The word Variable is an integral component of the life of any researcher. In the context of investigation in research, concepts are what we call as variables. The name itself implies its meaning, “It is something that varies.”
Does this term confuse you too much and you feel perplexed trying to exactly understand the importance of this term in research, its importance, and the types. Do not get overwhelmed. The concept is very simple and once understood well, it will make your research journey smoother and faster in many ways.
So let us first learn the definition of the term variable in context of research:
What is a variable in research?
In the domain of research, a variable is any property, characteristic, number, or a quantity that can vary (increase or decrease) over a period. They can even take different values in different situations. This contrasts with constants that do not vary.
In an event when a researcher is conducting research, experiments tend to manipulate the variables and their type might vary from research to research. For instance, a researcher might want to compare the effectiveness of four different drugs on a disease. Here the variable is going to be “the type of drug.” In a different situation, another researcher may want to study the impact of increase in working force of women on divorce rates. Here increase in the working force is the variable.
A business researcher might want to study the impact of covid on share prices. Here covid is the variable. Similarly, effectiveness, divorce, and share prices are also variables because they also vary due to manipulating fertilizers, early marriage, and dividends.
Variable examples
With some of the research topic examples we saw above; they are all research variables. The list of long and exhaustive. Let us look at some of the commonly used variables in research carried out around the world
All the examples given below are of variables and the common thing in them is the properties of each one of them is going to be different from person to person.
⦁ Age,
⦁ gender,
⦁ income
⦁ expenditure,
⦁ family size,
⦁ country of birth,
⦁ capital expenditure,
⦁ class grades,
⦁ blood pressure readings,
⦁ preoperative anxiety levels,
⦁ eye color, and
⦁ vehicle type.
These are few examples for you to relate and identify with the term variable and its application in research. Depending upon the kind of research, the variables can be anything that is going to vary.
Depending upon factors such as the type of research, the nature of the variable and the type statistical technique used on it, variables can be broadly classified into eight main categories
Let us look at all the eight types of variables with simple and relatable examples to help you understand the difference in them along with way they are applied in research
⦁ Qualitative Variable
⦁ Quantitative Variable
⦁ Discrete Variable
⦁ Continuous Variable
⦁ Independent Variable
⦁ Dependent Variable
⦁ Background Variable
⦁ Moderating Variable
⦁ Qualitative Variable
This is the primary distinction between variables, the qualitative and the quantitative types.
As the same signifies, qualitative variables are the ones that talk about an attribute that is qualitative in nature or to say, not numeric in nature, such as gender, social status, race, religion, color of eyes, geographical location, color of hair or skin, mode of payment and so on. Examples can be many. The unique identity of qualitative variables is that they do not have any logical numerical ordering.
For example, in the case of geographical location (India, Singapore, United Kingdom, USA), the value differs in qualitative terms. No ordering of geographical location is implied. These variables are sometimes even called as categorical variables. Let us look at how:
The variable “Gender” has two distinct characteristics, make and female. These values are expressed in categories and hence we call them as categorical variables. In another example, the place of residence if we tried to put in categories can be rural and urban, thus that also becomes a categorical variable.
In further splitting, categorical variables are either nominal or ordinal.
Do you understand the difference between nominal and ordinal, let us look at it in simple terms with examples to make its application clear
Ordinal variables can be put into sequence in a logical manner or in other words, ranked from higher to lower but at the same time they do not necessarily establish a numeric difference between each of the category. Examples could be grades in examination (A+,A,B+,B,C+,C etc) or clothing sizes (XXL, XL, L,M, S, XS).
Nominal variables cannot be ranked or even put in a logical order. For instance, religion, gender, geographical location.
A qualitative variable is unique in a way that it is not capable of being measured but can be categorized as having or not having certain characteristics.
⦁ Quantitative Variables
These are also called as numeric variables and these are the ones that can be measured in numbers. The simplest example of a quantitative variable in context of research is the age of the respondent.
Age is different for each person. One person could be 20 years, or 35 years and so on. Similarly, family size would also be a quantitative variable because the number of members in the family will be numeric and could be anything from 2 members to a larger number.
Quantitative variables also termed as numeric variables are not called so just because they are expressed in numbers but also because a quantitative variable is the one for which the resulting observations are numeric in nature and thus naturally, they possess ordering or ranking.
Quantitative variables are further classified as Discrete and Continuous Variables. Let us understand the difference between the two with suitable examples.
Variables such as number of employees in an organisation, number of defective items in a box of manufacturing unit are the classic examples of discrete variables. This is because the scores here will not be in decimals such as 4.65 or 7.23. They are going to be whole numbers or discrete while for data such as time taken to complete a specific task, waiting time for machinery or queue are continuous in nature. The waiting time could be 1.45 hours or the time taken to complete a task could be 4.6 minutes.
Do you still feel that you are not very sure of what is discrete and continuous in quantitative variables? Let us look at a few more examples
⦁ Discrete Variable
⦁ Number of deaths in Covid 19
⦁ Number of specific cars sold in a particular financial year
⦁ Number of road accidents in a specific time period
⦁ Number of new branches of a school opened in a period of five years
⦁ Continuous Variable
⦁ Height or weight of a body
⦁ Bank interest rates
⦁ Temperature of a place or person
⦁ Blood pressure
⦁ Time taken to complete a MCQ test
Always know that a continuous variable mostly is an outcome of measurement and can assume countless values in the specified range.
This flowchart will summarise for you the different types of qualitative and quantitative variables we have done till now:
Let us look at the next two important type of variables that we need to know the difference between for better understanding of the concept and the application of variables
Dependent and Independent Variable
A lot of research studies target to bring forth a causal relationship between an underlying phenomenon or problem. This is done to reveal as well as understand the relationship between two aspects, and how the two are related.
Let us look at a few statements to understand this better
⦁ High intake of sugar causes diabetes
⦁ Promotion of a product impacts its sales
⦁ Smoking aggravates the risk of lung cancer
⦁ Global warming causes rise in temperature
⦁ Yoga improves the health of those who practice
⦁ Nuclear families lead to more depressions amongst the family members
In all the above examples, we have both dependent as well as independent variable. Let us look at the first example, high intake of sugar causes diabetes. Here more consumption of sugar increases the chances of bring a diabetic. Being diabetic here is the dependent variable which is determined by the amount of sugar consumer by the participant so consumption of sugar is the independent variable. Similarly in all other examples, smoking, global warming, promotion are all independent variables which have some degree of impact on their dependent variables. In a general scenario, an independent variable is manipulated by the experimenter or researcher, and its effects on the dependent variable are measured.
Now let us understand, individually what is an independent variable and what is a dependent variable
⦁ Independent Variable
The variable that is used to describe or measure the factors which are assumed to either cause or influence is some way the outcome or the problem are called as independent variables. The researcher uses the independent variable to elaborate or explain the influence of the same on the dependent variable
Any amount of variability seen in the dependent variable seems to arise from the variability in the independent variable because of which an independent variable is many a times also called as the predictor variable, explanatory variable, or input variable in the statistical software.
⦁ Dependent Variable
The variable used to describe or measure the problem or outcome under study is called a dependent variable.
When there is a causal relationship between the independent and dependent variable the outcome or the effect is the dependent variable. So, like in the above example, high intake of sugar causes diabetes, diabetes here is the dependent variable. This variable is the variable that truly interests the researcher and he is wanting to explain what factors alter or impact it by adding one or more independent variables to the study. The dependent variable is also called by more than one name and the names are response variable, predicted variable, explained variable. In the statistical software like SPSS it is called as the label.
The below diagram will very simply explain you the fundamental behind the independent and dependent variable
⦁ Background Variable
In all the studies, the basic data or what we call as the demographic profile of the respondent is collected whether directly needed or not needed for the research. Information such as age, gender, educational qualification, income, socio economic strata, marital status, religion, place of birth etc may be taken from the respondents. All of these are referred to as background variables. Whatever information that the researcher intends to collect from the respondent from the above list or anything else will have some link with the independent variable and have some impact or influence on the problem. This is the reason they are called as background variables because they are present in the background. The researcher should try to involve only the necessary background variables in the study, else the study would get unnecessarily complicated without much constructive impact of the same.
⦁ Moderating Variable
In the hypotheses that are created to establish some kind of relationship between the independent and dependent variable, it is always assumed that the dependent variable is caused by the independent variable. In a simple relationship all the other variables are ignored and considered to be extraneous.
In a pragmatic and realistic scenario, no relationship is so straightforward and simple where the cause of the dependent variable is 100 per cent dependent on the independent variable and these simple one to one relationship needs to be revised to take into consideration the other variable that gives a better explanation to the relationship stated in the independent and dependent variable. This creates the need to incorporate another independent variable, which is in support to the primary independent variable. This another variable identified is supposed to be contributing significantly or have contingent effect on the simple and straightforward relationship between the independent and dependent variable. Such a variable is termed as a moderating variable. If this appears to complicated, let us look at an example:
“To study the relationship between the training of employees and their work productivity.” Here work productivity is the dependent variable and the training an independent variable. The type of training that the employee receives can have a significant impact on the outcome of work productivity and impact the relationship better so the “type of training received” will be the extraneous variable.
There are a few more kind of variables that can be further used in research, but as a fresh researcher if you have got a good conceptual clarity of the above eight variables, you are surely good to go!
You must be logged in to post a comment.