The purpose of this study was to estimate genetic parameters for sow BW loss during lactation. Data and pedigree information were available for Landrace (n = 3,310), York (n = 827) and Landrace × York F₁ sows (n = 354) from The Maschhoffs (Carlyle, IL). Sows were housed in environmentally controlled facilities with slatted concrete flooring and had ad libitum access to water. Females were restricted fed during gestation based on a visual body condition score of 1 to 5 (1 = thin, 5 = fat). During lactation sows were fed ad libitum. Sow traits analyzed included body condition score at farrowing (FBCS), total number born (TNB), number born alive (NBA), litter birth weight (LBW), litter weaning weight (LWW), number weaned (NW), body condition score at weaning (WBCS), and sow BW loss during lactation (WTΔ). Variance components were estimated using ASReml. All models included fixed effects of genetic line, parity, and contemporary group and random effects of animal (sow) and permanent environment. Covariates were included for LBW (NBA), LWW (piglet age at weaning and number of piglets fostered), NW (number of piglets fostered), WBCS (lactation length) and WTΔ (lactation length). Heritability estimates for FBCS, TNB, NBA, LBW, LWW, NW, WBCS and WTΔ were 0.17, 0.15, 0.15, 0.25, 0.15, 0.11, 0.16, and 0.13 respectively. Permanent environment variance estimates for FBCS, TNB, NBA, LBW, LWW, NW, WBCS and WTΔ were 0.0007, 0.26, 0.20, 0.49, 2.65, 0.04, 0.0004 and 1.29 respectively. Phenotypic variance estimates for FBCS, TNB, NBA, LBW, LWW, NW, WBCS and WTΔ were 0.015, 11.50, 10.49, 5.66, 112.4, 4.35, 0.014 and 251.5 respectively. Genetic correlations between WTΔ with FBCS, TNB, NBA, LBW, LWW, NW and WBCS were −0.05, 0.01, −0.02, 0.50, 0.28, 0.05 and −0.19 respectively. Phenotypic correlations between WTΔ with FBCS, TNB, NBA, LBW, LWW, NW and WBCS were 0.10, 0.09, 0.08, 0.15, 0.20, 0.15 and −0.03 respectively. Selection for reduced BW loss during lactation appears possible and would have minimal effect on litter size.