2. Introduction to the Scientific Method
Use conclusions to develop a new hypothesis
3. Variables
• Variables are the building blocks of
hypotheses that are held together by the
“glue” of the relationship we are studying
4. Variables and Variable Values
Variables Variable Values
• Types of Beer • Sam Adams, Bud, Corona
• Hair Color • Blonde, Black, Brown, Red
• A-E
• Grades • 85, 101, 124, 199 (Dr.
• IQ (As measured by the Dodge’s)
Weschler) • 0-252
• Attitudes towards People
with Disabilities (As
measured by the Modified
Issues in Disability Scale)
5. Understanding variables in light of
their research use.
• There are three characteristics of variables
that are necessary considerations in most
research; they are:
– A. definition,
– B. function, and
– C. type of measurement (i.e., measurement scale)
6. Variables: Definitions
• An operational definition “assigns meaning to a construct
or a variable by specifying the activities or “operations”
necessary to measure it...It is a specification of the
activities of the researcher in measuring the variable or
manipulating it.
• Types of operational definitions are:
– (a) measured, “which describes how a variable will be
measured” and includes the source of the data (e.g., a
specific standardized instrument or author developed
questionnaire)
– (b) experimental, which “spells out the details of the
investigator's manipulation of the variable” (e.g., the
specific details and procedures of the intervention or
treatment).
7. Variables: Definitions Cont.
• Hypothesis: Rewards increase punctuality.
• The variables are rewards and punctuality.
• A definition of rewards might be: Giving out candy
and soda during the first five minutes of class.
Depending on the design, this might be an
experimental definition.
• A definition of punctuality could be the number of
minutes after 2:00 that the person arrived as
recorded by the class timekeeper.
8. Variables: Functions
• Variables have different functions. These functions are
most frequently related to
– (a) presumed causality and to
– (b) the purposes of the inquiry.
9. Presumed Causality
• A. Variable functions related to presumed causality
include independent and dependent.
– Independent variable: “…is the factor that is manipulated
or controlled by the researcher”
– A variable that is “independent of the outcome being
measured. More specifically…[it is] what causes or
influences the outcome”.
• Note that classification variables can also be independent
variables.
• Also referred to as Explanatory Variables
10. Variables: Function Cont.
– Dependent variable: “is a measure of the effect (if any) of the
independent variable
• The term dependent implies “it is influenced by the independent
variable.
• Response variable or output. The factor that is observed or
measured to determine the effect of the independent variable.
• Dependent Variables are also referred to as Outcome Variables
11. Variables: Function Cont.
• B. Variable functions related to the purposes
of inquiry.
– We introduce control variables to remove their influence
from the relationship of the other variables,
12. Variables: Measurement Scales
• There are two different scales for
measurement of variables.
1. Variables can be: continuous or categorical
AND
2. Variables can be nominal, ordinal, interval,
or ratio
13. Variables: Measurement Scales Cont.
1. Continuous or Categorical
– Continuous variables have an ordered set of values
within a certain range. Values between two points
(e.g., 4 and 5) on the range actually mean
something. In other words, if a person scored 4.5,
they scored more than someone who scored 4 and
less than someone who scored 5.
– Categorical variables (i.e., discrete variables) are
measured in categories. An observation is either in a
category or it isn't. There is no meaningful “in
between” option. For example, cars might be
categorized as domestic or imported. Categories
must be mutually exclusive and exhaustive.
14. Variables: Measurement Scales Cont.
1. Nominal, Ordinal, Interval, or Ratio
– Nominal: Names, classes, or symbols designating
unique characteristics - simple classification, no
order.
– Ordinal: Assignment of numbers of symbols
indicates order of relationship. Order only is
indicated; there is no indication of amount. For
example if an ordinal scale used the numbers from 1
to 6, one could say that 6 was greater that 3, but one
could not say that it was twice the value of 3. Further
the value of 4.5 would have no meaning in such a
scale. Rank order data is an example of ordinal data.
15. Variables: Measurement Scales Cont.
– Interval: This type of data has the same
ordering properties as ordinal data and it also
has equal, meaningful intervals and an
arbitrary zero point. Therefore in an interval
scale, 4.5 would be meaningful.
– Ratio: This type of data has the same
properties as interval data and also has an
absolute zero point. In a ratio scale, 6 would be
twice as much as 3.
16. Variables: Measurement Scales Cont.
• Relating the Two Scales
• Categorical: Nominal (Ordinal?)
• Continuous: (Ordinal?) Interval and Ratio
• When planning data collection, ALWAYS TRY TO COLLECT DATA IN
CONTINUOUS FORM (unless it really confounds your collection
strategy). CONTINUOUS DATA CAN ALWAYS BE CATEGORIZED
LATER IF DESIRED FOR ANALYSIS, BUT CATEGORICAL DATA CANNOT
BE READILY TRANSFORMED INTO CONTINUOUS.
• For example, instead of asking people to mark one of six age
categories, one could simply ask their date of birth. So, why do we
care about scales? Among other reasons, scales determine the type
of statistics that can be used. Parametric statistics are only
appropriate with interval or ratio data. Nonparametric statistics
must be used with nominal and ordinal data.
17. Levels of Variables
Two Group Comparisons
Treatment Group Control Group
(Exercise) (No Exercise)
18. Levels and Factors
• The most basic experimental design has two variables
– Independent Variable
– Dependent Variable
• The independent variable has two Levels
– Experimental Group (Usually receives treatment)
– Control Group (Usually does not receive treatment)
– A study can also have two different amounts of an independent
variable
• Example: A Randomized and Controlled study looking at the effects of
exercise (Independent) on body fat (Dependent)
– Group 1 exercises 3 times a week for 6 weeks
– Group 2 does not exercise at all for three weeks
Researchers will compare the body fat of those who exercise to those
who do not.
19. Levels and Factors Cont.
• A grouping variable is called a “Factor”
• The number of groups are called “Levels”
• A 2 level variable design can be expanded to
include as many levels as needed!
20. Levels and Factors Cont.
(4 Level Factor)
Treatment 1 Treatment 2
Treatment 3 Control
24. Experimental hypothesis
• Predicts differences in the measure of the dependent
variable between the various conditions of the
independent variable
• 2-tailed hypothesis: Only predict a difference
• 1-tailed hypothesis: Predict a particular direction in
the difference (i.e. One group/condition will have a
higher or lower score)
25. Two tailed hypothesis
• (Two tailed) There will be a difference in [the
D.V.] between [condition A of the I.V.] and
[condition B of the I.V.]
• (Two-tailed) There will be a difference in I.Q.
Scores between male subjects and female
subjects
26. One-tailed hypothesis
• (One-tailed) There will be a decrease/increase
in [the DV] in [condition A of the IV]
compared to [condition B of the IV]
• (One-tailed) There will be an increase in I.Q.
Scores in female subjects than in male
subjects.
27. Null hypothesis
• To be scientific every experimental hypothesis
must be capable of being proven to be wrong.
For this reason a null hypothesis is always
proposed along with the experimental
hypothesis
• The null hypothesis states that there will be
no significant difference between
conditions/groups
28. Example, null hypotheses
(Two tailed) There will be no difference in I.Q.
scores between male subjects and female
subjects.
(One tailed) There will be no increase/decrease
in I.Q. scores between male subjects and
female subjects.
29. Accepting/rejecting null and
experimental hypothesis
• If there is a significant difference between the
conditions/groups, the experimental
hypothesis is accepted and the null hypothesis
is rejected
• If there is no significant difference between
conditions/groups, the experimental
hypothesis is rejected and the null hypothesis
is accepted
30. Questions, one-tailed, two-tailed
and null hypotheses
1. Based on the result of the Bandura study, do you
think we should reject or accept our experimental
hypothesis?
2. Some studies have failed to find an effect of
antidepressants on mood compared to placebo
groups. For these studies, should the null
hypothesis be rejected or accepted?
31. Your Tasks
• Define your variables and measurement scales
• Construct hypothesis and null hypothesis
33. Parts of the Statement
• Independent Variable:
The condition be studied. It is controlled by the
experimenter.
ex. Water
• Dependent Variable:
The condition affected by the ind. variable. It can’t be
controlled by the experimenter.
ex. Plant Growth
• Control:
The condition that is represented in a normal situation.
34. Steps to Writing the “If” section of your
Hypothesis
1. Start your sentence with the word “If”
2. Write down one of the variables
3. Connect statement with one of the following:
is related to
is affected by
causes
7. Write down the other variable
35. Writing the “Then” section of your
Hypothesis
• Write the word then (following the “if”
section)
• Make a comment on the relationship between
those two variables.
Ex. If section:
If water is related to plant growth,
Ex. Then section:
then the more you water plants, the bigger
they will grow.
36. Final “If / Then” Statement
If water is related to plant growth, then
the more you water plants, the bigger
they will grow.
37. What Makes a Good Hypothesis?
• Based on information contained in the
Background Research Paper
• Include the independent and dependent
variables
• Can be tested in an experiment
• For programming and engineering projects:
– Establish design criteria