paper1 - research methodds
General Issues in Research Design
Chapter 3
*
Foundations of Social Science
- Two pillars of science are logic and observation
- These pillars relate to the three key aspects of science:
Theory
Data collection
Data analysis
Theory
Theory: a set of concepts and the proposed relationship among these concepts; a structure that is intended to represent or models something about the world
Provide general statements about social life
Used to guide research and develop a hypothesis
Hypothesis: a specified expectation and empirical reality
Y = f(X)
Hypothesis testing: involves finding out if observations are consistent with the hypothesis
Regularities and Exceptions
Goal of theory is to find patterns of regularity in social life
Formal and informal norms create regularity
Regularities can be studied via scientific analysis
Exceptions do not negate regularities Relationships are probabilistic: patterns need not be reflected in 100% of observations
Aggregates, Not Individuals
Social scientists study social patterns, or aggregates, not individual behavior
We care about why aggregated patterns of behavior are regular even when participating individuals change over time
e.g., processing and classifying new inmates
Variables and Attributes
Social science involves the study of these two concepts
Theory is written in a variable language; people are the carriers of those variables
e.g., lower-class juveniles are more likely to steal
Attributes - characteristics that describe some object/person
Variables - logical groupings
Male and female are the attributes of the variable gender
Variables and Relationships
Theories describe the relationships that might be logically expected among variables
Causation – an attribute of one variable is expected to cause, predispose, or encourage an attribute of another variable
Independent variable: “cause”, “influencer”
Dependent variable: “effect”, “depends”
Type of defense attorney (IV) effects prison or probation (DV)
Differing Avenues for Inquiry
- Three distinctions underlie many of the variations in social scientific research:
Explanations
Reasoning
Type of data
Idiographic and Nomothetic Explanations
- Idiographic explanations: seek a full and detailed understanding of a single case or situation
- Nomothetic explanations: are partial explanations that explain a class of situations or events rather than a single one.
- Both types are powerful tools in criminal justice research
Example of Ideographic Explanations
Clifford R. Shaw developed ideographic explanations to understand the lives of juvenile delinquents. These case studies, described in such books as The Jack-Roller and Brothers in Crime, offered researchers a comprehensive view of the effect that variables such as family factors, peer influences, and community circumstances have on the engagement in juvenile delinquency. Data collection involved interviews with the youths and their parents, analyzing diaries kept by the youths, and reviewing juveniles medical, school, and arrest records. These case studies were later used to develop monothetic explanations of juvenile delinquency that could be generalized to all delinquents.
Inductive and Reductive Reasoning
Deductive reasoning: moves from the general to the specific
From a logically or theoretically-expected pattern to observations that test the presence of the pattern
Inductive reasoning: moves from the specific to the general
From a set of observations to the discovery of a pattern among them
Grounded theory
Qualitative and Quantitative Data
All observations are qualitative at the outset
Qualitative = non-numerical; greater richness of meaning
Quantitative = numerical; carries a focusing of attention and specification of meaning
e.g., a person’s age
Both are useful and legitimate – choose based on topic or combine aspects of both
e.g., What constitutes “maturity”?
Criteria for Causation
Posited by Shadish, Cook, & Campbell (2002)
Empirical relationship between variables
Temporal order (cause precedes effect)
No alternative explanations – no spurious other variable(s) affecting the initial relationship
Validity and Causal Inference
When we make a cause-and-effect statement, we are concerned with its validity – whether it is true and valid
Validity threats: reasons we might be incorrect in stating that some cause produced some effect
Does Drug Use Cause Crime?
Temporal order: which comes first?
A statistical relationship exists, but underlying causes affect both drug use and crime (IV threat)
Relationship between crime and drug use varies by type of drug
How will policy affect drug use and crime? A crackdown on all drugs among all populations will do little to reduce serious crime.
Scientific Realism
- Scientific realism: bridges idiographic and nomothetic approaches to explanation by seeking to understand how casual mechanisms operate in specific contexts
- Scientific realism studies how other possible influences are involved in cause-and-effect relationships
- Contains elements of both idiographic and monothetic modes of explanation
Units of Analysis 1
Unit of analysis: what or who is studied
Individuals - (police, victims, defendants, inmates, gang members, burglars)
Groups - multiple persons with same characteristics - (gangs, police beats, patrol districts, households, city blocks, cities, counties)
Unit of Analysis 2
Organizations - formal groups with established leaders and rules - (prisons, police departments, courtrooms, drug treatment facilities, businesses, agencies)
Social artifacts - products of social beings and their behavior - (stories in newspapers, posts on the Internet, photographs of crime scenes, incident reports, police/citizen interactions)
Issues in Logic
Ecological fallacy: danger of making assertions about individuals based on the examination of groups or aggregations (Poor areas = more crime, therefore poor people commit more crime)
Individualistic fallacy: using anecdotal evidence to make an argument
Time Dimension
Time sequence is critical in determining causation
Time is also involved in the generalizability of research findings
Observations can either be made more or less at one point, or stretched over a longer period
Cross-Sectional Studies
Cross-sectional studies: observing a single point in time; simple and least costly way to conduct research
We cannot see social processes or changes; have to worry if we picked a bad point in time to capture
Typically descriptive or exploratory in nature
Longitudinal Studies
Longitudinal studies: permit observations over time
Trend – those that study changes within some general population over time (UCR)
Cohort – examine more specific populations as they change over time (Wolfgang study)
Panel – similar to trend or cohort, but the same set of people is interviewed on two or more occasions (NCVS) (panel attrition)
Cincinnati Study on Lead Exposure
Researchers at the University of Cincinnati recruited individuals born from 1979-1985 to take part in a longitudinal panel study. During childhood, the research subjects’ blood was tested for lead exposure several times. Interviews and surveys of the subjects and their parents were used to assess the youths’ levels of delinquency. The results showed that youths who were exposed to lead engaged in more acts of delinquency and used marijuana more than those not exposed. At the time of this study, the research subjects were between 15 and 17. The researchers are still studying this subjects, which will allow for more examinations of the effects of lead exposure on adult behaviors.
Dietrich, K.N., Ris, M.D., Succop, P.A., Berger, O.G. & Bornschein, R.L. (2001). Early exposure to lead and juvenile delinquency. Neurotoxicology and Teratology, 23, 511-518.
Approximating Longitudinal Studies
Logical inferences: may be possible to draw approximate conclusions about processes that take place over time, even when only cross sectional data is available
When time order of variables is clear, logical inferences can be made about processes taking place over time
Retrospective Research
Asks people to recall their past for the purpose of approximating observations over time
People have faulty memories; people lie
Analysis of past records also suffer from problems – records may be unavailable, incomplete, or inaccurate
Prospective research – longitudinal study that follows subjects forward in time (Widom – child abuse/drug use)
Time Dimension Summarized
Cross-sectional study = snapshot – an image at one point in time
Trend study = slide show – a series of snapshots in sequence over time, allows us to tell how some indicator varies over time
Panel study = motion picture – gives information about individual observations over time