The process and problems of
Social research is done through the
1. Specifying a research question
2. Developing an appropriate research strategy
3. Choosing appropriate units of analysis
4. Conforming to scientific and ethical guidelines
What is the question?
•A social research question is a question about
the social world that you seek to answer through
the collection and analysis of firsthand, verifiable,
•But that doesn’t mean it is easy to specify a research
question. In fact, formulating a good research question
can be surprisingly difficult.
What makes a research question “good”?
1. Feasibility: Can you start and finish an investigation
with available resources and in the time allotted?
2. Social importance: Will the answer make a difference
in the social world, even if it only helps people
understand a problem?
3. Scientific relevance: Does your question help resolve
some contradictory research findings or a puzzling
issue in social theory?
What is the theory?
•Building and evaluating theory is one of the most
important objectives of social science.
•A theory is a logically interrelated set of propositions that
helps us make sense of many interrelated phenomena and
predict behavior or attitudes that are likely to occur when
certain conditions are met.
•Social theories suggest the areas on which we should
focus and the propositions that we should consider
How do we find relevant social theory and
•You’ll find that in any area of research, developing
an understanding of relevant theories will help you
to ask important questions, consider reasonable
alternatives and choose appropriate research procedures.
•The social science research community is large and active,
and new research results appear continually in scholarly
journals and books.
•The World Wide Web is also a good source.
What is the strategy?
•When we conduct social research, we are attempting to
connect theory with empirical data—the evidence we
obtain from the social world.
•Deductive research--starting with a social theory and then
testing some of its implications with data.
•Inductive research--first collecting the data and then
developing a theory that explains patterns in the data.
•A research project can use both strategies.
• In deductive research a specific expectation is deduced from
a general theoretical premise and then tested with data that have
been collected for this purpose.
• We call the specific expectation deduced from the more
general theory a hypothesis.
•A hypothesis proposes a relationship between two or
more variables—characteristics or properties that can vary.
Insert exhibit 2.2
•Variation in one variable is proposed to predict,
influence, or cause variation in the other variable.
•The proposed influence is the independent variable; its
effect or consequence is the dependent variable.
•After the researchers formulate one or more hypotheses
and develop research procedures, they collect data with
which to test the hypothesis.
Direction of association
•A pattern in a relationship between two variables---that
is, the value of a variable tends to change consistently in
relation to change in the other variable
• When researchers hypothesize that one variable increases
as the other variable increases, the direction of association
is positive .
•But when one variable increases as the other decreases,
or vice versa, the direction of association is
negative, or inverse .
• Inductive research begins with specific data, which
are then used to develop (induce) a general explanation
(a theory) to account for the data.
•Inductive reasoning enters into deductive research when we
find unexpected patterns in the data we have collected for
testing a hypothesis.
•We may call these patterns serendipitous findings
or anomalous findings.
What is the design?
•Researchers usually start with a question, though some begin with a
theory or a strategy.
•If you are very systematic, the question is related to a theory, and an
appropriate strategy is chosen for the research.
•There are several different types of research designs.
•One important distinction between the types is whether data are collected
at one point in time or at two or more points in time.
•Another distinction is whether the design focuses on individuals or on groups.
•In a cross-sectional research design, all data are collected
at one point in time. Identifying the time order of effects—
what happened first, and so on—is critical for developing
a causal analysis, but can be an insurmountable problem
with a cross-sectional design.
•In longitudinal research designs, data are collected
at two or more points in time, and so identification of
the time order of effects can be quite straightforward.
•By measuring the value of cases on an independent variable
and a dependent variable at different times, the researcher
can determine whether variation in the independent variable
precedes variation in the dependent variable.
•The value of longitudinal data is so great that every effort
should be made to develop longitudinal research designs
when they are appropriate for the search question asked.
Insert exhibit 2.4
Types of longitudinal designs
• Repeated cross-sectional design (trend study).
A type of longitudinal study in which data are collected
at two or more points in time from different samples of the
•Fixed-sample panel design (panel study). A type of
longitudinal study in which data are collected from the
same individuals—the panel—at two or more points in time.
In another type of panel design, panel members who
leave are replaced with new members.
Types of longitudinal designs con’t
•Event-based design (cohort study). A type of
longitudinal study in which data are collected at two
or more points in time from individuals in a cohort.
Units and levels of analysis
•Whenever we design research, we must decide whether
to use individuals or groups as our units of analysis and
whether to collect data at one or several points in time.
•The decisions that we make about these design
elements will affect our ability to draw causal
conclusions in our analysis.
• Units of analysis: the level of social life on which the
research question is focused, such as individuals, groups,
towns, or nations.
•In most sociological and psychological studies,
the units of analysis are individuals.
• Levels of analysis: from the most micro (small) to
the most macro (largest).
•Conclusions about processes at the individual level
(micro) should be based on individual-level data.
• Conclusions about group-level processes (macro)
should be based on data collected about groups.
•In most cases, when this rule is violated, we can be
misled about the existence of an association between
•A researcher who draws conclusions about individual-level
processes from group-level data could be making what
is termed an ecological fallacy.
Insert exhibit 2.6
•On the other hand, when data about individuals are
used to make inferences about group-level processes,
a problem occurs that can be thought of as the mirror
image of the ecological fallacy: the reductionist fallacy,
also known as reductionism, or the individualist fallacy.
But is it ethical?
•Research distorted by political or personal pressures to
find particular outcomes or to achieve the most
marketable results is unlikely to be carried out in an
open and honest fashion.
•Openness about research procedures and results goes
hand in hand with honesty in research design.
•Openness is also essential if researchers are to learn
from the work of others.
The uses of science
•Scientists must consider the uses to which their
research is put.
•Social scientists who conduct research for organizations
and agencies may face additional difficulties when
the organization, not the researcher, controls the
final report and the publicity it receives.
Research on people
•Whenever we interact with other people as social
scientists we must give paramount importance to the
rational concerns and emotional needs that will shape
their responses to our actions.
• It is here that ethical research practice begins, with
the recognition that our research procedures involve
people who deserve as much respect for their well-being
as we do for ours.
•Maintaining confidentiality is a key ethical obligation.
• This means obtaining informed consent.
•To be informed, consent must be given by persons
who are competent to consent, have consented
voluntarily, are fully informed about the research,
and have comprehended what they have been told
Other ethical issues
• Thepotential of withholding treatment from some
subjects, as is done in experiments with placebos.
• The extent to which ethical issues are a problem
varies dramatically with research designs.
• Survey research creates few ethical problems.
•But experiments can put people in uncomfortable
or embarrassing situations.
Institutional review boards (IRB)
• Federal regulations require that every institution that
seeks federal funding for biomedical or behavioral
research on human subjects have an institutional
review board (IRB) that reviews research proposals.
• IRBs at universities and other agencies apply ethics
standards that are set by federal regulations but can be
expanded or specified by the IRB itself.