means two things vary together. When one changes, the other changes, too.
Correlation does not mean two things are found together.
Three steps for showing causation:
1. Show correlation
Correlation means two things vary together. When one changes, the other changes
The variation is key here. Correlation does not mean things are bound together.
The things that are correlated must vary: take on different values, called
If only ne attribute is present in data, this isn't a variable because it doesn't vary.
E.g.: Hair colour.
Showing correlation requires that data include variation in both variables.
2. Show time-order
Cause must precede effect.
Does working longer hours lead to worse health, or do people in good health care
more about leisure time?
How to show? Longitudinal studies, theory.
3. Absence of spuriousness
This is the one we just can't seem to get around with 100% certainty.
What if 2 things vary together because they're both caused by something else.
Demonstrating spuriousness: find the correlation, hold possible source of
constant and look at the correlation again.
You can never be sure you've thought of and checked everything.
Experimental designs can dramatically reduce the risk of spuriousness.
Three purposes of research
Exploration is the attempt to develop an initial, rough understanding of some
To satisfy the researcher’s curiosity and desire for better understanding
To test the feasibility of undertaking a more extensive study
To develop the methods to be employed in any subsequent study 2
Description is the precise reporting and/or measurement of the characteristics of
some population or phenomenon under study.
Explanation is the discovery and reporting of relationships among different
aspects of the phenomenon under study. Whereas descriptive studies answer the
question “what’s so” explanatory ones tend to answer the question “why”
To answer why.
Both idiographic an nomothetic models of explanation rest on the idea of
The idiographic model aims at a complete understanding of particular
phenomenon, using all relevant factors.
explanations explain one, specific event or occurrence.
The nomothetic model aims at a general understanding-not necessarily complete
of a class of phenomena, using a small number of relevant causal factors.
Explain objective in general,explain a class of occurrences or a pattern.
Two types of causes
Acondition Must be present for the effect to follow
X is a necessary causes of Y, if Y cannot happen without X.
Take all the course to get a BA, but you need to pass all the course. Take
course is not sufficient causes, it is necessary.
X is a sufficient causes of Y if Y always happens when X happens.
Skip exam will fail.
Units of analysis are the people or things whose characteristics social researcher
observe, describe, and explain.
The unit of analysis in social reserach is the individual person, but it may also be
a social group, a formal org, a social artifact.
Erroneously drawing conclusions about individuals based solely on the
Cross-sectional study (same time different units) 3
Astudy based on observations representing a single point in time.
Exploratory and descriptive are often cross-sectional.
Asingle Canadian census
Astudy design involving the collection data at different point of time.
Trend study (general population)
A type of longitudinal study in which a given characteristic of some population is
monitored over time.
A study in which some specific subpopulation or cohort, is studied over time,
although data may be collected from different members in each set of observation.
Panel study (same sample each time)
A type of study of longitudinal study in which data are collected from the same set of
people at several points in time.
Design a research
3．Choice a method
6．Population and sample
11．Research design in review
Early days: The Wild Wild West
Before 1950's researchers were answerable only to their own consciences.
Abuses of the system lead to attention and eventually oversight.
Medical experiments on human subjects(syphilis and LSD experiments)
Social scientist making poor choices 4
After WWII, social scientist (and other wondered): WTF is wrong with people?
Milgram: People obey people in authority. (Shock experiment)
Zimbardo: People in authority abuse their power. (Prison Experiment)
Build fake prison, randomly assigned people to being prisoners and other to be
Experiment had to be discontinued for the safety of prisoners.
Most researchers are subject to codes of et