Introduction
Numerous Instances of interest in our lives entail two or more variables. These bring to our attention the knowledge of their interrelations’. The relationship between variables is among the leading in providing useful insights to their interdependency. This relationship or association between variables, in statistical presentations, may be described as positive, negative or null.
For instance, in America, the relation between the amounts of money a person may use on healthcare in one year can be linked to the number of years he/she survives after the first deposit. This association is termed negative, if the money spent leads to a shorter life expectancy of that individual and vice versa (Utts & Heckard, 2006) .
Association can therefore be referred to as a factor of two variables or more. Taking the instance above, the two variables that we are dealing with are, the number of years survived after the first deposit, and the money spent by the same person on healthcare in that year. In that sense, it is obvious that whenever the values of both variables increase, a positive association is presented, and whenever an inverse in values of the variables is attained, a negative association follows.
In an event that there is no clear relationship between such variables, no association may be assumed, however this depends on the individual dependency ratio. This paper will try to explain by giving examples, what it means to have a positive, negative and null association between two variables (Utts & Heckard, 2006).
Positive association
Two variables may be considered to have a positive association, when a change in value of one variable causes a corresponding change in magnitude of another variable. For instance, in considering growth in people, the association between their heights and weights is considered positive; this is because as height increases, weight also increases (Ferguson, 1966).
Negative association
Consequently, two variables are considered negative if an increase in value of one, leads to a decrease in value of the other. For instance, taking into account the age of used cars against their selling price, the higher the former, the higher its depreciation and the lower its cost. Clearly, this lowers its selling price. This association between age and price of a used car is termed a negative association (Ferguson, 1966).
No association
Two variables may be considered to have no association, when their correlation approaches zero, that is, their interdependency diminishes significantly to an extent that even a significant change in one does not cause a linear change on the other. For instance, in relating the association between number of users and CPU usage, it is quite clear that only a weak association can be transpired from the above; that is, their correlation approaches zero, and thus, not associated (Ferguson, 1966).
Conclusion
Association is a property of any two or more variables and is instrumental in determining the degree of correlation between such variables. Such correlations may be considered positive, negative, or non- associated. Positive association of any two variables is similar to direct proportionality in linear proportions, while negative association is considered similar to inverse proportionality.
In essence, two variables have a positive association when values of one variable have the propensity to increase as values of the other variable increase, while two variables have a negative association when values of one variable have a tendency to decrease as the values of the other variable increase, in cases where there is very weak correlation, the variables are considered non associated (Utts & Heckard, 2006).
References
Ferguson, G. A. (1966). Statistical analysis in psychology and education. New York: McGraw-Hill.
Utts, J. M. & Heckard, R. F. (2006). Activities Workbook for Utts/Heckard’s Mind on Statistics, 3rd / Edition 3. Web.