Step 2 in Research Process

transform your research idea into a

hypothesis
Definition of Hypothesis
• a hypothesis is a statement that describes or explains a
relationship between or among variables.
• A hypothesis is not a final answer but rather a proposal to be
tested and evaluated.
For example, a researcher might hypothesize that there is a
relationship between personality characteristics and cigarette
smoking.
Or another researcher might hypothesize that a dark and dreary
environment causes winter depression.
• Theoretical Fact/Statement: Visual imagery is related to human
memory.

• Research question: Is there a relationship between using visual

images and human memory?

• Hypothesis: The use of visual images is related to better memory

performance.
the results from an empirical research study will either support
the hypothesis or will refute the hypothesis.
Characteristics of a Good Hypothesis
• Logical
• Testable
• Refutable
• Positive
Logical
• A good hypothesis is usually founded in established theories or
developed from the results of previous research.

By knowing the basic facts, theories, predictions, and methods make up the
knowledge base for a specific topic area, you gain a clearer picture of exactly
which variables are being studied and exactly which relationships are likely to
exist.
Testable
• it must be possible to observe and measure all of the variables
involved.
• the hypothesis must involve real situations, real events, and real
individuals.
• You cannot test a hypothesis that refers to imaginary events or
hypothetical situations.
• For example, you could debate what might have happened if John
F. Kennedy had not been assassinated. This proposition does not
lead to a testable hypothesis. It cannot be observed and,
therefore, is inappropriate as scientific hypotheses.
Refutable
• It must be possible to obtain research results that are contrary to
the hypothesis. For example, if the hypothesis states that the
treatment will cause an increase in scores, it must be possible for
the data to show no increase.
• A refutable hypothesis, often called a falsifiable hypothesis, is a
critical component of the research process.
• A refutable hypothesis is one that can be demonstrated to be
false. That is, it is possible for the outcome to be different from the
prediction.
Positive
• it must make a positive statement about the existence of
something, usually the existence of a relationship, the existence
of a difference, or the existence of a treatment effect.
• Statistically, it is called null (no relationship/no difference/no
improvement) and alternative hypothesis (existence of
relationship, difference, improvement)
• Specifically, the basic nature of science is to assume that
something does not exist until there is enough evidence to
demonstrate that it actually does exist.
• Suppose, for example, that I would like to test the hypothesis that
there is a relationship between creativity and intelligence.
• In this case, begin with the assumption that a relationship does
not exist, and the goal for my research study is to gather enough
evidence (data) to provide a convincing demonstration that a
relationship does exist.
Step 3: Defining and Measuring
Variables
• researchers are interested in how variables are affected by
different conditions or how variables differ from one group of
individuals to another.
• For example, a clinician may be interested in how depression
scores change in response to therapy, or a teacher may want to
know how much difference there is in the reading scores for third-
grade children versus fourth-grade children.
• To evaluate differences or changes in variables, it is essential that
we are able to measure them.
• Two aspects of measurement are particularly important when
planning a research study or reading a research report:
Constructs and Operational Definitions
• Occasionally, a research study involves variables that are well
defined, easily observed, and easily measured.
• For example, a study of physical development might involve the
variables of height and weight.
• Both of these variables are tangible, concrete attributes that can
be observed and measured directly.
• On the other hand, some studies involve intangible, abstract
attributes such as motivation or self-esteem. Such variables are
not directly observable, and the process of measuring them is
more complicated.
Theories and Constructs
• In attempting to explain and predict behavior, scientists and
philosophers often develop theories that contain hypothetical
mechanisms and intangible elements.
• Although these mechanisms and elements cannot be seen and
are only assumed to exist, we accept them as real because they
seem to describe and explain behaviors that we see.
• For example, a bright child does poor work in school because she
has low “motivation.” A kindergarten teacher may hesitate to
criticize a lazy child because it may injure the student’s “self-
esteem.”
• But what is motivation, and how do we know that it is low?
• Do we read the child’s motivation meter?
• What about self-esteem? How do we recognize poor self- esteem
or healthy self-esteem when we cannot see it in the first place?
• Many research variables, particularly variables of interest to
behavioral scientists, are in fact hypothetical entities created from
theory and speculation. Such variables are called constructs, or
hypothetical constructs.
• Constructs are hypothetical attributes or mechanisms that help
explain and predict behavior in a theory.
 Rewards
Motivation Performance
Reinforcement
Mechanism of construct as defined by
theories in a specific context
Lack of
concentration

worry

Outcomes
exam anxiety nervousness
(behaviors)

External stimulus construct

predictors
Increased blood
pressure
Operational Definitions
• An operational definition is a procedure for indirectly measuring
and defining a variable that cannot be observed or measured
directly.
• An operational definition specifies a measurement procedure (a
set of operations) for measuring an external, observable behavior,
and uses the resulting measurements as a definition and a
measurement of the hypothetical construct.
• Hypothetical construct: Intelligence
• Operational definition: The score a person receives on the
Wechsler Intelligence Scale for Children (WISC) or any
standardized IQ test.
• Intelligence itself can't be observed directly, but test scores based
on tasks measuring memory, reasoning, and vocabulary serve as
indirect, observable indicators.
• Hypothetical construct: Aggression in children
• Operational definition: The number of times a child hits, kicks,
or shouts at peers during a 30-minute play session, observed
by a trained researcher.
• We cannot directly observe "aggression" as a psychological state,
but we define it through specific, countable behaviors.
• Hypothetical construct: Test anxiety
• Operational definition: The score on a self-report
questionnaire such as the Test Anxiety Inventory (TAI).
• Anxiety is internal and subjective, but we can measure it through
how individuals respond to validated survey items.
• Hypothetical construct: Happiness
• Operational definition: The average score on a 10-point Likert
scale survey asking participants to rate their current mood.
• Since happiness is a personal, internal experience, it’s
operationalized through self-reports.
Another example (operationalizing hunger)
• For example, the construct “hunger” can be operationally defined as
the number of hours of food deprivation.
• In a research study, for example, one group could be tested
immediately after eating a full meal,
• a second group could be tested 6 hours after eating,
• and a third group could be tested 12 hours after eating.
• In this study, we are comparing three different levels of hunger, which
are defined by the number of hours without food.
• Alternatively, we could measure hunger for a group of rats by recording
how much food each animal eats when given free access to a dish of
rat chow. The amount that each rat eats defines how hungry it is.
Limitations of Operational Definitions
• Not the same as the construct:
• Operational definitions only capture observable indicators of the
construct
• They do not fully encapsulate the construct's complexity.
• E.g., intelligence or anxiety is measured through behaviors or test
scores, not the actual internal experience.
• Omission of important components
• Operational definitions may leave out key aspects of a construct.
• Example: Defining depression solely by behavioral symptoms
(e.g., social withdrawal, insomnia) ignores emotional and
cognitive dimensions.
• Solution: Use multiple measures or procedures to capture the full scope
of the construct
• Inclusion of irrelevant components
• Operational definitions can include elements that are not part of the
construct.
• Example: Self-report measures of depression may be influenced by:

• Verbal abilities (understanding and expressing feelings).

• Willingness to disclose personal or sensitive information.

This can distort the measurement (e.g., a more expressive person may
appear more depressed than someone who is reserved or unable to
articulate their symptoms).
Using Operational Definitions for Hypothetical
Constructs
• Necessity of Operational Definitions:
• Required when variables are hypothetical constructs (e.g.,
intelligence, motivation).
• Essential to make abstract concepts measurable and observable.
• Creating vs. Adopting Definitions:
• You usually don’t need to create your own operational
definition.
• Best practice: Review previous research involving the same
construct to see how it has been defined and measured.
• Using Established Methods:
• Past research reports describe in detail how variables were
operationally defined
• Reading multiple sources helps identify standard or commonly
accepted measurement procedures.
• Advantages of Conventional Methods:
• Using established methods makes your results comparable with
existing findings.
• Promotes consistency and validity across studies.
Identifying Scales of Measurement and
Evaluating Reliability and Validity
• scales of measurement (nominal ordinal ratio interval)
• Reliability: The reliability of a measurement procedure is the
stability or consistency of the measurement. If the same
individuals are measured under the same conditions, a reliable
measurement procedure produces identical (or nearly identical)
measurements.
• Validity: The validity of a measurement procedure is the degree to
which the measurement process measures the variable that it
claims to measure
 Modalities of Measurement
Measure Definition Strengths Weaknesses

- Prone to distortion and bias

Participants describe or - Most direct access to
(e.g., social desirability)-
Self-Report rate their own feelings, internal states- Based on
Influenced by question
attitudes, or behaviors. individual self-awareness
phrasing and context

Biological responses - Expensive equipment

- Highly objective and
linked to the construct required- Can create
Physiological reliable- Not affected by
are recorded (e.g., heart unnatural settings- May lack
personal interpretation
rate). construct specificity

- Flexible and adaptable- - Behavior may be situational

Observable actions or
Can target actual behavior or temporary- Risk of
Behavioral performance are used to
or indicate underlying incomplete representation if
infer the construct.
construct only one behavior is measured
Step 4: Identify the Participants or
Subjects for the Study, Decide How
They Will be Selected, and Plan for
Their Ethical Treatment
Sampling Methods
Population and Sample
• A population is the entire set of individuals of interest to a
researcher. Although the entire population usually does
not participate in a research study, the results from the
study are generalized to the entire population.

• A sample is a set of individuals selected from a

population and usually is intended to represent the
population in a research study.
Populations and sample
Target Population
• A target population is the group defined by the researcher’s
specific interests.
• Individuals in a target population typically share one
characteristic.
• All children of divorced parents, all elementary school–aged
children, and all adolescents diagnosed with bulimia nervosa are
examples of target populations.
• Usually, target populations are not easily available. For example,
for a researcher interested in the treatment of bulimia nervosa in
adolescents, the target population would be all of the adolescents
in the world who are diagnosed with this disorder.
Accessible Population
• Clearly, the researcher would not have access to most of these
people to recruit as a sample of participants for the research
study.
• However, a researcher would have access to the many local
clinics and agencies that treat clients with eating disorders.
• These local clients (adolescents diagnosed with bulimia nervosa)
become the accessible population from which the sample is
selected. Most researchers select their samples from accessible
populations.
 The representativeness of a
sample refers to the extent to
which the characteristics of
Representative Samples the sample accurately reflect
the characteristics of the
population.

• How accurately we can generalize the results from a given sample

to the population depends on the representativeness of the
sample.
• Thus, one problem that every researcher faces is how to obtain
a sample that provides a reasonable representation of the
population.
• To generalize the results of a study to a population, the researcher
must select a representative sample.
• A representative sample is a sample with the same
characteristics as the population.
 Read about
Threat to Representativeness WEIRD
Western,
Educated,
A BIASED SAMPLE is a Industrialized,
SELECTION BIAS OR SAMPLING
Rich and
sample with different BIAS occurs when participants Democratic
characteristics from or subjects are selected in a
manner that increases the
those of the population.
probability of obtaining a
(outcome) biased sample. (cause)

if the population we are interested in is adults

the individuals in a sample are smarter (or older
and we recruit our sample from the students
or faster) than the individuals in the population
enrolled at a university, we are likely to obtain a
sample that is smarter, on average, than the
individuals in the entire population.
Surveying only urban residents to study national
opinions — rural populations are left out
Using an online survey to study health behaviors
excludes people without internet access
Sample Size (How many participants?)
• In research, we usually study a small group (sample) to
understand a larger group (population).
• The main goal is to have a sample that fairly represents the
population.
• A larger sample is usually more representative than a small one.
• But bigger isn't always better — beyond a certain point, increasing
size gives little extra benefit.
• For many studies, 25–30 participants per group is a practical and
commonly used target.
Practical & Ethical Considerations
• Sample size depends on study goals, resources, and context.
• multiple treatment groups; you need enough people in each
group to make valid comparisons
• Accuracy; You may need a larger total sample
• Ethical balance is important:
• Too few participants = weak or inconclusive results (wasted
effort).
• Too many = unnecessary use of people's time and effort.
Sampling Basics
• The process of selecting individuals for a study is called
sampling.
• sampling methods (also called sampling techniques or
sampling procedures)
Sampling Methods

Probability Non-Probability
Sampling Sampling
Probability Sampling
• In probability sampling, the entire population is known, each
individual in the population has a specifiable probability of
selection, and sampling occurs by a random process based on
the probabilities.
• For example, if there are 100 people in a group and everyone has
an equal chance of being picked, then each person has a 1 out of
100 (or 1/100) chance of being selected.
• Probability sampling has three important conditions:
The exact size of the population
Each individual in the population Selection must be a random
must be known and it must be
must have a specified probability process, which simply means
possible to list all of the
of selection. that every possible outcome is
individuals.
equally likely
Example of Probability Sampling
• A university wants to evaluate a new teaching method used in a
large introductory psychology course. There are 300 students
enrolled, and the university decides to randomly select 30
students to complete a detailed feedback form.
• Population Size Known (The list of all 300 enrolled students is
available from course records.)
• Specified Probability of Selection (Each student has a 1 in 300
chance of being selected for the survey)
• Unbiased and Random Selection
• The 30 students are selected using a random number generator.
Non-Probability Sampling
• In nonprobability sampling, the population is not completely
known, individual probabilities cannot be known, and the
sampling method is based on factors such as commonsense or
ease, with an effort to maintain representativeness and avoid bias
• the researcher does not know the population size and cannot
list the members of the population.
• the researcher does not use an unbiased method of selection and
has a greater risk of producing a biased sample than does
probability sampling
Example of Non-probability Sampling
• A researcher who wants to study the behavior of preschool
children may go to a local child-care center where a group of
preschool children is al ready assembled.
• Because the researcher is selecting from a restricted group,
rather than the entire population of preschool children, this
sample has an in creased chance of being biased.
• For example, if the child-care center includes only white,
middle-class children, then the sample definitely does not
represent the target population of preschool children..
Probability
Sampling
Techniques
 Probability
Sampling

Proportionate
Simple Random Systematic Stratified Random
Stratified Random Cluster Sampling
Sampling Sampling Sampling
Sampling

Sampling with Sampling without

replacement replacement
Simple Random Sampling
• The basic requirement for random sampling is that each individual in
the population has an equal chance of being selected. (Equality
means that no individual is more likely to be chosen than another.)
Every individual in the population has the same probability of being
selected.
• A second requirement that is sometimes added is that each selection
is independent of the others (Independence means that the choice of
one individual does not influence or bias the probability of choosing
another individual)

• Equality makes the sample fair. Independence makes the sample

unbiased and valid.
The process of simple random sampling
consists of the following
Step 1: Clearly define the population from which you want to select
a sample.
Step 2: List all the members of the population.
Step 3: Use a random process to select individuals from the list.
For example: A researcher has a population of 100 third-grade children
from a local school district, from which a sample of 25 children is to be
selected. Each child’s name is put on a list, and each child is
assigned a number from 1 to 100. Then the numbers 1 to 100 are
written on separate pieces of paper and shuffled. Finally, the
researcher picks 25 slips of paper and the numbers on the paper
determine the 25 participants.
Random Process
• researchers typically use some random process such as a coin toss or
picking numbers from a hat to guide the selection.
• But what if, in picking the numbers from a hat, the size of the papers is
different or the slips of paper are not shuffled adequately?
• The researcher could select individuals with larger slips of paper or
individuals at the end of the list whose slips of paper are at the top of
the pile.
• A more unbiased random process involves as signing each individual a
number and then using the random number table for selection of
participants.
• Or use softwares/websites for random sampling
https://www.randomizer.org/#randomize
Is this an example of simple random sampling
• a researcher who is interested in a population
defined as all the adults who live in a particular city.
To obtain a sample, the researcher opens a city
phone book at random, plunks down a fin ger on
someone’s name, and selects that person to be in
the sample. The researcher then turns to the next
page and plunks a finger on the next name to be
included. This process of turning pages and picking
names continues until the complete sample is
obtained.
NO,
• requirement of equality is violated; not everyone in the
population has an equal chance of being selected.
• Some people in the population have no chance of being
selected because their names are not in the phone book (for
example, people who have unlisted phone numbers, phone
numbers under other people’s names, or only use cell phones).
• the names are not selected independently. Because the
researcher picks only one name from each page, all the other
names on that page are excluded from the sample.
• Thus, selecting one name produces a bias (zero probability)
against all the other names on the same page.
The two principal methods of random
sampling are:
• Sampling with replacement:
• an individual selected for the sample be recorded as a sample
member and then returned to the population (replaced) before the
next selection is made.
• This procedure ensures that the probability of selection remains
constant throughout a series of selections.
• For example, if we select from a population of 100 individuals, the
probability of selecting any particular individual is 1⁄100.
• To keep this same probability (1⁄100) for the second selection, it is
necessary to return the first individual to the pool before the next
is selected.
• Because the probabilities stay constant, this technique ensures that
the selections are independent.
• Sampling without replacement:
• As the term indicates, this method removes each selected
individual from the population before the next selection is made.
• Although the probability of being selected changes with each
selection, this method guarantees that no individual appears
more than once in a single sample.
• Because the probabilities change with each selection, this
technique does not produce independent selections; the
probability that you will be selected increases each time another
person is selected and removed from the population.
Systematic Sampling
• Systematic sampling begins by listing all the individuals in the
population, then randomly picking a starting point on the list.
• The sample is then obtained by moving down the list, selecting
every nth name. The size of n is calculated by dividing the
population size by the desired sample size.
 Example of Systematic Sampling
• For example, suppose a researcher has a population of 100 third-
grade students and would like to select a sample of 25 children. Each
child’s name is put on a list and assigned a number from 1 to 100.
• Then, the researcher uses a random process such as a table of
random numbers to select the first participant, for example,
participant number 11.
• With a population of 100 children and a desired sample size of 25, the
size of n in this example is 100/25 = 4.
• Therefore, every fourth individual after participant 11 (15, 19, 23, and
so on) is selected.
• Note that systematic sampling is identical to simple random sampling (i.e., follow the three steps)
for selection of the first participant; however, after the first individual is selected, the researcher
does not continue to use a random process to select the remaining individuals for the sample.
• This technique is less random than simple random sampling
because the principle of independence is violated.
• Specifically, if we select participant number 11, we are biased
against choosing participants number 12, 13, and 14, and we are
biased in favor of choosing participant number 15.
• However, as a probability sampling method, this method ensures
a high degree of representativeness.
Another example
Suppose a researcher has a population of 60 employees working
in a company and wants to select a sample of 12 employees for
a satisfaction survey. Each employee is listed and given a
number from 1 to 60.
The researcher uses a random method — such as a random
number generator — to select the first person, say employee
number 5.
Next, the researcher calculates the sampling interval:
Interval=60/12=5
So, starting with employee #5, the researcher selects every 5th
person on the list:
• 5 (random start), 10th, 15th, 20th, 25th……… and so on, until 12
employees are selected.
Non-
Probability
Sampling
Techniques