# Statistical control in quasi-experimental and correlation...

## Statistical control in quasi-experimental and correlation studies

With different methods of constructing a correlation study, its results allow one to answer several questions that summarize all possible conclusions from it.

First, the correlation study answers the question of whether there is a reliable, nonrandom relationship between two or more variables or the variables are not related.

Secondly, it allows you to determine the nature of the connection: direct or reverse (to calculate the correlation coefficients). As already mentioned, a direct link assumes that at high values ​​of one variable the expression of other variables will also be high, and at low, respectively, low. For example, the higher the level of a person's depression, the more negative events he calls when describing his or her prospective future. Feedback suggests that for high values ​​of one variable the values ​​of other variables will be low. For example, the higher the level of depression, the less a woman watches her appearance.

When evaluating cross-tabulation, links that do not necessarily have to be linear are identified, therefore, in an analogous way

the nature of the connection is often not possible, but you can compare the poles of the variables being compared. For example, people who suffer from alcoholism suffer from memory disorders, and people without alcohol dependence are not. Or schoolchildren who eat buns in the buffet, they can pull themselves up on the bar every once, and those who do not eat can pull themselves up at least once.

Third, the calculation of the correlation coefficients makes it possible to estimate the strength of the connection. The correlation coefficient varies from -1 to +1. The value of the coefficient in the range from 0 to +1 expresses a direct relationship, in the range from -1 to 0 - feedback. The closer the value of the correlation coefficient to +1 or -1, the stronger the relationship between the variables, the closer the correlation coefficient to 0, the stronger the connection.

The values ​​of the correlation coefficient +1 and -1 mean that any changes in some variable can be predicted but only by the level of expression of one variable correlating with it. Human behavior is very difficult, therefore, as a rule, this does not happen in life - any psychological construct is connected with many other constructs. For example, the student's score in the examination can not depend 100% on the diligence of the student. It is also related to his intellectual abilities, the availability of resources (associated with the lack of the need to earn a living, raise a child, take care of parents, etc.), the amount of alcohol that he consumes, and many other factors.

However, the most important issue of scientific research, in which the experimenter not only tries to reflect certain external relations, but also strives to penetrate the essence of the phenomenon, concerns the search for cause-and-effect patterns. Correlation and quasi-experimental schemes of organization of scientific research, as well as truly experimental schemes, presuppose such an opportunity. However, the logic of causal inference is somewhat different in them. The basis of the causal conclusion here is the so-called statistical control.

[...]

[...]

[...]

[...]

[...]

[...]

[...]

[...]

[...]

[...]

[...]

[...]

[...]

[...]

## Other services that we offer

If you don’t see the necessary subject, paper type, or topic in our list of available services and examples, don’t worry! We have a number of other academic disciplines to suit the needs of anyone who visits this website looking for help.

## How to ...

We made your life easier with putting together a big number of articles and guidelines on how to plan and write different types of assignments (Essay, Research Paper, Dissertation etc)