Conjunctive Analysis of Case Configurations
Also known as: CACC, Conjunctive Analysis, Case Configuration Analysis
Conjunctive analysis of case configurations (CACC) is an exploratory, case-based method for analyzing categorical crime data. Introduced by Miethe, Hart, and Regoeczi in 2008, it builds a matrix of all observed combinations of categorical attributes — the distinct case 'profiles' — and tabulates how often each occurs and what its outcome rate is, revealing how attributes act in combination rather than as isolated net effects.
Key highlights
- Treats the case as a holistic configuration, exposing how attributes act together rather than as isolated, additive net effects.
- Reveals context-dependent (conjunctive) interactions and situational clustering that single regression coefficients average away.
- Produces an intuitive, transparent table of recurring case profiles with their frequencies and outcome rates, easy to communicate.
- Largely assumption-free and exploratory — no linearity, additivity, or distributional assumptions about the predictors.
- Bridges qualitative configurational thinking (as in QCA) with quantitative data, accommodating many cases at once.
Intuition
This section is available to Pro members. Upgrade to Pro
How it works
This section is available to Pro members. Upgrade to Pro
When to use it
Use CACC when your cases are best described by several categorical attributes and you suspect those attributes work in combination — when context, not isolated main effects, drives the outcome. It is well suited to exploratory analysis of crime events, victimization, sentencing, and homicide situations, where you want to see which recurring case profiles exist and how their outcome rates differ. It complements rather than replaces regression: regression estimates average net effects, while CACC surfaces interactions and rare-but-meaningful configurations. It is less appropriate when key variables are inherently continuous and shouldn't be categorized, when the sample is too small to populate profiles with stable case counts, or when you need formal hypothesis tests of a single causal effect rather than a descriptive map of configurations.
Strengths & limitations
- Treats the case as a holistic configuration, exposing how attributes act together rather than as isolated, additive net effects.
- Reveals context-dependent (conjunctive) interactions and situational clustering that single regression coefficients average away.
- Produces an intuitive, transparent table of recurring case profiles with their frequencies and outcome rates, easy to communicate.
- Largely assumption-free and exploratory — no linearity, additivity, or distributional assumptions about the predictors.
- Bridges qualitative configurational thinking (as in QCA) with quantitative data, accommodating many cases at once.
- It is descriptive and exploratory: it maps configurations and outcome rates but does not provide formal significance tests or causal estimates.
- The number of possible profiles grows multiplicatively with attributes and levels, so adding variables quickly fragments the data ('dimensionality').
- Results depend heavily on how continuous variables are categorized and on the dominant-profile frequency threshold chosen.
- Rare but important configurations may fall below the threshold and be dropped, while sparse profiles give unstable outcome rates.
- Comparisons across profiles can multiply quickly, inviting over-interpretation of differences that are within sampling noise.
Common pitfalls
This section is available to Pro members. Upgrade to Pro
Applications
This section is available to Pro members. Upgrade to Pro
Frequently asked
How does CACC differ from regression analysis?
Regression is variable-based: it estimates the average net effect of each predictor while holding the others constant, assuming effects add up. CACC is case-based: it treats each case as a whole configuration of categorical attributes, tabulates the recurring profiles, and reports each profile's outcome rate. Where regression gives one coefficient per variable, CACC shows how the same attribute can matter differently depending on the other attributes present, making conjunctive, context-dependent effects visible. The two are complementary rather than competing.
What is the relationship between CACC and qualitative comparative analysis (QCA)?
CACC grows directly out of the configurational logic of Ragin's QCA, which represents cases as combinations of conditions and looks for which combinations are linked to an outcome. CACC adapts that thinking to larger, quantitative crime datasets: instead of Boolean minimization across a small number of cases, it enumerates observed attribute combinations, keeps the dominant (frequent) ones, and compares their outcome rates. In practice analysts sometimes use QCA tools (such as the fsQCA software or the R QCA package) alongside CACC for configurational work.
How many attributes can CACC handle?
In principle any number, but practically the method is constrained by the multiplicative growth of possible profiles: with p attributes each having Lⱼ levels there are ∏ Lⱼ logically possible combinations, so adding variables rapidly fragments the data. Analysts therefore use a modest set of substantively important categorical attributes, keep the number of levels small, and rely on the dominant-profile threshold to focus on the configurations that actually recur often enough to analyze reliably.
Sources
- 1.Miethe, T. D., Hart, T. C., & Regoeczi, W. C. (2008). The conjunctive analysis of case configurations: An exploratory method for discrete multivariate analyses of crime data. Journal of Quantitative Criminology, 24(2), 227–241.
- 2.Miethe, T. D., & Regoeczi, W. C. (2004). Rethinking Homicide: Exploring the Structure and Process Underlying Deadly Situations. Cambridge University Press.ISBN 9780521030106
You have read it. What now?
Cite this page
ScholarGate. (2026, June 22). Conjunctive Analysis of Case Configurations. ScholarGate. https://scholargate.app/criminology/conjunctive-analysis-case-configurations