The purpose of this project was to use statistical modeling techniques to estimate rape and domestic assault rates, adjusting for interviewing conditions under which the National Crime Victimization Survey (NCVS) was administered. Data for women 16 years of age and older interviewed in the NCVS (see NATIONAL CRIME SURVEYS: NATIONAL SAMPLE, 1986-1990 [NEAR-TERM DATA] [ICPSR 8864]) were analyzed. The researchers considered whether the type of interview (personal or telephone) and the presence of another person (particularly a spouse) influenced or "gagged" the reporting of rape and domestic violence in the NCVS. The researchers also investigated correlates, primarily demographic in nature, of reporting rape, domestic violence, other assaults, and breaking and entry. In total, the data file contains reports of 434 rapes, 1,973 incidents of domestic violence, 13,459 other assaults, and 88,950 incidents of breaking and entry. The binary-coded variables provide information on whether the respondent was alone during the interview, others who were present, whether the interview was by telephone, whether the respondent refused a telephone interview, the number of persons who lived in the household, whether the respondent owned her home, whether the land use was urban, whether the household the respondent was living in was the same household from the last interview, whether the respondent had moved more than three times in the last five years, and whether an assault, domestic violence incident, rape, breaking and entry, or no crime was reported. Demographic information includes the respondent's education, income, employment during the last six months, marital status at the time of the interview, and whether the respondent was white (or non-white) or Hispanic (or non-Hispanic). Variables coded the same as the NCVS variables include age, respondent's relationship to the offender, type of crime, year and quarter of interview, NCVS control number, and person weight.