Chapter 4 Summary
Before you can observe and analyze, you need a plan. First, you must specify clearly
what you want to find out. Second, you must determine the best way to go about doing it.
Three Purposes of Research-
Most social science research is conducted to explore a topic or to familiarize with
This approach occurs when a researcher examines a new interest or when the
subject of study is relatively new.
Sometimes pursued through the use of focus groups. (i.e. in market research)
Typically done for 3 reasons:
1. to satisfy curiosity and desire for better understanding
2. to test the feasibility of undertaking a more extensive study
3. to develop methods to be used in subsequent studies.
Shortcoming is that they seldom provide satisfactory answers to research
questions. However, they can hint at answers and give insights into methods to be
The people in exploratory research are seldom representative of the larger pop.
Observation and description of situations and events.
More accurate and precise than causal observation.
Many begin as qualitative studies and researchers then go on to examine why
observed patterns exist.
Answer the question of why a phenomenon occurs
Identifying variables that provide an explanation.
Logic of Causation-
Social science operates on a basis of a causal model that is probabilistic
Causation in Idiographic & Nomothetic Explanations:
Idiographic model aims at explanation through the enumeration of many reasons
that lie behind an action or event.
Example- in response to a plea of extenuating circumstance, a criminal court may
seek to examine all various factors that led to the defendant’s behavior.
Nomothetic model is designed to discover the most important considerations in
explaining a general class of action or events.
Involves the isolation of a few considerations that will provide a partial
explanation of a behavior.
Aims at providing the greatest amount of explanation with the smallest number of
causal variables in order to uncover general patterns of cause and effect. Probabilistic- nomothetic model indicates a very high or low probability that a
given action will occur whenever a limited number of specified considerations are
Adding variables increases the degree of explanation, but makes explanation more
Phrases like “leads to”, “arises from”, and “predictor of”, signal causal
Example- looking for an explanation of prejudice, researcher’s would note that a
large number of circumstances and experiences can contribute to this. They would
look for factors that affect the levels of prejudice.
Criteria for Nomothetic Causality-
1. The variables must be correlated
2. The cause takes place before the effect
3. The variables are nonspurious
To say that a causal relationship exists, there must be an actual, observed
relationship- correlation- between the variables.
When one changes, so does the other.
Particular attributes of one variable are associated with particular attributes of the
A causal variable must precede the effects
The observed correlation between variables cannot be explained in terms of a
Spurious relationships- a coincidental statistical correlation between two variables
that is shown to be caused by some third variable.
The mere fact of association does not tell us which variable causes the other, or
whether there is any causal relationship between them.
False Criteria for Nomothetic Causality-
Complete Causation: Nomothetic explanations are probabilistic and usually
Exceptional Cases: Exceptions do not disconfirm a causal relationship.
Majority of Cases: Causal relationships can be true even if they do not apply in
the majority of cases. As long as they are more likely, we say there is a causal
relationship. The standard of causation can be seen in terms of necessary and
Necessary & Sufficient Causes-
A necessary cause represents a condition that MUST be present for an effect to
follow. A sufficient cause represents a condition that, if present, guarantees the effect.
This does not mean that a sufficient cause is the only possible causes.
A cause can be sufficient but not necessary.
Single causes that are both necessary and sufficient are never discovered among
nomothetic relationships among variables
In idiographic research, there may be a depth of explanation from which one
could determine a sufficient cause for a particular result, but there could also be
other causal paths to the same results. Therefore, idiographic causes are sufficient
but not necessary.
Units of Analysis-
The what or who being studied. The most typical units of analysis are people; but
social artifacts, groups, populations, and other aggregates are studied as well.
The things we want to examine in order to create summary descriptions of all
such units and to explain differences among them.
The most typical units of analysis. Researchers tend to describe and explain social
groups and interactions by aggregating and analyzing the descriptions of
Descriptive studies with individuals as their units of analysis typically aim to
describe the population that comprises those individuals.
Explanatory studies aim to discover the social dynamics operating within that
Individuals may be characterized by their membership in social groupings. They
can then be aggregated to make generalizations about the populations they belong
May be interested in characteristics of a group, considered as a single entity.
Example- if you were to study criminals by looking at members of a gang,
individuals would be the unit of analysis. However, if you wanted to learn the
difference between big and small gangs and studied all the gangs in a city, you
would be interested in the group rather than it’s individual members.
We can derive the characteristics of social groups from those of their individual
Social groups may be characterized according to their environments (i.e. families
may be described by their dwellings)
Some attributes apply only to collectivities, other apply only to individuals (i.e.
families or gangs can be characterized by “number of members”).
Examples- Individual corporations characterized by number of employees, net
profits, gross assets, etc. Also, churches, universities, academic departments. Social Artifacts:
Any product of social beings or their environment.
Concrete objects such as books, paintings, poems, automobiles, buildings, jokes,
student excuses for missing exams, etc.
Each social artifact implies a set of all objects of the same class.
Social interactions are also social artifacts (i.e. weddings, friendships, court cases,
divorces, fistfights, student demonstrations).
Faulty Reasoning about Units of Analysis: The Ecological Fallacy-
Ecological Fallacy- erroneously drawing conclusions about individuals based
solely on the observation of groups.
Assumption that something learned about an ecological unit says something about
the individuals making up that unit.
(Example- an analysis shows that a political riding with relatively younger voters