The Variables, Hypothesis and

Assumptions
Learning Objectives:
At the end of the topic the students should be able to:
• Discuss the independent variable;
• Discuss the dependent variable;
• Discuss the intervening variable;
• Discuss the moderate variable;
• Discuss the control variable;
• Discuss the manipulate variable;
• Discuss the null hypothesis and the steps on how
to write a hypothesis; and
• Discuss the importance of assumptions.
• You won't be able to do very much in research unless you know how to
talk about variables. A variable is any entity that can take on different
values. OK, so what does that mean? Anything that can vary can be
considered a variable. For instance, age can be considered a variable
because age can take different values for different people or for the
same person at different times. Similarly, country can be considered a
variable because a person's country can be assigned a value.
(https://www.socialresearchmethods.net/kb/variable.php)
• Every true experimental design must have this statement at the core of
its structure, as the ultimate aim of any experiment.
• The hypothesis is generated via a number of means, but is usually the
result of a process of inductive reasoning where observations lead to the
formation of a theory. Scientists then use a large battery of deductive
methods to arrive at a hypothesis that is testable, falsifiable and realistic.
• During the process of writing your thesis or dissertation, you might
suddenly realize that your research has inherent flaws. Don’t worry!
Virtually all projects contain restrictions to your research. However, being
able to recognize and accurately describe these problems is the difference
between a true researcher and a grade-school kid with a science-fair
project. Concerns with truthful responding, access to participants, and
survey instruments are just a few of examples of restrictions on your
research. In the following sections, the differences among delimitations,
limitations, and assumptions of a dissertation will be clarified.
(https://www.phdstudent.com/Choosing-a-Research-Design/stating-the-
obvious-writing-assumptions-limitations-and-delimitations)
 The Independent and Dependent Variable
General Guidelines in Writing the Variables, Their Definitions and
Importance to the Study
• Theories, concepts and ideas that will explain the meaning
of every variable are included.
• The section provides for the related literature and studies for
each of the variables included in the research.
• Related studies for each variable are also presented
without discussion on its parallelism to the present study.
• The discussion also included how the variables were used in
the present research to explain its importance.
• The variables are arranged based on its presentation in the model.
• A minimum of two related literature and two related studies
are required for each variable.
• Another important distinction having to do with the term 'variable' is the
distinction between an independent and dependent variable. This
distinction is particularly relevant when you are investigating cause-effect
relationships. It took me the longest time to learn this distinction. (Of
course, I'm someone who gets confused about the signs for 'arrivals' and
'departures' at airports -- do I go to arrivals because I'm arriving at the
airport or does the person I'm picking up go to arrivals because they're
arriving on the plane!). I originally thought that an independent variable
was one that would be free to vary or respond to some program or
treatment, and that a dependent variable must be one that depends on my
efforts (that is, it's the treatment). But this is entirely backwards! In fact the
independent variable is what you (or nature) manipulates -- a treatment or
program or cause. The dependent variable is what is affected by the
independent variable -- your effects or outcomes. For example, if you are
studying the effects of a new educational program on student
achievement, the program is the independent variable and your measures
of achievement are the dependent ones.
• The dependent variable is the variable a researcher is interested in. The changes
to the dependent variable are what the researcher is trying to measure with all
their fancy techniques. In our example, your dependent variable is the person's
ability to throw a ball. We're trying to measure the change in ball throwing as
influenced by hunger.
• An independent variable is a variable believed to affect the dependent variable.
This is the variable that you, the researcher, will manipulate to see if it makes the
dependent variable change. In our example of hungry people throwing a ball, our
independent variable is how long it's been since they've eaten.
• To reiterate, the independent variable is the thing over which the researcher has
control and is manipulating. In this experiment, the researcher is controlling the
food intake of the participant. The dependent variable is believed to be
dependent on the independent variable.
• Your experiment's dependent variable is the ball throwing, which will hopefully
change due to the independent variable. So now, our scientific sentence is, 'You
are going to manipulate an independent variable to see what happens to the
dependent variable.' (http://study.com/academy/lesson/research-variables-
dependent-independent-control-extraneous-moderator.html)
 The Intervening Variables
• Intervening variables are hypothetical internal states
that are used to explain relationships between
observed variables, such independent and dependent
variables.
• Intervening variables are not real things. They are
interpretations of observed facts, not facts
themselves. But they create the illusion of being
facts.
Examples:
• learning, memory, motivation, attitude, personality,
traits, knowledge, understanding, thinking,
expectation, intelligence, intention.
 The Moderate Variable
• A mediator variable is the variable that causes mediation in the dependent and the
independent variables. In other words, it explains the relationship between the dependent
variable and the independent variable. The process of complete mediation is defined as
the complete intervention caused by the mediator variable. This results in the initial
variable no longer affecting the outcome variable. The process of partial mediation is
defined as the partial intervention.
• The mediation caused by the mediator variable is developed as a mediation model. This
model that develops due to the mediation is a causal model. In other words, this means that
the mediator variable has been assumed to cause the affect in the outcome variable and
not vice versa. In the field of psychology, the mediator variable explains how the external
physical events affect the internal psychological significance.
• The mediation caused by the variable cannot be defined statistically. On the
contrary, statistics can be utilized to assess an assumed meditational model
developed by the mediator variable.
Baron and Kenny have given steps for conducting meditational hypotheses.
A variable plays a role on the mediator variable under some specific
conditions. The conditions of being the mediator variable are as follows:
• If the change in the level of the independent variable significantly accounts
for variation in the other variable, then the variable is considered a
mediator variable.
• If the change in the other variable significantly accounts for the variation
in the dependent variable, then the other variable is considered a
mediator variable.
• If the other variable strongly dominates the significant relationship
between the dependent and the independent variable, then the other
variable is termed as a mediator variable. In other words, if the relationship
between the dependent and the independent variable no longer exists and
their variations are controlled by some other variable, then that variable is
termed as the mediator variable.
• In general, the mediation model examines the relationship between the
dependent variable and the independent variable, the relationship between
the independent variable and the mediator variable and the relationship
between the dependent variable and the mediator variable.
• If the mediator variable is measured with less than perfect consistency,
then the effects caused are likely to be biased. In other words, the effect
of the mediator variable is likely to be underestimated and the effect of the
independent variable and the independent variable is likely to be
overestimated. This bias in the variation of the variable is generally due to
measurement error. An Instrumental variable is then used to solve this
problem of bias in the variability of the mediator variable. If this approach
does not work, then the researcher working on the mediator variable is
required to explain that since the reliability of the mediator variable is very
high, the bias caused is fairly minimal.
• If the mediation caused by the mediator variable is perfect in nature, then
the independent variable and the mediator variable are correlated to each
other. This correlation between the mediator variable and the independent
variable is termed as collinearity. If the independent variable explains all
the variation caused by the mediator variable, there will not be any unique
variation that would explain the dependent variable, and this will thus
result in multicollinearity.
• Multicollinearity is generally expected in the mediational analysis of the
mediator variable and the dependent and the independent variable,
and therefore it cannot be avoided by the researcher.
(http://www.statisticssolutions.com/mediator-variable/)
 The Control Variable
• The control variable (or scientific constant) in scientific experimentation is the
experimental element which is constant and unchanged throughout the course of
the investigation. The control variable strongly influences experimental results,
and it is held constant during the experiment in order to test the relative
relationship of the dependent and independent variables. The control variable
itself is not of primary interest to the experimenter.
• A variable in an experiment which is held constant in order to assess the
relationship between two other variables, is the control variable. A control
variable is the one element that is not changed throughout an experiment,
because its unchanging state allows the relationship between the other variables
being tested to be better understood.
• Essentially, a control variable is what is kept the same throughout the experiment,
and it is not of primary concern in the experimental outcome. Any change in a
control variable in an experiment would invalidate the correlation of dependent
variables (DV) to the independent variable (IV), thus skewing the results.
(https://en.wikipedia.org/wiki/Control_variable)
 The Manipulative Variable
• It is easy to see how cause and effect work in the world around
us. You've probably noticed that if you knock a glass of water over,
the water spills all over the surrounding area. If you've forgotten to
apply sunscreen and then spent the day in the sun, you know how
miserable you will feel later that night! Scientists are always
looking for new ideas to test and new ways to explain phenomena
they observe in the world around us. Often, it's easy to see how
changing something on purpose can cause an effect. For
example, you can place your fingers on your wrist to measure
your heart rate and observe that it increases as you go from
relaxing to exercising.
• Scientists make changes in experiments to see if those changes
will cause an effect in something they observe. The thing that is
changed on purpose is called the manipulated variable.
Sometimes it is also called the independent variable.
• In an experiment, there are many variables for a scientist to keep track of.
A variable is anything that can change in an experiment. Some examples
of variables include the heart rate of a runner, how many bees visit a
flower in a day, the temperature of water in a fish tank, and how much
yeast is added to bread dough. The experimenter starts with a question
to answer, such as 'Which kind of exercise is most effective at increasing
heart rate?' After doing some research, they make a prediction, called
the hypothesis. In this case, they might predict, 'If a person does jumping
jacks, then their heart rate will increase more than walking, jogging, or
playing catch.' In this example the manipulated variable is the type of
exercise: jumping jacks, walking, jogging, and playing catch.
• Designing the manipulated variable is a critical part of the experiment. Research
is done in advance so that the scientist knows which values of the manipulated
variable to select and how much to change each one in the experiment. It would
not have made sense to use an activity such as fishing or knitting in this case,
because the participant would be seated and not moving around. In other
experiments, such as changing the concentration of oxygen in a room where
athletes are performing, research is critical because oxygen is necessary for
survival! The scientist would need to know what is a safe range for oxygen to be
for humans and then all values for the experiment would need to be within that
range.
• Many times it makes sense to include a control. A control is something used as
a basis for comparison. In the exercise example, a control would be a person
just standing. The heart rate would be measured just to see if perhaps other
factors, such as extreme heat or cold, caused a heart rate change in anyone in
the area. In some experiments, the control is referred to as a control group, such
as an area in a garden where fertilizer was not applied. This control group can
be used to compare the results of changing the manipulated variable.
 The Null Hypothesis and the Steps How to Write a Hypothesis

General Guidelines in Writing the Hypothesis

• The section should have an
introductory statement
• It should enlist the hypotheses in the research.
Hypotheses are stated in the null hypothesis.
There are five steps in hypothesis testing:
• Making assumptions
• Stating the research and null hypotheses and selecting (setting) alpha
• Selecting the sampling distribution and specifying the test statistic
• Computing the test statistic
• Making a decision and interpreting the results
If you learn these five basic steps, it will help you greatly in hypothesis
testing. It gives you a procedure to follow, regardless of the particular
problem you are working with. (https://learn.bu.edu/bbcswebdav/pid-
826908-dt-content-rid-
2073693_1/courses/13sprgmetcj702_ol/week04/metcj702_W04S01T05_five
steps.html)
Tips for Writing Hypotheses
• When you state your hypotheses, be sure that the content of the
hypothesis matches the experimental procedure. What you write should
be the best estimation of the outcome of the lab procedure. Along with the
hypothesis, you should write several sentences which explain the scientific
reasoning that led you to that hypothesis.
(https://www.bcps.org/offices/lis/researchcourse/develop_write_introductio
n_hypothesis.html)
 The Importance of Assumptions
• Assumptions are things that are accepted as true, or at least plausible, by
researchers and peers who will read your dissertation or thesis. In other
words, any scholar reading your paper will assume that certain aspects of
your study is true given your population, statistical test, research design, or
other delimitations. For example, if you tell your friend that your favorite
restaurant is an Italian place, your friend will assume that you don’t go
there for the sushi. It’s assumed that you go there to eat Italian food.
Because most assumptions are not discussed in-text, assumptions that
are discussed in-text are discussed in the context of the limitations of your
study, which is typically in the discussion section. This is important,
because both assumptions and limitations affect the inferences you can
draw from your study. One of the more common assumptions made in
survey research is the assumption of honesty and truthful responses.
• However, for certain sensitive questions this assumption may be more
difficult to accept, in which case it would be described as a limitation of the
study. For example, asking people to report their criminal behavior in a
survey may not be as reliable as asking people to report their eating
habits. It is important to remember that your limitations and assumptions
should not contradict one another. For instance, if you state that
generalizability is a limitation of your study given that your sample was
limited to one city in the United States, then you should not claim
generalizability to the United States population as an assumption of your
study. Statistical models in quantitative research designs are accompanied
with assumptions as well, some more strict than others. These
assumptions generally refer to the characteristics of the data, such as
distributions, correlational trends, and variable type, just to name a few.
Violating these assumptions can lead to drastically invalid results, though
this often depends on sample size and other considerations.