CRJU lecture 4 2.10.26
Terms:
causation
Units of analysis
Probabilistic causation
Ideographical causation
Nomothetic causation
Correlation
Necessary cause
Sufficient cause
Validity
Casual inference
Reliability
Validity
Panel studies
Retrospective research
Prospective research
Statistical conclusion validity
Internal validity
Construct validity
External validity
Bias
Generalizability
Temporal order
Units of analysis
Social artifacts
Causation
Ecological fallacy
Individualistic fallacy
Reductionism
Cross sectional studies
Descriptive research
Exploratory research
Longitudinal studies
Trend studies
Cohort studies
Scientific realism
Causation
the focus in explanatory research
Cause in social science is inherently probabilistic
-in criminal justice, this could mean that certain factors make criminal behavior more or less likely within groups of people
Idiographic causation
idiographic casual explanations are intended to explain one particular context or phenomenon
Nomothetic Causation
seeks to identify general laws and patterns that apply to may cases. Its utility power is determined by its applicability (accuracy) scope of application (generality)
Criteria for causality
To infer nomothetic causation, shadish, cook, and Campbell suggest examining
if two variables vary together they must be empirically correlated
the cause occurs before the effect
the empirical correlation between the cause and effect is not due to some other factor
it can not be a spurious relationship
Necessary and sufficient causes
within the probabilistic model there are two types of causes
a necessary cause represents a condition that must be present for the effect to occur
a sufficient cause represents a condition that will pretty much guarantee that the effect will occur if it is present
Validity and casual Inference
validity is the approximate truth of an inference
By saying something is valid we make a judgement about the extent to which relevant evidence supports that inference as being true or correct
Reliability versus Validity
reliability measures a methods consistency, and validity addresses it’s accuracy
4 general categories of validity: statistical conclusion validity, internal validity, construct validity, external validity
Statistical conclusion validity
asks are changes in one variables related to changes in another?
corresponds with the first criterion for causality: empirical correlation between variables
Internal validity
IV threats can challenge casual statements about the observed covariation between two variables
an observed association between two variables has internal validity if the real is, in fact, casual and not due to the effects of one or more variables
External Validity
concerned with whether research findings in one study can be replicated in another study, often other different conditions
do the findings apply equally kn different settings? -
Example- Kansas City evaluation finding reductions in gun related crimes in police patrolled hotspots. Having similar findings in other locations with different types of crimes suggests the original findings from the Kansas City study had a high level of external validity
Construct validity
concerned with how well an observed relationship between variables represents the casual process
refers to generalizing from what we observe and measure to the real world things in which we are interested
Bias- internal validity and statistical conclusion validity threats are related to systematic and non systematic bias
Generalizability- construct validity and external validity are concerned with generalization to real world behaviors and conditions
Temporal order: which comes first, the drug use or the crime?
a statistical relationship exists, but the underlying causes affect both drug use and crime. This is a threat to internal validity
a crackdown on all drugs among all populations will have little effect to reduce serious crime
Scientific realism
bridges the idiographic and nomothetic approaches to explanation by seeking to understand how casual mechanisms operate in specific contexts
studies how such influences are involved in cause and effect relationships
Exhibits elements of both idiographic and nomothetic approaches to explanation
Units of analysis
The Who or the what being studies
also typically the unit of observation
Social artifacts
the products of social beings and their behavior. Social interactions are also examples.
Ecological fallacy
refers to the danger of making assertions about individuals based on the examinations of groups Or aggregations
Individualistic fallacy occurs when researchers have trouble reconciling general patterns of attitudes and actions with known individuals exceptions
Reductionism
an overly strict limitation on the concepts and variables to be considered as causes of the broad range of human behavior represented by crumbs and criminal justice policy
Cross sectional studies
carefully observe a single point in time (a cross section)
Typically descriptive and explanatory in nature
Descriptive research aims to define or summarize an event without explaining why it exists, focuses on acquiring and conveying facts
Explanatory research aims to explain why a phenomenon occurs by working to understand the causes and correlations between variables
Longitudinal studies
designed to permit observations over an extended period of time
Retrospective research
asks people to recall their past for the purposes of approximating observations over time
faulty technique because people have faulty memories
Prospective research
a longitudinal study that follows subjects forward in time