Appendix I: Objectives, Scope, and Methodology
FEMA made to the MD contractors, we drew a statistical sample of 250 units that were paid for by FEMA as receiving a preventative maintenance inspection. We constructed the population of preventative maintenance inspections using contractor back-up invoice documentation and monthly contract status reports as well as FEMA receiving reports confirming FEMA payments for unit maintenance from June 2006 through January 2007. We acquired preventative maintenance inspection forms from the MD contractors and FEMA. Improper or potentially fraudulent payments for unit maintenance include cases where the payment was made (1) for preventative maintenance inspections on units not identified in FEMA’s database, (2) based on preventative maintenance inspection forms that did not exist, and (3) based on inspection forms that did not contain an occupant’s signature denoting a full inspection occurred or that three attempts to conduct an inspection were made. To assess the reliability of the preventive maintenance inspections documentation from June 2006 through January 2007, we (1) reviewed existing documentation related to the data sources and (2) examined the data to identify obvious problems with completeness, accuracy, or duplicates. We determined that the data were sufficiently reliable for the statistical sample. Because we followed a probability procedure based on random selections, our sample is only one of a large number of samples that we might have drawn. Since each sample could have provided different estimates, we express our confidence in the precision of our particular sample’s results as a 95 percent confidence interval (e.g., plus or minus 5 percentage points). This is the interval that would contain the actual population value for 95 percent of the samples we could have drawn. As a result, we are 95 percent confident that each of the confidence intervals in this report will include the true values in the study population.
With regard to emergency after-hours calls, we could not test the $2.2 million in payments FEMA made because the data we received concerning these calls did not contain complete information. To determine whether FEMA made emergency after-hours repair payments for units that do not exist in its inventory records, we compared the barcodes on the 7,310 housing units that received emergency repairs from June 2006 to January 2007 with the barcodes listed in FEMA’s main database for tracking the assignment and location of mobile homes and trailers. We were unable to identify records for 1,732 of these 7,310 units. Using FEMA’s payment records, we then determined that FEMA made 2,780 improper or potentially fraudulent emergency repair payments related to these 1,732 trailers.
GAO-08-106 Hurricane Katrina