Many concepts have a double dimension: a colloquial and a technical one . This is what happens with the “margin of error” label.
in its everyday sense
When a person says “there is no margin for error” in relation to a project, it means that they cannot make a mistake for any reason. On the contrary, it is said that “there is a small margin of error” when a possible mistake does not have serious consequences. It should be taken into account that the meaning of margin depends on the context of the language used.
The statistics is a mathematical tool that allows you to establish measurements on any kind of area. Through it, it is possible to know specific data about different aspects of nature, such as demographic data, voting trends, diseases, among others. An important piece of data for statistical studies is to establish a limit or margin of error for a sample.
The margin of error represents, in a nutshell, the greatest possible error in relation to certain numerical data.
In this sense, there are two types of error margins: one absolute and one relative. The first refers to the accurate measurement of something. In this way, if an object measures 15 cm and when measuring again we notice an error, which actually measures 14.9 cm, the absolute margin of error is 0.1 cm (this means the subtraction between the real measure of the object and the measurement performed from it).
Relative error is determined as follows: the absolute value divided by the actual value. Continuing with the example above, the absolute value is 0.1 cm and the real value is 15 cm, so the relative error will be as follows: 0.1:15 which is equal to 0.00666 cm.
The statistical margin of error in social surveys
This type of calculation is widely used in the preparation of surveys, measuring citizens’ opinions about some aspect of reality , for example, their assessment of a candidate or a political proposal . Although statistics are a neutral and objective tool, in practice, the information provided does not always correspond to the reality of the facts.
Thus, the following question is appropriate: why do social statistics show so many errors? This question has two possible answers:
1) Some statistics have been “cooked” so that their final results do not express what they actually intend to measure;
2) The people surveyed do not always tell the truth, as their answers do not always allow them to know the reality of an issue.