THREE TYPES OF STATISTICAL ANALYSIS WERE CONDUCTED: (1) POLICE INPUT MEASURES CONSISTING OF NUMBER OF LAW OFFICERS PER 100,000 POPULATION, POLICE EXPENDITURES ON ENFORCEMENT PER CAPITA, NUMBER OF OFFICERS PER SQUARE MILE, REAL EXPENDITURE PER SQUARE MILE, NUMBER OF OFFICERS PER CAPITA-MILE (NUMBER OF OFFICERS DISCOUNTED BY POPULATION AND AREA), AND REAL PER CAPITA EXPENDITURES PER SQUARE MILE; (2) POLICE OUTPUT MEASURES CONSISTING OF THE CLEARANCE RATE (THE PERCENT OF REPORTED CRIMES FOR WHICH ARRESTS HAVE BEEN MADE) AND THE CONVICTION RATE, OR PROBABILITY OF PUNISHMENT; AND (3) CRIME RATE RESPONSE AS DETERMINED BY REGRESSING CRIME RATES ON THE PROBABILITIES OF ARREST AND CONVICTION, THE MEAN NUMBER OF YEARS SENTENCED, AND ECONOMIC ACTIVITY AS MEASURED BY BANK DEBITS. RESULTS SHOWED THAT BOTH ORDINARY LEAST SQUARE AND STEP REGRESSION ANALYSES INDICATED THAT CRIME RATES FOR HOMICIDE AND AUTO THEFT WERE NEGATIVELY AND SIGNIFICANTLY CORRELATED WITH THEIR RESPECTIVE CLEARANCE RATES. CRIME RATES WERE ALSO FOUND TO BE NEGATIVELY CORRELATED WITH RISKS OF PUNISHMENT MEASURED BY THE PROBABILITY OF CONVICTION AFTER ARREST. THE PUNISHMENT VARIABLE, MEAN NUMBER OF YEARS SENTENCED, WAS NEGATIVELY ASSOCIATED WITH THE CRIME RATE FOR HOMICIDE BUT POSITIVELY ASSOCIATED WITH AUTO THEFT. NO EVIDENCE WAS FOUND AT THE MACRO (OR AGGREGATE) LEVEL THAT LINKED ENFORCEMENT EFFORT AND CLEARANCE RATES FOR EITHER AUTO THEFT OR HOMICIDE. EACH OF THE SIX ENFORCEMENT VARIABLES WERE FOUND TO HAVE NO SIGNIFICANT ASSOCIATION WITH EITHER CLEARANCE RATE. POLICE EFFORT WAS NOT AS MUCH AFFECTED BY POLICE INPUT AS IT WAS BY THE OUTPUT OF THE CRIMINAL SECTOR. IT WAS CONCLUDED, HOWEVER, THAT SIGNIFICANTLY LARGE INCREASES IN THE ENFORCEMENT EFFORT COULD HAVE A POSITIVE EFFECT ON CLEARANCE RATES AND A NEGATIVE EFFECT ON CRIME RATES, PARTICULARLY IF MEASURED BY A DISAGGREGATED FUNCTION BY FUNCTION STUDY. FOOTNOTES AND TABLES ARE PROVIDED. (DEG)