Course: “Research Methods in Education” (8604)

Semester: Spring, 2021

Q. 1 What are the sources of knowledge? Define scientific method and describe its different steps.

Sociologists make use of tried and true methods of research, such as experiments, surveys, and field research.

But humans and their social interactions are so diverse that these interactions can seem impossible to chart or

explain. It might seem that science is about discoveries and chemical reactions or about proving ideas right or

wrong rather than about exploring the nuances of human behavior.

However, this is exactly why scientific models work for studying human behavior. A scientific process of

research establishes parameters that help make sure results are objective and accurate. Scientific methods

provide limitations and boundaries that focus a study and organize its results.

The scientific method involves developing and testing theories about the world based on empirical evidence. It

is defined by its commitment to systematic observation of the empirical world and strives to be objective,

critical, skeptical, and logical. It involves a series of prescribed steps that have been established over centuries

of scholarship.

The scientific method is an essential tool in research.

But just because sociological studies use scientific methods does not make the results less human. Sociological

topics are not reduced to right or wrong facts. In this field, results of studies tend to provide people with access

1
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
to knowledge they did not have before—knowledge of other cultures, knowledge of rituals and beliefs, or

knowledge of trends and attitudes. No matter what research approach they use, researchers want to maximize

the study’s reliability, which refers to how likely research results are to be replicated if the study is reproduced.

Reliability increases the likelihood that what happens to one person will happen to all people in a group.

Researchers also strive for validity, which refers to how well the study measures what it was designed to

measure. Returning to the crime rate during a full moon topic, reliability of a study would reflect how well the

resulting experience represents the average adult crime rate during a full moon. Validity would ensure that the

study’s design accurately examined what it was designed to study, so an exploration of adult criminal behaviors

during a full moon should address that issue and not veer into other age groups’ crimes, for example.

In general, sociologists tackle questions about the role of social characteristics in outcomes. For example, how

do different communities fare in terms of psychological well-being, community cohesiveness, range of

vocation, wealth, crime rates, and so on? Are communities functioning smoothly? Sociologists look between the

cracks to discover obstacles to meeting basic human needs. They might study environmental influences and

patterns of behavior that lead to crime, substance abuse, divorce, poverty, unplanned pregnancies, or illness.

And, because sociological studies are not all focused on negative behaviors or challenging situations,

researchers might study vacation trends, healthy eating habits, neighborhood organizations, higher education

patterns, games, parks, and exercise habits.

Sociologists can use the scientific method not only to collect but also to interpret and analyze the data. They

deliberately apply scientific logic and objectivity. They are interested in—but not attached to—the results. They

work outside of their own political or social agendas. This doesn’t mean researchers do not have their own

personalities, complete with preferences and opinions. But sociologists deliberately use the scientific method to

maintain as much objectivity, focus, and consistency as possible in a particular study.

With its systematic approach, the scientific method has proven useful in shaping sociological studies. The

scientific method provides a systematic, organized series of steps that help ensure objectivity and consistency in

exploring a social problem. They provide the means for accuracy, reliability, and validity. In the end, the

scientific method provides a shared basis for discussion and analysis (Merton 1963).

2
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Typically, the scientific method starts with these steps—1) ask a question, 2) research existing sources, and 3)

formulate a hypothesis.

The first step of the scientific method is to ask a question, describe a problem, and identify the specific area of

interest. The topic should be narrow enough to study within a geography and time frame. “Are societies capable

of sustained happiness?” would be too vague. The question should also be broad enough to have universal

merit. “What do personal hygiene habits reveal about the values of students at XYZ High School?” would be

too narrow. That said, happiness and hygiene are worthy topics to study. Sociologists do not rule out any topic,

but would strive to frame these questions in better research terms.

That is why sociologists are careful to define their terms. In a hygiene study, for instance, hygiene could be

defined as “personal habits to maintain physical appearance (as opposed to health),” and a researcher might ask,

“How do differing personal hygiene habits reflect the cultural value placed on appearance?” When forming

these basic research questions, sociologists develop an operational definition, that is, they define the concept

in terms of the physical or concrete steps it takes to objectively measure it. The operational definition identifies

an observable condition of the concept. By operationalizing a variable of the concept, all researchers can collect

data in a systematic or replicable manner.

The operational definition must be valid, appropriate, and meaningful. And it must be reliable, meaning that

results will be close to uniform when tested on more than one person. For example, “good drivers” might be

defined in many ways: those who use their turn signals, those who don’t speed, or those who courteously allow

others to merge. But these driving behaviors could be interpreted differently by different researchers and could

be difficult to measure. Alternatively, “a driver who has never received a traffic violation” is a specific

description that will lead researchers to obtain the same information, so it is an effective operational definition.

Research Existing Sources

The next step researchers undertake is to conduct background research through a literature review, which is a

review of any existing similar or related studies. A visit to the library and a thorough online search will uncover

existing research about the topic of study. This step helps researchers gain a broad understanding of work

previously conducted on the topic at hand and enables them to position their own research to build on prior

3
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
knowledge. Researchers—including student researchers—are responsible for correctly citing existing sources

they use in a study or that inform their work. While it is fine to borrow previously published material (as long as

it enhances a unique viewpoint), it must be referenced properly and never plagiarized.

To study hygiene and its value in a particular society, a researcher might sort through existing research and

unearth studies about child-rearing, vanity, obsessive-compulsive behaviors, and cultural attitudes toward

beauty. It’s important to sift through this information and determine what is relevant. Using existing sources

educates researchers and helps refine and improve studies’ designs.

Formulate a Hypothesis

A hypothesis is an assumption about how two or more variables are related; it makes a conjectural statement

about the relationship between those variables. In sociology, the hypothesis will often predict how one form of

human behavior influences another. In research, independent variables are the cause of the change.

The dependent variable is the effect, or thing that is changed.

Q. 2 Describe different types of research categorized on the basis of methods used and the purpose of

research.

Research is a logical and systematic search for new and useful information on a particular topic. Research is

important both in scientific and nonscientific fields. In our life new problems, events, phenomena and processes

occur every day. Practically, implementable solutions and suggestions are required for tackling new problems

that arise. Scientists have to undertake research on them and find their causes, solutions, explanations and

applications.

The research is broadly classified into two main classes: 1. Fundamental or basic research and 2. Applied

research. Basic and applied researches are generally of two kinds: normal research and revolutionary research.

In any particular field, normal research is performed in accordance with a set of rules, concepts and procedures

called a paradigm, which is well accepted by the scientists working in that field. In addition, the basic and

applied researches can be quantitative or qualitative or even both (mixed research).

1. Fundamental or basic research:

Basic research is an investigation on basic principles and reasons for occurrence of a particular event or process

4
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
or phenomenon. It is also called theoretical research. Study or investigation of some natural phenomenon or

relating to pure science are termed as basic research. Basic researches sometimes may not lead to immediate use

or application. It is not concerned with solving any practical problems of immediate interest. But it is original or

basic in character. It provides a systematic and deep insight into a problem and facilitates extraction of scientific

and logical explanation and conclusion on it. It helps build new frontiers of knowledge. The outcomes of basic

research form the basis for many applied research.

Basic research

• Seeks generalization

• Aims at basic processes

• Attempts to explain why things happen

• Tries to get all the facts

• Reports in technical language of the topic

2. Applied research:

In an applied research one solves certain problems employing well known and accepted theories and principles.

Most of the experimental research, case studies and inter-disciplinary research are essentially applied research.

Applied research is helpful for basic research. A research, the outcome of which has immediate application is

also termed as applied research. Such a research is of practical use to current activity.

Applied research

• Studies individual or specific cases without the objective to generalize

• Aims at any variable which makes the desired difference

• Tries to say how things can be changed

• Tries to correct the facts which are problematic

• Reports in common language

Basic and applied research, further divided into three types of research bearing some characteristics feature as

follows:

Quantitative research

5
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
• It is numerical, non-descriptive, applies statistics or mathematics and uses numbers.

• It is an iterative process whereby evidence is evaluated.

• The results are often presented in tables and graphs.

• It is conclusive.

• It investigates the what, where and when of decision making.

Qualitative research

• It is non-numerical, descriptive, applies reasoning and uses words.

• Its aim is to get the meaning, feeling and describe the situation.

• Qualitative data cannot be graphed.

• It is exploratory.

• It investigates the why and how of decision making.

Mixed research

Mixed research- research that involves the mixing of quantitative and qualitative methods or paradigm

characteristics. Nature of data is mixture of variables, words and images.

Other types of research

Exploratory Research

Exploratory research might involve a literature search or conducting focus group interviews. The exploration of

new phenomena in this way may help the researcher’s need for better understanding, may test the feasibility of

a more extensive study, or determine the best methods to be used in a subsequent study. For these reasons,

exploratory research is broad in focus and rarely provides definite answers to specific research issues.

The objective of exploratory research is to identify key issues and key variables.

Descriptive research

The descriptive research is directed toward studying “what” and how many off this “what”. Thus, it is directed

toward answering questions such as, “What is this?”.

Explanatory research

• Its primary goal is to understand or to explain relationships.

6
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
• It uses correlations to study relationships between dimensions or characteristics off individuals, groups,

situations, or events.

• Explanatory research explains (How the parts of a phenomenon are related to each other).

• Explanatory research asks the “Why” question.

Longitudinal Research

Research carried out longitudinally involves data collection at multiple points in time. Longitudinal studies may

take the form of:

• Trend study- looks at population characteristics over time, e.g. organizational absenteeism rates during

the course of a year

• Cohort study- traces a sub-population over time, e.g. absenteeism rates for the sales department;

• Panel study- traces the same sample over time, e.g. graduate career tracks over the period 1990 – 2000

for the same starting cohort.

While longitudinal studies will often be more time consuming and expensive than cross-sectional studies, they

are more likely to identify causal relationships between variables.

Cross-sectional Research

One-shot or cross-sectional studies are those in which data is gathered once, during a period of days, weeks or

months. Many cross-sectional studies are exploratory or descriptive in purpose. They are designed to look at

how things are now, without any sense of whether there is a history or trend at work.

Action research

• Fact findings to improve the quality of action in the social world

Policy-Oriented Research

• Reports employing this type of research focus on the question ‘How can problem ‘X’ be solved or

prevented ?’

Classification research

• It aims at categorization of units in to groups

• To demonstrate differences

7
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
• To explain relationships

Comparative research

• To identify similarities and differences between units at all levels

Causal research

• It aims at establishing cause and effect relationship among variable

Theory-testing research

• It aims at testing validity of a unit

Theory-building research

• To establish and formulate the theory

Last of all, it is needless to say that scientific research helps us in many ways:

• A research problem refers to a difficulty which a researcher or a scientific community or an industry or a

government organization or a society experiences. It may be a theoretical or a practical situation. It calls

for a thorough understanding and possible solution.

• Research provides basis for many government policies. For example, research on the needs and desires

of the people and on the availability of revenues to meet the needs helps a government to prepare a

budget.

• It is the fountain of knowledge and provide guidelines for solving problems.

• Only through research inventions can be made; for example, new and novel phenomena and processes

such as superconductivity and cloning have been discovered only through research.

• It is important in industry and business for higher gain and productivity and to improve the quality of

products.

• Research leads to a new style of life and makes it delightful and glorious.

• It leads to the identification and characterization of new materials, new living things, new stars, etc.

• Mathematical and logical research on business and industry optimizes the problems in them.

• Social research helps find answers to social problems. They explain social phenomena and seek solution

to social problems.

8
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Q. 3 Define casual comparative (Ex-Post Factor) research and discuss it in detail with example.

Causal-comparative research is an attempt to identify a causative relationship between an independent variable

and a dependent variable.The relationship between the independent variable and dependent variable is usually a

suggested relationship (not proven) because you (the researcher) do not have complete control over the

independent variable.

The Causal Comparative method seeks to establish causal relationships between events and circumstances. In

other words, it finds out the causes of certain occurrences or non-occurrenceces. This is achieved by comparing

the circumstances associated with observed effects and by noting the factors present in the instances where a

given effect occurs and where it does not occur. This method is based on Miill’s canon of agreement and

disaggrement which states that caoses of given observed effect may be ascertained by noting elements which

are invariably present when the result is present and which are invariably absent when the result is absent.

Causal-comparative research scrutinizes the relationship among variables in studies in which the independent

variable has already occurred, thus making the study descriptive rather than experimental in nature. Because the

independent variable (the variable for which the researcher wants to suggest causation) has already been

completed (e.g., two reading methods used by a school ), the researcher has no control over it. That is, the

researcher cannot assign subjects or teachers or determine the means of implementation or even verify proper

implementation.

Sometimes the variable either cannot be manipulated (e.g., gender) or should not be manipulated (e.g., who

smokes cigarettes or how many they smoke). Still, the relationship of the independent variable on one or more

dependent variables is measured and implications of possible causation are used to draw conclusions about the

results.

Also known as “ex post facto” research. (Latin for “after the fact”) since both the effect and the alleged cause

have already occurred and must be studied in retrospect .In this type of research investigators attempt to

determine the cause or consequences of differences that already exist between or among groups of individuals.

Used, particularly in the behavioral sciences. In education, because it is impossible, impracticable, or

unthinkable to manipulate such variables as aptitude, intelligence, personality traits, cultural deprivation,

9
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
teacher competence, and some variables that might present an unacceptable threat to human beings, this method

will continue to be used.

Causal-Comparative Research Facts

▪ Causal-Comparative Research is not manipulated by the researcher.

▪ -Does not establish cause-effect relationships.

▪ -Generally includes more than two groups and at least one dependent variable.

▪ -Independent variable is causal-comparative studies is often referred to as the grouping variable.

▪ -The independent variable has occurred or is already formed.

The Nature of Causal-Comparative Research

A common design in educational research studies, Causal-comparative research, seeks to identify associations

among variables. Relationships can be identified in causal-comparative study, but causation cannot be fully

established.

Attempts to determine cause and effect. It is not as powerful as experimental designs Causal-comparative

research attempts to determine the cause or consequences of differences that already exist between or among

groups of individuals.

Alleged cause and effect have already occurred and are being examined after the fact. The basic causal-

comparative approach is to begin with a noted difference between two groups and then to look for possible

causes for, or consequences of, this difference.

Used when independent variables cannot or should not be examined using controlled experiments. When an

experiment would take a considerable length of time and be quite costly to conduct, a causal-comparative study

is sometimes used as an alternative.

Main purpose of causal-comparative research:

▪ Exploration of Effects

▪ Exploration of Causes

▪ Exploration of Consequences

Basic Characteristics of Causal-comparative research

10
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
In short it the basic Characteristics of Causal-comparative research can be concluded:

▪ -Causal comparative research attempts to determine reasons, or causes, for the existing condition

▪ Causal comparative studies are also called ex post facto because the investigator has no control over the

exogenous variable. Whatever happened occurred before the researcher arrived.

▪ -Causal-comparative research is sometimes treated as a type of descriptive research since it describes

conditions that already exist.

▪ -Causal-comparative studies attempt to identify cause-effect relationships; correlational studies do not

▪ -Causal-comparative studies involve comparison, correlational studies involve relationship.

▪ -Causal-comparative studies typically involve two (or more) groups and one independent variable, whereas

correlational studies typically involve two or more variables and one group

▪ -Causal-comparative studies typically involve two (or more) groups and one independent variable, whereas

correlational studies typically involve two or more variables and one group

▪ -In causal-comparative the researcher attempts to determine the cause, or reason, for preexisting differences

in groups of individual.

▪ Involves comparison of two or more groups on a single endogenous variables.

▪ -Retrospective causal-comparative studies are far more common in educational research

▪ -The basic approach is sometimes referred to as retrospective causal-comparative research (since it starts

with effects and investigates causes)

▪ -The basic approach is sometimes referred to as retrospective causal-comparative research (since it starts

with effects and investigates causes)

▪ -The basic causal-comparative approach involves starting with an effect and seeking possible causes.

▪ The characteristic that differentiates these groups is the exogenous variable.

▪ -The variation as prospective causal-comparative research (since it starts with causes and investigates

effects)

▪ We can never know with certainty that the two groups were exactly equal before the difference occurred.

Three important aspects of Causal Comparative method are:

11
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
1- Gathering of data on factors invariably present in cases where the given result occurs and discarding of

those elements which are not universally present

2- 2-Gathering the data on factors invariably present in cases where the given effect does not occur

3- 3 Comparing the two sets of data, or in effect, substracting one from the other to get at the causes responsible

for the occurance or otherwise of the effect.

Examples of variables investigated in Causal-Comparative Research

▪ -Ability variables (achievement)

▪ -Family-related variables (SES)

▪ -Organismic variables (age, ethnicity, sex)

▪ -Personality variables (self-concept)

▪ -School related variables (type of school, size of school)

Causal Comparative Research Procedure

Experimental, quasi-experimental, and causal-comparative research methods are frequently studied together

because they all try to show cause and effect relationships among two or more variables. To conduct cause and

effect research, one variable(s) is considered the causal or independent variable and

Causal comparative research attempts to attribute a change in the effect variable(s) when the causal variable(s)

cannot be manipulated.

For example: if you wanted to study the effect of socioeconomic variables such as sex, race, ethnicity, or

income on academic achievement, you might identify two existing groups of students: one group – high

achievers; second group – low achievers. You then would study the differences of the two groups as related to

socioeconomic variables that already occurred or exist as the reason for the difference in the achievement

between the two groups. To establish a cause effect relationship in this type of research you have to build a

strongly persuasive logical argument. Because it deals with variables that have already occurred or exist, causal-

comparative research is also referred to as ex post facto research.

12
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
The most common statistical techniques used in causal comparative research are analysis of variance and t-tests

wherein significant differences in the means of some measure (i.e. achievement) are compared between or

among two or more groups.

Data Sources

▪ Raw scores such as test scores

▪ Measures such as grade point averages

▪ Judgements, and other assessments made of the subjects involved

Research Tools

▪ Standardized tests

▪ Surveys

▪ Structured interviews

Procedural Considerations

▪ The most important procedural consideration in doing causal comparative research is to identify two or

more groups which are demonstrably different in an educationally important way such as high academic

achievement versus low academic achievement. An attempt is then made to identify the cause which

resulted in the differences in the effect (i.e. academic achievement). The cause (i.e. race, sex, income, etc.)

has already had its effect and cannot be manipulated, changed or altered. In selecting subjects for causal-

comparative research, it is most important that they be identical as possible except for the difference (i.e.

independent variable – race, sex, income) which may have caused the demonstrated effect (i.e. dependent

variable – academic achievement)

▪ Hypotheses are generally used

▪ Statistics are extensively used in experimental research and include measures of spread or dispersion such

as:

▪ t-tests;

▪ Chi-Square;

▪ analysis of variance as well as measures of relationship such as

13
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
▪ : Pearson Product-Moment Coefficient;

▪ Spearman Rank Order Coefficient; Phi Correlation Coefficient; regression

Q. 4 What is an experiment and how you will conduct and experimental research? What will be the

threats to internal and external validity and how you will minimize these threats?

The design of research is fraught with complicated and crucial decisions. Researchers must decide which

research questions to address, which theoretical perspective will guide the research, how to measure key

constructs reliably and accurately, who or what to sample and observe, how many people/places/things need to

be sampled in order to achieve adequate statistical power, and which data analytic techniques will be employed.

These issues are germane to research of all types (exploratory, explanatory, descriptive, evaluation research).

However, the term “research design” typically does not refer to the issues discussed above.

The term “experimental research design” is centrally concerned with constructing research that is high in causal

(or internal) validity. Causal validity concerns the accuracy of statements regarding cause and effect

relationships. For example, does variable 1 cause variation in variable 2? Or does variable 2 cause variation in

variable 1? Or does variable 3 cause variation in both variables 1 and 2? And what is the magnitude of the

causal relationships among the variables? Thus, research design as used herein is a concern of explanatory and

evaluation research but generally does not apply to exploratory or descriptive research.

The importance of making causal inferences in criminology is hard to overstate. A central issue in many

criminological debates concerns whether correlates of offending are causally related to offending. The

correlates of offending are well known: bad parenting, deviant friends, prior delinquency behavior, youthful age

(i.e., adolescents and young adults), being male, deviant attitudes, personality traits such as impulsivity and

psychopathy, and so forth. Criminologists largely agree on these correlates of offending. Yet, “correlation does

not imply causation.” The field of criminology is filled with debates about which of these relationships are

causal in nature. Perhaps the best known of these debates focuses on association between deviant peers on

offending. Social learning theorists assert that having numerous, close relationships with those involved in

deviance causes one's own level of deviance to increase. On the other hand, social control theorists argue that

this relationship is noncausal; instead, the positive relationship between having deviant peers is the result of

14
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
“homophily” (the tendency of individuals to associate with similar others) – “birds of a feather flock together.”

Likewise, there is disagreement over whether the relationship between prior offending and future offending is

causal. Theorists such as Gottfredson and Hirschi (1990) argue that this relationship is spurious, as both prior

and future offending are caused by low self‐control. Other theories, such as Sampson and Laub's (1993)

age‐graded theory of informal social control, assert that involvement in crime and contact with the criminal

justice system increase the likelihood of future offending because these experiences diminish bonding to

important sources of informal social control (e.g., marriage, employment).

Debates concerning causal inference are not confined to theory. The effectiveness, or causal effect, of many

criminal justice – based interventions on measures of offending are hotly debated. Evaluations of criminal

justice interventions (e.g., reentry programs, drug court, and domestic violence programs) often find that

program participants have less recidivism than nonparticipants. Yet, most evaluations have difficulty proving

that the observed differences were actually caused by program participation.

Simply put, research design is a central concern in criminology because carefully designed research that is

implemented with high fidelity can establish causal validity/causal inferences.

Criteria for Establishing Causal Inferences

The three classic criteria necessary to support a causal inference, according to the philosopher John Stuart Mill,

are: (1) association (correlation), (2) temporal order, and (3) nonspuriousness. The criterion of association

requires that there is a systematic relationship between the cause and effect variables. This criterion is by far the

easiest to determine. The second criterion of temporal order is a bit more complicated. The temporal order

criterion requires that the cause, or more precisely variation in the cause variable, must occur before the

observed variation in the effect variable. The third criterion of nonspuriousness is by far the most difficult to

achieve. This criterion requires that the observed relationship between the cause and the effect variables must

not be due to other omitted or unmeasured third variables. Using the relationship between delinquent peers and

offending as an example, this criterion requires that this relationship cannot be due to homophily or any other

potential explanation. Because there are usually many, many potentially relevant third variables and many of

these third variables are unobserved, the criterion of nonspuriousness can be quite difficult to achieve.

15
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Types of Experiments

Shadish, Cook, and Campbell (2002) define an experiment as “a study in which an intervention is deliberately

introduced to observe its effects” (p. 12). Shadish and colleagues distinguish two broad types of

experiments: randomized experiments and quasi experiments. The central difference between these two types of

techniques is the use of random assignment to the levels of the hypothesized cause variable.

The hallmark of all randomized experiments is the use of random assignment to experimental conditions. In

randomized experiments, research subjects are randomly assigned to different levels of the hypothesized cause

variable (i.e., experimental conditions) by the researchers. Random assignment can be achieved in many

different ways, such as by flipping a coin, using a table of random numbers, or using numbers randomly

generated by a computer. The method of randomization is largely arbitrary, but the use of some form of

randomization is the crucial element of a randomized experiment.

Randomized experiments come in many forms or designs. The most common form of a randomized experiment

involves randomly assigning research subjects, all of whom have been screened for eligibility, to either the

treatment group that receives the experimental intervention of interest or the control group that does not; the

control group, instead, typically receives no treatment, standard care, or a placebo. Randomized experiments

involving the use of a no‐treatment control group are often referred to as “randomized controlled trials.”

Randomized controlled trials are considered by many to be the gold standard of evaluation research for their

high causal validity. There are many variations on this basic design. One common variation involves multiple

treatment groups that receive varying doses of the experimental intervention. Another common variation

involves “blinding” – procedures designed to prevent research subjects, treatment providers, and/or researchers

from knowing which experimental condition a research subject was assigned. Double‐blind randomized control

trials typically attempt to prevent research subjects and researchers from learning which research subjects were

assigned to the control group, until after all data have been collected. Blinding is intended to prevent various

kinds of bias from contaminating the research results. Randomized experiments are increasingly common in

criminology (see, e.g., Farrington & Welsh, 2005), but double‐blind randomized experiments are extremely

rare.

16
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Quasi experiments do not use randomization to assign research subjects to experimental conditions; instead,

some other method of assignment is utilized. Often research subjects voluntarily choose to participate or not to

participate in the treatment of interest. Thus, the actions and wishes of the research subjects typically affect

assignment.

Quasi experiments utilize a wide variety of designs. The two most common involve one‐group and two‐group

designs. The simplest and least rigorous quasi‐experimental research design involves one group of research

subjects who participated in some treatment of interest. These research subjects are observed before and after

the administration of treatment of interest. And the observed changes in the outcome of interest are causally

attributed to participation in the treatment. Another widely used quasi‐experimental design involves the use of

two groups. Typically, two‐group quasi experiments involve a comparison group that does not receive the

treatment of interest and a treatment group that does receive the treatment. These groups are compared, often

while controlling for any observed differences, and the remaining differences are causally attributed to the

treatment.

Randomized experiments and quasi experiments are capable of clearly establishing the first two criteria for

causal inferences (association and temporal order); yet, they differ sharply in their ability to establish

nonspuriousness. Randomized experiments are able to convincing establish nonspuriousness because of their

use of random assignment. Random assignment ensures that research subjects will be equal in expectation on all

variables – both observed and unobserved variables – prior to the administration of the experimental

intervention. The phrase “equal in expectation” does not mean that the research subjects assigned to each of the

experimental conditions will be perfectly equal on all variables. Instead, equal in expectation means that if we

could repeat this assignment process an infinite number of times, the population means on all variables would

be equal for each of the experimental conditions. Therefore, any differences between research subjects assigned

to the various experimental conditions are due to chance. Because there are no systematic differences between

the experimental groups on any variable besides the experimental condition, randomized experiments are able

to rule out all potential third variables as alternative explanations for the observed differences on the outcome

variable(s) of interest.

17
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Quasi experiments have much greater difficulty in establishing nonspuriousness. In quasi experiments the

actions and/or wishes of those involved in the research affect which experimental condition they eventually

receive. This is highly problematic, as research subjects who choose to participate in a particular level of the

experimental condition often differ from other research subjects on observed and/or unobserved variables. If

research subjects in various levels of the experimental condition (e.g., program participants vs. nonparticipants)

differ only on observed variables, then it would be easy to control for these observed differences by using

statistical techniques such as multiple regression. However, in the absence of random assignment, how does one

establish convincingly that participants and nonparticipants differ only on observed variables? It stands to

reason that if the groups differ on observed variables, then they also differ on unobserved variables as well.

Further, even if participants and nonparticipants are equal on observed variables, this does not mean that these

groups are also equal on important unobserved variables. This is the crucial issue, because it is these

unobserved differences that cause selection bias. Selection bias refers to inaccuracies in the estimated

relationship between variables that is caused by omitted or unmeasured variables. Because quasi experiments do

not establish that research subjects are equal in expectation on all variables, especially unobserved variables,

prior to the administration of the experimental intervention, selection bias is a persistent problem in

quasi‐experimental research designs .

In the language of research methods, in randomized experiments, the assignment of research subjects to

experimental conditions is exogenous . Exogenous in this context means outside or external to everyone

involved in the experiment including the research subjects, treatment providers, and researchers – only

randomization affects experimental assignment. Research subjects have no influence on which level of the

experimental condition they will be assigned. However, in quasi experiments, the actions and wishes of those

involved in the research including research subjects, their families, treatment providers, criminal justice

officials, and researchers among many others may affect assignment; and therefore, assignment in quasi

experiments is endogenous – meaning that the assignment process is affected by factors internal to the

experiment. Endogeneity is highly problematic because accurate estimation of causal relationships requires the

cause variable to be at least partially exogenous.

18
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Threats to Causal Validity

Randomized Experiments

The use of randomized experimental research designs ensures that the research subjects in each of the

experimental conditions are equal in expectation before the administration of the experimental treatment.

However, the use of randomized experimental designs does not ensure that the experiment will remain bias‐free

after randomization. Randomized experiments must be carefully planned and implemented to avoid various

biases affecting their results postrandomization. In particular, there are three primary threats (i.e., sources of

bias) that must be guarded against for randomized experiments to achieve high levels of causal validity. The

first potential threat is contamination . Contamination occurs in situations where research subjects assigned to

different levels of the experiment (e.g., participants and nonparticipants) come into direct contact or interact in

other ways. Contamination occurs when nonparticipants end up receiving the treatment via interactions with

participants. For example, if nonparticipants learn ideas/techniques discussed in the experimental treatment,

then this knowledge may attenuate the size of the treatment effect because in essence nonparticipants received

some of the experiment treatment vicariously. Cross‐overs are a second potential threat to the causal validity of

randomized experimental designs. Cross‐overs refers to research subjects assigned to one condition who end up

in some other experimental condition. For example, if some nonparticipants end up receiving the treatment

because of an error or deliberate actions, then these individuals have “crossed‐over.” Cross‐overs, particularly

as their numbers rise, may attenuate the magnitude of the treatment effect and thereby negatively affect the

experiment's causal validity. The third potential threat to randomized experimental research designs is attrition .

Attrition is the loss of research subjects due to factors such as being unable to locate the subjects for follow‐up

interviews/assessments, subjects declining to participate, death of research subjects, and so forth. Attrition

becomes an increasingly potent problem as the length of the tracking period grows. Attrition is problematic in

two ways. First, general attrition (i.e., attrition across experimental conditions) undermines external validity, the

ability to generalize research findings beyond the sample. Second and more problematic in terms of causal

validity is differential attrition (i.e., attrition rates differ markedly between experimental conditions), as

differential attrition has the potential to undo the equating of groups accomplished via random assignment.

19
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Quasi Experiments

Quasi experiments face a host of issues that threaten the causal validity of findings derived from these designs.

The particular threats depend on the specific design features of the quasi experiment. Quasi experiments using

one‐group designs face the most serious threats to the causal validity of their findings. These threats

include maturation (i.e., changes due to aging), regression to the mean (i.e., the tendency of research subjects

who scored unusually high and low scores in initial assessments to regress toward less extreme scores in later

assessments), testing (i.e., the tendency of research subjects to respond differently in later assessments because

they have been sensitized to the behaviors under investigation), and “history” (i.e., external events, besides the

intervention, that cause changes in the behaviors under investigation). All of these threats are competing

explanations for the results obtained from one‐group quasi‐experimental research designs. Given the number of

threats challenging the causal validity of one‐group designs, these designs are the weakest type of experiments.

Two‐group quasi‐experimental designs generally have fewer and different primary threats to their causal

validity in comparison to one‐group designs. Briefly, two‐group quasi‐experimental designs have all of the

same threats as randomized experiments and the additional threat of selection bias. As discussed above, the

nonrandom assignment of research subjects to experimental conditions leaves open the possibility that research

subjects assigned to various levels of the experimental condition differed on observed and unobserved variables

before the administration of the experimental treatment. As a result, the variable capturing treatment assignment

is potentially endogenous, which is highly problematic because accurate estimation of the treatment effect

requires the treatment assignment variable to be exogenous.

Exogeneity in Nonrandomized Experiments

The use of randomized experiments is not the only means of achieving exogeneity. There are several other

research designs/research methods of achieving at least partial exogeneity. These designs/methods are more

frequently utilized in fields outside of criminology and are making inroads in criminology. These

quasi‐experimental designs/methods include natural experiments, regression discontinuity, and instrumental

variable estimation. These techniques allow researchers to accurately estimate causal relationships and draw

causal inferences in certain situations.

20
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
Natural experiments are one means of establishing exogenous variation in a cause variable when researcher‐led

random assignment is not feasible. A natural experiment is study in which external factors such as natural

events, serendipity, or policy changes “assign” research subjects to various experimental conditions of interest.

Because the assignment process is external to the research subjects under observation, the assignment process is

exogenous, or at least arguably exogenous. This exogenous variation allows researchers to accurately estimate

causal relationships.

Natural experiments seem to be increasingly common in the social sciences (see Dunning, 2012). As an

example of a natural experiment, Kirk (2009) wished to learn the causal effect of relocating previously

incarcerated offenders from their old neighborhoods of residence to new less criminogenic neighborhoods. This

is an important theoretical and practical issue because we know that many parolees return to the same

criminogenic neighborhoods and social networks that contributed to their involvement in offending in the first

place, and therefore we shouldn't be surprised that recidivism is often alarmingly high. While it is not

impossible to conduct a randomized experiment on this issue, it would be difficult for a variety of reasons.

However, a recent natural event, Hurricane Katrina, forced many parolees who resided in high‐crime areas of

New Orleans hard hit by the storm to move to other neighborhoods. In essence, Hurricane Katrina exogenously

assigned some parolees to new neighborhoods, which made it possible to estimate the causal effect of relocation

on recidivism. Kirk found that parolees who moved to a new area were substantially less likely to be

reincarcerated within three years of release in comparison to parolees who did not move.

Another research design capable of establishing exogenous variation is the regression discontinuity design (see

Murnane and Willett, 2011). The key element of this design is the use of some “forcing variable” that

establishes a cut point (or threshold) that assigns research subjects below the cut point to one experimental

condition and those above the cut point to another condition. The cut point is used as an exogenous source of

variation; research subjects just below and just above the cut point are compared to estimate the causal

relationship between the variables of interest. As an example of a regression discontinuity design, Berk and

Rauma (1983) assessed the causal effect of providing financial assistance in the form of unemployment

insurance to recently released former prison inmates. In order to qualify for the financial assistance former

21
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
prison inmates had to have made at least $1,500 in the year prior to release; this criterion was used as the

forcing variable used to assign former inmates to either the control (no financial assistance) or the treatment

(financial assistance) conditions. Berk and Rauma found that financial assistance caused a 13% reduction in

recidivism.

Outside of criminology, the most popular means of estimating causal relationships without the use of a random

experiment is instrumental variable estimation. The logic of instrumental variable estimation begins by noting

that if some part of the variation in some endogenous variable of interest could be established as exogenous,

then this part of the variation in the variable of interest could be used to accurately estimate its causal effect on

the outcome of interest. An “instrumental variable” can be used to identify exogenous variation. An

instrumental variable is one that satisfies two assumptions: (1) it is uncorrelated with the error term of the

regression of the outcome variable of interest on the endogenous independent variable of interest, and (2) it is

correlated with the endogenous variable of interest. The first assumption means that the instrumental variable

can have no effect on the outcome variable except via its indirect effect on the outcome through the endogenous

independent variable. This is a strong assumption because the instrumental variable must only be related to the

outcome variable through the endogenous independent (causal) variable and the instrumental variable cannot be

correlated with other factors that affect the outcome variable. If an instrumental variable meeting these criteria

can be found, then estimating the causal relationship between the endogenous variable and the outcome of

interest is straightforward and can be accomplished using several statistical techniques, of which two‐stage least

stages is most popular.

Instrumental variable estimation has rarely been applied in criminology. Apel, Bushway, Paternoster, Brame,

and Sweeten (2008) is one example of instrumental variable estimation in criminology. Apel and colleagues

examine the relationship between hours worked by youth and delinquency. Prior research typically finds that

youth who work more hours are more likely to be involved in delinquency; however, number of hours worked

is likely to be endogenously related to delinquency, as youth who work more hours are likely to be different

from other youth on a host of factors that are also related to delinquency. Apel and colleagues use variation in

state child labor laws as an instrumental variable to identify exogenous variation in the number of hours

22
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
worked. Contrary to prior research, these authors find that the number of hours worked by youth reduces

delinquency.

Q. 5 Write notes on following:

a) Survey Studies

Survey Research is defined as the process of conducting research using surveys that researchers send to survey

respondents. The data collected from surveys is then statistically analyzed to draw meaningful research

conclusions. In the 21st century, every organization’s eager to understand what their customers think about their

products or services and make better business decisions. Researchers can conduct research in multiple ways, but

surveys are proven to be one of the most effective and trustworthy research methods. An online survey is a

method for extracting information about a significant business matter from an individual or a group of

individuals. It consists of structured survey questions that motivate the participants to respond, Creditable

survey research can give these businesses access to a vast information bank. Organizations in media, other

companies, and even governments rely on survey research to obtain accurate data. The traditional definition of

survey research is a quantitative method for collecting information from a pool of respondents by asking

multiple survey questions. This research type includes the recruitment of individuals, collection, and analysis of

data. It’s useful for researchers who aim at communicating new features or trends to their respondents.

Generally, it’s the primary step towards obtaining quick information about mainstream topics and conducting

more rigorous and detailed quantitative research methods like surveys/polls or qualitative research methods like

focus groups/on-call interviews can follow. There are many situations where researchers can conduct research

using a blend of both qualitative and quantitative strategies.

b) Interrelationship Studies

Interrelationships are the connections and interactions between people, groups of people, or parts of a system

within the system or outside the system. They can often explain events such as success or failure of a business

venture. A system is a set of distinct parts that interact with each other to form a distinct whole. A business or

other type of organization is a system with parts such as organizational structure, management structure,

23
 Course: “Research Methods in Education” (8604)
Semester: Spring, 2021
resources, information, and employees. Something outside the system is part of the system's external

environment.

Implication for Business

Understanding how interrelationships work is an important part of strategy formation and is a primary

component of some theories of management, including systems theory and the concept of a learning

organization. Let's take a closer look at each of these.

Strategy Formulation

A key step in formulating any strategy is to identify the strengths, weaknesses, opportunities, and threats facing

an organization - often referred to as SWOT analysis. Many times there is no simple explanation of a weakness

or strength, but rather they arise out of interaction of various components of your organization as well as the

outside environment. For example, imagine you are a book publisher who sees a weakness due to declining

market share. The weakness is actually related to the external threat of electronic books, which also provides an

opportunity for the company to enter the electronic book market.

Systems Theory

This is a management technique that treats a business as a system. In open-system theory, you view the business

as a system that interacts with its outside environment through inputs (such as raw materials), throughputs (such

as the manufacturing process), and outputs (the finished products) that are released back into the business'

external environment. Understanding the interrelationships of inputs, throughputs, and outputs is crucial to

effective management under the systems theory technique.

24