§ Mr. FieldTo ask the Secretary of State for Health what assessment he has made of the level of accuracy of his Department's most recent measurement of prescription fraud. [128913]
§ Ms StuartThe measurement exercise was designed so as to ensure that the variation in the results due to sampling should be no more than 1 per cent. (So that for an estimate of x per cent. the true value would have a 95 per cent. confidence interval of x plus 1 per cent. and x minus 1 per cent. or better). In fact the final estimate of the fraud/in error rate had 95 per cent. confidence limits of plus or minus 0.6 per cent.
A sample of forms dispensed by community pharmacists and appliance contractors to people claiming exemption from payment for prescription charges was selected using robust statistical techniques. The selected prescription forms were then subjected to a stringent investigative process to establish whether the patient who had made the claim had done so correctly, in error or fraudulently. Each case was investigated and examined individually and, where necessary, patients were contacted to establish the reasons for inconsistencies in the information given by them. The National Audit Office have examined the methodology used to arrive at the estimates and found that it was sound.