What do comparative weights, probability weights mean, and what are the differences?

Weighting is a relative concept for a certain indicator. The weight of an indicator refers to the relative importance of the indicator in the overall evaluation.

Example. For example, if you give it a score of 100 and your boss gives it a score of 60, if it is average, it is (100 + 60) 2 = 80 points. But because the weight of what the boss says is heavier than yours, if the weight of the boss is 2 and you are 1, then the average is taken.

It's a weighted average, and the result is (100*1 + 60*2) (1+2)=points, which is obviously tilted towards your boss. If the boss weight is 1 and your weight is 3, the result is (100*3+60*1) (1+3)=90. This is the calculation of the average according to the different weights, so it is also called the weighted average.

Probability, in short, the chance of an event occurring or occurring. It is impossible for any ** to rise forever, it can only rise and fall.

Is it really a strict probability game? Let's take a look at a simple example, what is the probability that the stock price will rise on the 3rd day if it rises for 2 consecutive days? 50%？

Theoretically, the probability of rising and ** is 50%, but history tells us that the probability of the stock price rising on the third day is much greater than the probability of **! Therefore, we must also seize the hot spots, find the right rhythm, and attack decisively.

It means that in fact, the market is a matter of probability, either up or down, what you need to judge is that the probability of going up is high or the probability of going down is on the line, and then operate!! Me.

The difference between weights and probabilities is that weights are only used in discrete cases, whereas probabilities exist in both discrete and continuous.

In the case of pairs and discreteness, the weights are equal to the probabilities.

For example, the probability and weight in a binomial distribution are the same.

Also, if it is a sample survey, we get a lot of values (in reality, sample surveys will hardly get too much of the same data, such as randomly selecting 100 people to measure height), then we divide the data into regions (for example, divide the height into several levels, such as the question of how many people are 165cm and 175cm tall), so that the probability and weight of falling in this area are the same, which is equivalent to reducing the problem to a discrete situation.

(1) Probability weight, which is the average rate of return of weighted stocks.

The relationship between the probability weight moment and the linear moment, and the calculation formula of the linear moment is the linear combination of the probability weight moment, and the calculation results of the two are exactly the same. Both the probability weight moment and the linear moment are related to the specified frequency distribution pattern and the probability as the weight, and the sensitivity of the results is poor.

For ** revenue applications, their calculations are only preliminary estimates and can only be used after a plausibility analysis.

2) The method of determining the weight of the evaluation index, the comparative weight is an important index system in the comprehensive evaluation, and the reasonable allocation of the weight is the key to quantitative evaluation. Therefore, whether the composition of the weights is reasonable or not directly affects the scientific nature of the assessment. There are many ways to determine weights, such as expert consultation method (DELPHI), expert ranking method, and analytic hierarchy process.

Rank-sum ratio (RSR), correlation coefficient method, principal component analysis.

and factor analysis, but each method has its advantages and disadvantages. Here, it would be more convenient and efficient to calculate the return with a probability weight and a loss with a comparison weight, and it would be more possible to derive the magnitude of the gain and loss (yield and loss ratio).