How Statistics Determined the Dollar Amount of Parking Meter Theft in New York City

How do you recover stolen cash when you don’t know how much was stolen? New York City asked Dr. William Fairley, senior statistician at A+I, to determine the amount.

Our case begins when six Brink’s employees – assigned to collect coins from New York City parking meters – were arrested under a bridge in Manhattan with a trunkful of coins. The city filed a complaint against Brink’s for negligence in supervising its employees and for breach of contract, and the case came to trial in the U.S. District Court for the Southern District of New York.

A+I approached the problem by asking: what do we know? They compared daily meter revenues collected by the Brink’s team with the amounts collected before Brink’s was hired, and after the firm was fired.

Jeffrey Glen, the attorney in the case for the City of New York wrote:  “… the analysis chosen enabled the statistician [Dr. Fairley] to conclude that theft accounted for the intercompany revenue difference, and that but for the theft, [the organization’s] collections would have exceeded those of [another organization’s] for a 10-month comparison period by some $1,400,000… The jury returned a verdict for the city of $1,000,000 in compensatory damages, and this verdict was affirmed by both the trial judge and the court of appeals.”  

In upholding the decision for the city, Judge Weinfeld of the 2nd Circuit Court of Appeals responded to criticisms that the statistical estimate was imprecise by referencing Dr. Fairley’s testimony: “The statistical expert testified on cross-examination that 'the most reasonable estimate of the difference, and what [you can] most reasonably attribute the difference to, [is] the best you can do’…. The method employed to calculate the damages was somewhat akin to that upheld in Bigelow v. RKP Radio Pictures, Inc., which recognized that when a defendant’s tortious conduct...precludes precise ascertainment of damages, the jury may make ‘a just and reasonable estimate of the damage based on relevant data’.”

In a subsequent case of stolen parking collections, Dr. Fairley presented a simple graphical analysis of the amount of the theft, closely following the method applied so effectively in the Brink’s case. The contractor conceded responsibility and quickly settled the case.

Analysis & Inference has also estimated theft and fraud amounts for parking and rapid transit systems in Philadelphia, Boston, New York and San Diego.  

At the Philadelphia International Airport, when drivers exiting the parking lot presented a ticket for payment, the attendants substituted counterfeit tickets with a lower value and pocketed the difference. The thieves were three years into their lucrative scam before they were caught and convicted. To estimate the dollar amount stolen, A+I triangulated the value by applying custom statistical models to several sources of airport operational data. Both the insurer and the Airport accepted A+I’s findings and negotiated the amount of the claim.