of sampling: simple random, serial, typical, mechanical and combined.

A simple random sample consists of selecting from the whole set of units studied at random without any system.

A mechanical sample is used when there is orderliness in the general population, for example, there is a certain sequence of units ( employee registration numbers , electoral lists, respondents' phone numbers, apartment and house numbers, etc.).

Typical selection is used when the entire population can be divided into groups by type. At work with the population such can be, for example, educational, age, social groups, at research of the enterprises - branch or the separate organization, etc.

Serial selection is convenient when units are combined into small series or groups. Such a series can be lots of finished products, school classes, work collectives and other groups.

Combined sampling involves the use of all previous types of sampling in a particular combination.