Content area
Full text
Structural equation modeling (SEM) is by far the best known and most widely used path modeling technique in the international business literature. However, recently international business researchers have begun to use a lesser known path modeling technique called partial least squares (PLS). PLS offers some advantages over SEM such as lower sample size requirements, easier testing of moderating relationships, and built-in capability to handle formative indicators which may explain the increased use by international business researchers. We examine the use of PLS in the international business literature, and the potential of a new path modeling technique called generalized structured component analysis (GeSCA) for international business research. We find mixed support for some of the commonly cited reasons for using PLS over SEM in the international business literature, but do find support for the use of PLS when sample sizes are not large enough for the use of SEM. Finally, we discuss GeSCA 's ability to handle multi-group analysis which may make it an attractive alternative over PLS for international business researchers who are using small sample sizes with data from multiple countries.
As pointed out in Hult et al. (2006), structural equation modeling (SEM) has become increasingly popular in the international business literature. The use of structural equation modeling has many well known advantages over other techniques such as standard regression analysis, as it allows for estimation and evaluation of an entire conceptual model rather than mere testing of individual hypotheses. Other advantages include the capability of estimating measurement error. One particular advantage for SEM in international business literature pointed out by Huit, et al. (2006) is the ability to compare models across groups, a useful feature for research that involves samples from multiple countries or cultures.
A lesser known path modeling technique is partial least squares (PLS). A method similar to SEM, Goodhue et al. (2006) find PLS to be widely used in the information systems but used only sparingly in other disciplines within management. However, a recent review by Henseler, et al. (2009) finds a growing use of PLS in the international marketing literature including several marketing studies published in top tier international business journals. PLS offers several potential advantages to international business researchers such as the smaller sample size requirements...