Key Terms: Correlation, Type, Relationship, Indicator, Negative Association, Elasticity, Null Hypothesis, Negative Selection, and Relation Hypothesis. Practice Exercise 1.

A negative association means there is no positive association between the variables. Positive association means there is no negative association between the variables. A correlation, however, shows there is some relationship between the variables.

To use correlation to find out if there is a relationship between the variables, you first determine the mean value of the variable. Then you multiply the mean value by the correlation between the variables.

If the mean is greater than zero, then the relationship is positive and if the mean is less than zero, then the relationship is negative. The values of the variables may differ as well. In these cases the correlation between the variables is zero.

A positive association means there is a positive correlation between the variables. Conversely, a negative association means there is a negative correlation between the variables. In either case, a positive relationship is very likely. A negative association is more likely in any case where the correlation between the variables is zero.

A positive relationship between the variables is a strong basis for an argument that the variables are related. To make an argument, a number of factors must all have the same values. Some of the factors may have a high or low value. If there is a high value in one of the factors, then there is a high value in all the other factors.

This means there is a positive relationship between the variables. This also means that there is a good chance of the relationship being a good one. When the numbers are low, the argument has a poor chance of being correct. It is not uncommon to find that there are many negative relationships when there are positive relationships. Also, if there are many positive relationships, it is rare to find many negative relationships.

To support this positive relationship, there may be several factors that affect the relationship. They can all be correlated, so there is a good chance that all of the relationships are positively related. One factor can be found, however, that will be a strong predictor of all the others.

That factor is the size of the negative relationship. A negative relationship will have a stronger effect on the other effects. The relationship will be weaker when the negative relationship is smaller.

A positive correlation between two variables does not necessarily mean there is a direct relationship between them. For example, a positive relationship does not always mean that the relationship is a good one. Sometimes there is just a strong relationship between the two variables. This can be because there are two variables with similar mean values.

To support this idea, the relationship should be a good one for both variables. There are many times when a positive relationship may exist, but the effect on the third variable is not large. In those situations, there is no reason to conclude that the relationship is actually a good one.

Even though the correlation is an important part of the study of statistics, it is not a very good way of determining a relationship between two variables. A positive relationship does not mean there is a good relationship, only that the relationship is likely to be positive. A negative relationship is not a good sign, but it cannot tell us that there is a bad relationship. It only indicates that there is some correlation between the variables. It does not prove anything about the relationship.