Psychologists and organizational scientists and others interested in measurement have long been concerned about the reliability and validity of instruments that are used with different groups and in different situations. In the past several decades, the increased globalization of many business enterprises and other institutions has resulted in the need and desire to use research instruments with individuals in different cultures. Most major consulting fi rms with practices that include survey research and the assessment of human potential work in countries in multicultural and multilingual contexts. Researchers are also interested in extending their ideas and theories beyond the U.S. culture in which much of our psychological research has been conducted. The major assumption, often untested, is that individuals with the same observed score on some measuring device have the same standing on the construct that is the target of measurement. However, differences (e.g., in culture, in language) in the populations being measured necessitate examining the degree to which the instrument measures the same construct across these groups. Test equivalence (alternatively, measurement equivalence/invariance) is recognized as an important concern for different cultural or gender groups even when members of these groups use the same language, highlighting the fact that nonequivalence can occur along a wide variety of dimensions. More formally defi ned, measurement invariance means that individuals whose standing on some construct is equivalent receive the same observed scores on a measure regardless of group membership or status.