How to compare: “amazing cars” and “ugly barracks”, in a marketing survey and in big data
We all participated in surveys, online or in real life. And when we start a new project, we cannot do without polls. But sometimes there are poll results with which it is not clear what to do except to smile , below, in the picture, the result of the poll by the All-Russian Center for the Study of Public Opinion (VTsIOM).
I was curious how the questions with qualitative assessments are being used now and found that VTsIOM, FOM , Levada-Center use mainly a three-band scale (bad / normal / good). In cases of more detailed questions, the scale increases to 5-6 units , but rarely.
')
Then, today, a situation arises in which sociologists move away from a multi-level scale of qualitative assessments and try to use a three-level one. And if sociology can wriggle out of this, then when analyzing decent amounts of data, the need to use qualitative assessments becomes a complicating factor and reduces the reliability of the results. Since, for example, it is almost impossible to distinguish between the concepts “beautiful apartment” and “excellent housing”, and with the answer, one of the characters in “The Twelve Chairs”: “To whom and the mare is a bride”, the multi-traitability of qualities goes beyond reasonable limits.
The gradation mechanism is there and it is well used by banks in determining fraud in financial documents. This is Benford's distribution law, which, in 1984, was proved by Ted Hill .
Theoretical calculations of the proposed tool are presented in this material: “ Benford 's law and distributions falling under it ”.
In Wikipedia, this law is formulated as follows: if we have the base of the number system b (b> 2), then for the digit d (d ∈ {1, ..., b - 1}) the probability of being the first significant digit is:
Based on the above, we obtain a mechanism for the gradation of qualitative features, as follows.
Choose the number of intervals, well, let's say 5, that is, four gradations and one median interval. So b = 6, we obtain the probabilities for the intervals:
1st interval - 0.386853;
2nd interval - 0,226294;
3rd interval - 0.160558;
4th interval - 0.124539;
The 5th interval is 0.101756.
From the statistics of frequency, words evaluating qualitative signs, we make a series in ascending order and affix an index. We carry out the conversion of frequency to the probability of expression. Next, we accumulate probabilities from the tail, until we get a value equal to the extreme row (the 5th), in our case - 0.101756 and words (qualitative definitions), the probabilities of which fall into this amount, are attributed to the 5th range. Further, on a decreasing index, we carry out further summation until we reach the value of the probability of the 4th range and, further, similarly, to the value of the first interval.
As a result, we get clear subsets with real numerical evaluation.
I will not hope that the selection of synonyms is easy. Since everyone determines for himself the result / effort ratio that is convenient for him.
I was curious how the questions with qualitative assessments are being used now and found that VTsIOM, FOM , Levada-Center use mainly a three-band scale (bad / normal / good). In cases of more detailed questions, the scale increases to 5-6 units , but rarely.
')
Then, today, a situation arises in which sociologists move away from a multi-level scale of qualitative assessments and try to use a three-level one. And if sociology can wriggle out of this, then when analyzing decent amounts of data, the need to use qualitative assessments becomes a complicating factor and reduces the reliability of the results. Since, for example, it is almost impossible to distinguish between the concepts “beautiful apartment” and “excellent housing”, and with the answer, one of the characters in “The Twelve Chairs”: “To whom and the mare is a bride”, the multi-traitability of qualities goes beyond reasonable limits.
The gradation mechanism is there and it is well used by banks in determining fraud in financial documents. This is Benford's distribution law, which, in 1984, was proved by Ted Hill .
Theoretical calculations of the proposed tool are presented in this material: “ Benford 's law and distributions falling under it ”.
In Wikipedia, this law is formulated as follows: if we have the base of the number system b (b> 2), then for the digit d (d ∈ {1, ..., b - 1}) the probability of being the first significant digit is:
Based on the above, we obtain a mechanism for the gradation of qualitative features, as follows.
Choose the number of intervals, well, let's say 5, that is, four gradations and one median interval. So b = 6, we obtain the probabilities for the intervals:
1st interval - 0.386853;
2nd interval - 0,226294;
3rd interval - 0.160558;
4th interval - 0.124539;
The 5th interval is 0.101756.
From the statistics of frequency, words evaluating qualitative signs, we make a series in ascending order and affix an index. We carry out the conversion of frequency to the probability of expression. Next, we accumulate probabilities from the tail, until we get a value equal to the extreme row (the 5th), in our case - 0.101756 and words (qualitative definitions), the probabilities of which fall into this amount, are attributed to the 5th range. Further, on a decreasing index, we carry out further summation until we reach the value of the probability of the 4th range and, further, similarly, to the value of the first interval.
As a result, we get clear subsets with real numerical evaluation.
I will not hope that the selection of synonyms is easy. Since everyone determines for himself the result / effort ratio that is convenient for him.
Source: https://habr.com/ru/post/459052/
All Articles