Technical Abstract: The objectives of this study were to estimate heritabilities for herds participating in Dairy Herd Improvement and the relationship of herd heritability with sire misidentification rate. Individual herd heritabilities for milk, fat and protein yield and somatic cell score (SCS) were calculated with daughter-dam regression and daughter-sire predicted transmitting ability (PTA) regression using 4,712,166 records for 16,336 herds in August 2000 and 7,084,953 records for 20,920 herds in August 2006. Herd heritabilities were estimated with regression models in ASReml that included fixed breed, age within parity, herd-year-season of calving, dam records nested within state, sire PTA within state, and an interaction between sire PTA and herd variance; random regression coefficients were dam records within herd and sire PTA within herd. Average daughter-dam herd heritability estimates ranged from 0.21 (SCS in 2000) to 0.73 (protein percent in 2006), whereas daughter-sire herd heritability ranged from 0.10 (SCS in 2000) to 0.42 (protein percent in 2006). Verification of sire identification with DNA marker analysis was provided by Accelerated Genetics and Alta Genetics, Inc. Daughter-sire herd heritability was more strongly correlated with sire misidentification rate than daughter-dam herd heritability. The correlation between a principal component for all measures of herd heritability and sire misidentification rate was -0.38 and -0.50 in 2000 and 2006, respectively. Herd heritability can be generated with simple regression techniques for several thousand herds simultaneously. The herd heritability estimates were correlated negatively with sire misidentification rates and could be used to identify herds that provide inaccurate data for progeny testing.