Understanding Different Types of Variables

Good day everyone. For this particular lecture, we will be discussing about the different types of variables. But first, let's analyze this situation here. Say for example, a teacher wants to identify the factors that influence the low academic performance of students. What are some possible factors? It may be that the student was not able to understand the instruction. Or, instead of studying, the student simply slept. Or, perhaps the student ran out of time. and was in a hurry to finish the test or even during the review the student was not able to focus. All these factors, being confused, sleeping instead of reviewing, running out of time, and being out of focus can be considered as variables that contribute to our study. Now, at this point, let us talk about the definition of a variable. A variable is an entity that can take on different values. It is an aspect of a theory that can vary or change as part of the interaction within the variable. the theory, or anything that can change or affect the results of a particular study. Take note that anything that can vary can be considered a variable. These are needed to understand differences in a particular study. research study. Again, a variable may take different forms. It can be age, gender, IQ level, the lifestyle of an individual, temperature, or medical treatment used. Remember that anything can be a variable as long as it is something that a researcher is interested in. Now at this point, let's talk about the different classifications of variables. Variables may be classified as numeric, categorical, experimental, or non-experimental. The classifications would determine the roles of variables in a particular study. Now let's talk about the numeric variable classification. The numeric classification of variables are variables with values that describe a measurable numerical quantity. Pretty much it answers the questions how many or how much, meaning to say that numeric variables are considered quantitative data. Numeric variables are further divided into two types which are continuous or interval variables and discrete variables. Continuous or interval variables assume any value between a certain set of real numbers depending on the scale used, while discrete variables can only assume any whole value within the limits of the given variables. Now, some of the examples of the continuous or interval variables can be time. If you're going to observe, in time we do not only look at the hours, We also recognize the existence of minutes and seconds. Age could also be an example because in between the age of 10 and 11, we recognize that there are people who are 10 and a half and even 10 and 3 quarters. Weight is also an example because we do not only focus on whole numbers for the weight, we also have grams and milligrams in between. And finally, Another example of a continuous variable could be the height. When we recognize or when we indicate the height of a person, we do not only look at the feet. We also consider the centimeters and inches. Take note that continuous or interval variables in the simplest description recognize the value between whole numbers. Now, let's proceed with the discussion of discrete variables. Discrete variables, unlike the continuous or interval variables that recognize the existence of values in between whole numbers, only focus on the whole numbers itself. Some examples would be class attendance, number of establishments in an area, and number of children in the family. Again, note that discrete variables are whole numbers because remember in class attendance we do not have half a student as well as in the number of the children in the family. We don't have two and a half children in the family. It always recognizes that values are that of a whole number. The next variable classification is the categorical variable. Categorical variables are variables with values that describe a quality or characteristic of a data unit. Pretty much it answers the questions what type or which category, hence we have the term categorical. Now, unlike the numeric variables, categorical variables are qualitative in nature and are further divided into four types which are ordinal variables, nominal variables, dichotomous variables, and polychotomous variables. Let's first talk about the ordinal variables. Ordinal variables can take a value which can be logically ordered or ranked. Some examples would be clothing size, academic ranking, levels of satisfaction, and salary scale. Take note of the operative terms which are values that can be logically ordered and ranked. Some of these examples would explain that A person who is size XS or extra small is ranked differently than that of someone who is a smaller size. Take note that it gradually gets bigger in terms of the ranking. Similarly, in terms of academic ranking, a person who ranks first is different than someone who ranks second and someone who ranks third. In terms of levels of satisfaction, Of course, a person who is very satisfied has a different level compared to someone who is simply satisfied or someone who is actually very dissatisfied. In the simplest terms, ordinal variables serve the purpose of classification and ranking. Now, let's proceed to nominal variables. Nominal variables, unlike ordinal variables wherein the values can be arranged logically in terms of ranking, have values which cannot be organized in a logical sequence. Some examples would be the learning styles, the language spoken, blood type, and plate numbers. Now, you might be thinking, plate numbers have numbers in them. Aren't they supposed to be numeric variable or ordinal variables? Well, the answer is no. Because plate numbers serve the purpose of nominal variables which is for the purpose of identification. Remember that plate numbers are unique in order to identify the vehicle that it is assigned to. Similar to your blood type, blood type A is different from blood type B. However, having blood type A doesn't mean you're greater than persons who have blood type B. Or having a blood type AB doesn't mean you're the greatest among all these blood types. In terms of learning styles, being a visual learner doesn't mean you're greater than someone who is musical or auditory learner. It simply is for the purpose of identifying which particular learning purpose or learning style would serve you best. In terms of the language spoken, learning or speaking one particular language doesn't mean you're greater than all the others. It simply is for the purpose of identifying in which country you came from, whether from your Japan, from China, from Korea, or from Thailand. However, it doesn't mean that if you speak Thai, it doesn't mean that you're greater than those who speak Korean or even the others. Again, it's merely for the purpose of identification. Before we proceed, let's sum up the differences and similarities between ordinal variables and nominal variables. Ordinal variables and nominal variables are both categorical. However, ordinal variables can be organized or ranked while nominal variables would be for classification and identification purposes only. Let's now proceed with the other categorical variable classifications which are dichotomous variables, and polychotomous variables. Dichotomous variables are variables that represent only two categories. Example would be a yes or no choice, true or false, or even gender in terms of biological gender. Whereas polychotomous variables are variables that have many possible categories. Example would be performance level and educational attainment. Take note of the operative terms between the two. Dichotomous variables would only have two categories, while polychotomous variables would have many possible categories. Now let's talk about another variable classification, which is experimental variable. The experimental variable are variables that determine causal relationships. It is subdivided into independent variables. Dependent variables, control variables, moderating variables, and extraneous variables. Now let's talk about independent variables and dependent variables. Independent variables are presumed to cause changes in another variable. These are usually manipulated in an experiment, hence independent variables are also called as the causal variable. While dependent variables are variables that change because of another variable. These are usually affected by the manipulation of the independent variable and Dependent variables are the variables that are monitored in an experiment. Hence, we call dependent variables as the effect variable. Let's take for example this particular study on the effect of studying in the academic performance of students. So we have the two variables which are studying and academic performance. From this particular situation, we could determine that studying is the independent variable and academic performance is the dependent variable because studying greatly affects academic performance. In another example, we have the effect of diet and exercise on the physical fitness of individuals. Similarly, we have two variables which are diet and exercise and physical fitness. From this particular situation, we could determine that diet and exercise is the dependent variable while physical fitness is the dependent variable because diet and exercise affects the physical fitness of individuals. At this point, we now focus on control variables and moderator variables. Control variables are variables that are held constant. These help to identify the possible differences in the outcomes as a result of controlling certain variables. While moderator variables are variables that delineates how a relationship of interest changes under different conditions or circumstances. Moderator variables may be quantitative or qualitative in nature. Let's look at this example on the study regarding the effect of playing music on the academic performance of students. We have our students here. Playing music and academic performance. From this particular situation, we are able to identify that playing music is our independent variable as it might influence the academic performance of our students. A possible moderator variable would be the genre of music that is played. Remember that a moderator variable introduces change in the results if done in a different situation or condition. As such, we try to identify which particular genre of music, whether classical music or rock music, would be effective in terms of improving the academic rate of the students. Now, a possible control variable would be the class duration, which is 60 minutes per class. Regardless whether you're a class exposed to classical music or the class exposed to rock music, both groups will have the same duration of class in order to determine the possible effects of music exposure to the students. And lastly, we have extraneous variables. Extraneous variables are variables that are already existing during the conduct of an experiment. These variables could influence the results of the study as such, as much as possible must be controlled because they can offer an alternative result. Take note that these are variables which are already existing or extra variables that are already existing, hence we have the term extraneous variables. Let's go back to our example earlier on the study regarding the effect of playing music on the academic performance of students. We have Playing music as our independent variable and academic performance as our dependent variable. A possible extraneous variable that might influence or change the result would be noise. Another would be ventilation and lighting. Noise, of course, would cause a distraction to the students, hence they would not be able to focus properly even if they are exposed to classical music or rock music. Whereas, ventilation and lighting might result to a change in the atmosphere which would result to the students feeling uncomfortable in terms of studying in that particular area, regardless whether they're exposed to classical music or rock music. In both situations, noise and ventilation and lighting are considered extraneous variables because if they are not controlled, they might offer a different result. that is not expected in the study itself. And the last variable classification would be the non-experimental variables. Non-experimental variables are variables which cannot be manipulated by the researcher, hence it is for non-experimental studies. Non-experimental variables are further classified into predictor variables, which are variables that can change or affect other variables in a non-experimental study, and criterion variables, which are variables that are influenced by the predictor variable in a non-experimental study. Let's consider these examples here on the influence of management styles on employee satisfaction. Our predictor variable would be the management styles because it affects the criterion variable which is the employee satisfaction. In another example, we have the conduct of guidance counseling programs and degree of absenteeism and dropout rate among grade 8 students. Our predictor variable would be the conduct of guidance counseling programs as it might influence or affect our criterion variable which is the degree of absenteeism and dropout rate. As we end our discussion, let's focus on this particular reflection. Recognizing variables and knowing their classification and roles would help researchers have a more detailed idea regarding how the variables in their study interact and affect each other. This contributes to a more meaningful discussion regarding the possible outcomes of a study as reflected in their identified variables.

What are some possible factors? It may be that the student was not able to understand the instruction. Or, instead of studying, the student simply slept. Or, perhaps the student ran out of time. and was in a hurry to finish the test or even during the review the student was not able to focus.

All these factors, being confused, sleeping instead of reviewing, running out of time, and being out of focus can be considered as variables that contribute to our study. Now, at this point, let us talk about the definition of a variable. A variable is an entity that can take on different values. It is an aspect of a theory that can vary or change as part of the interaction within the variable.

the theory, or anything that can change or affect the results of a particular study. Take note that anything that can vary can be considered a variable. These are needed to understand differences in a particular study. research study. Again, a variable may take different forms.

It can be age, gender, IQ level, the lifestyle of an individual, temperature, or medical treatment used. Remember that anything can be a variable as long as it is something that a researcher is interested in. Now at this point, let's talk about the different classifications of variables.

Variables may be classified as numeric, categorical, experimental, or non-experimental. The classifications would determine the roles of variables in a particular study. Now let's talk about the numeric variable classification. The numeric classification of variables are variables with values that describe a measurable numerical quantity. Pretty much it answers the questions how many or how much, meaning to say that numeric variables are considered quantitative data.

Numeric variables are further divided into two types which are continuous or interval variables and discrete variables. Continuous or interval variables assume any value between a certain set of real numbers depending on the scale used, while discrete variables can only assume any whole value within the limits of the given variables. Now, some of the examples of the continuous or interval variables can be time.

If you're going to observe, in time we do not only look at the hours, We also recognize the existence of minutes and seconds. Age could also be an example because in between the age of 10 and 11, we recognize that there are people who are 10 and a half and even 10 and 3 quarters. Weight is also an example because we do not only focus on whole numbers for the weight, we also have grams and milligrams in between.

And finally, Another example of a continuous variable could be the height. When we recognize or when we indicate the height of a person, we do not only look at the feet. We also consider the centimeters and inches. Take note that continuous or interval variables in the simplest description recognize the value between whole numbers. Now, let's proceed with the discussion of discrete variables.

Discrete variables, unlike the continuous or interval variables that recognize the existence of values in between whole numbers, only focus on the whole numbers itself. Some examples would be class attendance, number of establishments in an area, and number of children in the family. Again, note that discrete variables are whole numbers because remember in class attendance we do not have half a student as well as in the number of the children in the family. We don't have two and a half children in the family.

It always recognizes that values are that of a whole number. The next variable classification is the categorical variable. Categorical variables are variables with values that describe a quality or characteristic of a data unit.

Pretty much it answers the questions what type or which category, hence we have the term categorical. Now, unlike the numeric variables, categorical variables are qualitative in nature and are further divided into four types which are ordinal variables, nominal variables, dichotomous variables, and polychotomous variables. Let's first talk about the ordinal variables.

Ordinal variables can take a value which can be logically ordered or ranked. Some examples would be clothing size, academic ranking, levels of satisfaction, and salary scale. Take note of the operative terms which are values that can be logically ordered and ranked.

Some of these examples would explain that A person who is size XS or extra small is ranked differently than that of someone who is a smaller size. Take note that it gradually gets bigger in terms of the ranking. Similarly, in terms of academic ranking, a person who ranks first is different than someone who ranks second and someone who ranks third.

In terms of levels of satisfaction, Of course, a person who is very satisfied has a different level compared to someone who is simply satisfied or someone who is actually very dissatisfied. In the simplest terms, ordinal variables serve the purpose of classification and ranking. Now, let's proceed to nominal variables.

Nominal variables, unlike ordinal variables wherein the values can be arranged logically in terms of ranking, have values which cannot be organized in a logical sequence. Some examples would be the learning styles, the language spoken, blood type, and plate numbers. Now, you might be thinking, plate numbers have numbers in them. Aren't they supposed to be numeric variable or ordinal variables?

Well, the answer is no. Because plate numbers serve the purpose of nominal variables which is for the purpose of identification. Remember that plate numbers are unique in order to identify the vehicle that it is assigned to.

Similar to your blood type, blood type A is different from blood type B. However, having blood type A doesn't mean you're greater than persons who have blood type B. Or having a blood type AB doesn't mean you're the greatest among all these blood types.

In terms of learning styles, being a visual learner doesn't mean you're greater than someone who is musical or auditory learner. It simply is for the purpose of identifying which particular learning purpose or learning style would serve you best. In terms of the language spoken, learning or speaking one particular language doesn't mean you're greater than all the others.

It simply is for the purpose of identifying in which country you came from, whether from your Japan, from China, from Korea, or from Thailand. However, it doesn't mean that if you speak Thai, it doesn't mean that you're greater than those who speak Korean or even the others. Again, it's merely for the purpose of identification. Before we proceed, let's sum up the differences and similarities between ordinal variables and nominal variables. Ordinal variables and nominal variables are both categorical.

However, ordinal variables can be organized or ranked while nominal variables would be for classification and identification purposes only. Let's now proceed with the other categorical variable classifications which are dichotomous variables, and polychotomous variables. Dichotomous variables are variables that represent only two categories. Example would be a yes or no choice, true or false, or even gender in terms of biological gender. Whereas polychotomous variables are variables that have many possible categories.

Example would be performance level and educational attainment. Take note of the operative terms between the two. Dichotomous variables would only have two categories, while polychotomous variables would have many possible categories.

Now let's talk about another variable classification, which is experimental variable. The experimental variable are variables that determine causal relationships. It is subdivided into independent variables.

Dependent variables, control variables, moderating variables, and extraneous variables. Now let's talk about independent variables and dependent variables. Independent variables are presumed to cause changes in another variable.

These are usually manipulated in an experiment, hence independent variables are also called as the causal variable. While dependent variables are variables that change because of another variable. These are usually affected by the manipulation of the independent variable and Dependent variables are the variables that are monitored in an experiment. Hence, we call dependent variables as the effect variable.

Let's take for example this particular study on the effect of studying in the academic performance of students. So we have the two variables which are studying and academic performance. From this particular situation, we could determine that studying is the independent variable and academic performance is the dependent variable because studying greatly affects academic performance.

In another example, we have the effect of diet and exercise on the physical fitness of individuals. Similarly, we have two variables which are diet and exercise and physical fitness. From this particular situation, we could determine that diet and exercise is the dependent variable while physical fitness is the dependent variable because diet and exercise affects the physical fitness of individuals. At this point, we now focus on control variables and moderator variables. Control variables are variables that are held constant.

These help to identify the possible differences in the outcomes as a result of controlling certain variables. While moderator variables are variables that delineates how a relationship of interest changes under different conditions or circumstances. Moderator variables may be quantitative or qualitative in nature. Let's look at this example on the study regarding the effect of playing music on the academic performance of students.

We have our students here. Playing music and academic performance. From this particular situation, we are able to identify that playing music is our independent variable as it might influence the academic performance of our students.

A possible moderator variable would be the genre of music that is played. Remember that a moderator variable introduces change in the results if done in a different situation or condition. As such, we try to identify which particular genre of music, whether classical music or rock music, would be effective in terms of improving the academic rate of the students. Now, a possible control variable would be the class duration, which is 60 minutes per class. Regardless whether you're a class exposed to classical music or the class exposed to rock music, both groups will have the same duration of class in order to determine the possible effects of music exposure to the students.

And lastly, we have extraneous variables. Extraneous variables are variables that are already existing during the conduct of an experiment. These variables could influence the results of the study as such, as much as possible must be controlled because they can offer an alternative result.

Take note that these are variables which are already existing or extra variables that are already existing, hence we have the term extraneous variables. Let's go back to our example earlier on the study regarding the effect of playing music on the academic performance of students. We have Playing music as our independent variable and academic performance as our dependent variable.

A possible extraneous variable that might influence or change the result would be noise. Another would be ventilation and lighting. Noise, of course, would cause a distraction to the students, hence they would not be able to focus properly even if they are exposed to classical music or rock music. Whereas, ventilation and lighting might result to a change in the atmosphere which would result to the students feeling uncomfortable in terms of studying in that particular area, regardless whether they're exposed to classical music or rock music. In both situations, noise and ventilation and lighting are considered extraneous variables because if they are not controlled, they might offer a different result.

that is not expected in the study itself. And the last variable classification would be the non-experimental variables. Non-experimental variables are variables which cannot be manipulated by the researcher, hence it is for non-experimental studies.

Non-experimental variables are further classified into predictor variables, which are variables that can change or affect other variables in a non-experimental study, and criterion variables, which are variables that are influenced by the predictor variable in a non-experimental study. Let's consider these examples here on the influence of management styles on employee satisfaction. Our predictor variable would be the management styles because it affects the criterion variable which is the employee satisfaction.

In another example, we have the conduct of guidance counseling programs and degree of absenteeism and dropout rate among grade 8 students. Our predictor variable would be the conduct of guidance counseling programs as it might influence or affect our criterion variable which is the degree of absenteeism and dropout rate. As we end our discussion, let's focus on this particular reflection.

Recognizing variables and knowing their classification and roles would help researchers have a more detailed idea regarding how the variables in their study interact and affect each other. This contributes to a more meaningful discussion regarding the possible outcomes of a study as reflected in their identified variables.

Transcript for:Understanding Different Types of Variables

Transcript for:
Understanding Different Types of Variables