7 VARIABLES

Research problems are conveyed by a set of concepts. In order to move from the conceptual to the empirical level, concepts are normally converted into variables. It is in the form of variables that concepts appear in hypothesis and are tested.

1.7.1 Definition of the term variable

A variable is a type of quantity that may take on more than one value (Ogula, 1998).  For example, sex is a variable because it takes on two values (male & female).

A variable can also be considered as a measurable characteristic which assumes different characteristics among the subjects. It can take differing or varying values. Thus, a variable is an empirical property that can take on two or more values, (Nachmias & Nachmias, 1996). If a property can change, either in quantity or quality, it can be regarded as a variable. For example, Religious affiliation can be said to be a variable since it can be differentiated into several values: Christian, Moslem, Hindu, Buddhist, etc.

1.7.2 Types of Variables

There are many types of variables. Various types of variables that one is likely to encounter in a research project are discussed here below:

1.7.3 Independent Variables

An independent variable is one that the researcher manipulates or makes changes to in order to determine its effect or influence on the dependent variable. It is the presumed cause of changes in the values of the dependent variable. For example, one may want to determine whether there is any relationship between a particular method of teaching and the students performance in a particular subject. Method of teaching, in this case, is the independent variable while the students performance is the dependent variable.

The independent variable can influence or affect the dependent variable in a positive or negative way. Sometimes this variable has been referred to as a predictor variable because it predicts the amount of variation that occurs in the dependent variable.  

     Independent variable                                                        Dependent variable

1.7.4 Dependent Variables

The dependent variable is the variable which is expected to change as a result of the presence, absence or magnitude of the independent variables (Mbwesa 2006). Its behaviour depends on the behaviours or actions of the independent variable. Hence, dependent variables are also called response variables since they respond to changes made in the independent variables. A dependent variable, sometimes called the criterion variable, attempts to indicate the total influence arising from the effects of the independent variable. A dependent variable varies as a function of the independent variable.  

For instance, in a research question such as The influence of fringe benefits on the teachers morale.  Teachers morale may, to some extent, depend on the nature and variety of fringe benefits.  In this case therefore, teachers morale is the dependent variable while fridge benefits are the independent variables.

Independent Variable                        Dependent Variable

1.7.5 Control Variables

Control variables are used to test the possibility that an empirically observed relation between an independent and a dependent variable is spurious  in other words, that it can be explained only by the presence of another variable, other than those stated in the hypothesis (Nachmias & Nachmias, 1996). By using control variables, the researcher can ensure that there is an inherent, causal link between the variables, as stated in the hypothesis, and that the observed relation is not based on an unforeseen connection with some other phenomenon.

If a researcher suspects that a certain variable is likely to influence the research results, he/she should control for that variable in the study by including it in the study. When a possible extraneous variable is built into the study, it is often referred to as a control variable.

For example, illustrating the significance of control variables is the empirical relation observed between political participation and government expenditure. Is the amount of government expenditure (dependent variable) caused by the extent of political participation (independent variable)? Seemingly, yes. However, research has shown that the empirical relation between political participation and government expenditure vanishes when the control variable of economic development is introduced. The level of economic development influences both government expenditure and political participation.

Without the influence of economic development, the observed relation between political participation and government expenditure would continue to appear valid.

Example: Importance of Control Variable 

         Original observation                          Original observation 

                                                  Spurious Relation

Control variables, thus, serve the important purpose of testing whether or not the observed relations between independent and dependent variables are spurious.

Once extraneous variables are identified, the researcher controls for them in three basic ways:

Build the extraneous variable into the study.

Hold the variable constant: consider only one level or category of the variable. (Include the variable in the study but only at one level)

Remove the effects of the extraneous variable by statistical procedures, that is, control the effects of an extraneous variable by statistically siphoning its effect on the dependent variable.

The two main statistical procedures that are used to achieve this are analysis of covariance and partial correlation.       

1.7.6 Extraneous Variables

These are variables that affect the outcome of a research study either because the researcher is not aware of their existence or if the researcher is aware, he/she does not control for them, (Mugenda & Mugenda 2003).  It is any uncontrolled variable which can influence the outcome of the study or the effect of the independent variable on the dependent variable, (Ogula, 2005).

For example, age may change the way a student performs in an examination irrespective of the teaching method.

1.7.7 Intervening variable

An intervening variable is a type of extraneous variable.  It is a type of a variable which comes between the independent and the dependent variable.  It is recognized as being caused by the independent variable and as being a determinant of the dependent variable (Nachmias & Nachmias, 1996).

For Example: A study on High School teachers absenteeism:

In a study on High School teachers absenteeism, (among female teachers) married women were found to have a higher rate of absenteeism compared to single women. One could therefore conclude that marital status is a determinant of absenteeism.  A search for possible intervening variables in the study revealed that amount of work is indeed an intervening variable. One can also argue that, were it not for the amount of housework, there would not be a difference in the rate of absenteeism between married and single women. The intervening variable amount of work is a consequence of function of marital status and a determinant of absenteeism.

Independent Variable       Intervening Variable      Dependent Variable  

Antecedent Variables:

An antecedent variable comes before the independent variable as shown below:

Antecedent ----------- Independent Variable ----------------- Dependent Variable                                                                                               

An antecedent variable does not interfere with the established relationship between an independent and a dependent variable.  Rather, antecedent variable clarifies the influence that precedes such a relationship.

For instance, a researcher might hypothesize that political stability would attract many investors, that high investments would lead to increased job opportunities, that increased job opportunities would lead to a high standard of living, etc.  Some conditions that must hold for a variable to be classified as an antecedent variable include:

The variables including the antecedent variable must be related in some logical sequence.

When the antecedent variable is controlled for, the relationship between the independent and the dependent variables should not disappear; rather, it should be enhanced.

Suppressor Variables:

A suppressor variable is an extraneous variable, which, when not controlled for, removes a relationship between the two variables, (Mbwesa, 2006).  When a suppressor variable is not controlled for in a study, it intercedes to cancel out, minimize or conceal a true relationship between the independent and the dependent variables.  When a suppressor variable is introduced in the study as a control variable, a true relationship emerges.

Distorter Variables:

A distorter variable is a variable that converts what was thought of as a positive relationship into a negative relationship and vice versa, (Mugenda & Mugenda, 2003).  This effect leads a researcher into drawing erroneous conclusions from the data.  When a distorter variable is controlled for, a true relationship is obtained.

1.7.8 Continuous and Discrete Variables:

An important attribute of variables is whether they are continuous or discrete.  This attribute affects research operations, particularly, measurement procedures, data analysis and methods of statistical inference and logical generalization.

Continuous Variables:

These variables take on values within a given range. They exist in some degree along a continuum.  Such variables can often be subdivided into smaller and smaller units.

A continuous variable does not have a minimum  sized unit.  Length is an example of a continuous variable because there is no minimum unit of length to be found in nature.  A particular object may be at least 10 inches long; it may be 10.5 inches long, or it may be 10.540 inches long.

Examples of a continuous variable are height, test scores which may range from 0 - 100 etc.

Height

       1                2             3               4          5            6         7             8 

Discrete Variables: 

Variables also take on values representing added categories.  All those variables which produce data that falls into categories are said to be discrete since only certain values are possible. Such variables do not vary in degree, amount or quantity but are qualitatively different. For example, Religious Affiliation.

 1.7.9 Dichotomous Variables:

These are variables that have only two values reflecting the presence or absence of a property (Mbwesa, 2006). Examples: male or female, employed, unemployed, etc.  In other words, such variables can only exist in a dichotomous form.

1.8 RELATIONS

A relation in research always refers to a relation between two or more variables. When we say that variable X and variable Y are related, we mean that there is something in common to both variables. For example, if we say that education and income are related, we mean that the two go together that they co-vary, or change together in a systematic way.

1.8.1 Co-variation  

Co-variation means that two or more phenomena vary together (Nachmias & Nachmias, 1996).

For example, if a change in the level of Education is accompanied by a change in the level of income, you can say that education co-varies with income i.e. individuals with higher levels of education have higher income than individuals with lower levels of education.  In scientific research, the notion of co-variation is expressed through measures of relations commonly referred to as correlations or associations.  Thus, in order to infer that one phenomenon causes another, a researcher must find evidence of a correlation between phenomena.

Co-variation is what education and income have in common; individuals with higher education have higher incomes.  Establishing a relationship in empirical research therefore consists of determining whether the values of one variable co-vary with values of one or more other variables and measuring those values.  The researcher systematically pairs values of one variable with values of other variables. 

Example:     Relation between Education & Income:

Observation                         Years of schooling                        Income

Tom

Mary

Tonny

John

15

14

13

12

Ksh 40,000

        35,000

        29,000

        20,000

The table expresses a relation because the two sets of values have been linked  they co-vary:

Higher education is linked with higher income and lower education with lower income.