This paper proposes a scaled difference chi-square test statistic for moment structure analysis. Satorra and Bentler (1994) introduced a family of scaling corrections to improve the chi-square approximation of goodness-of-fit test statistics in small samples, large models, and nonnormal data. For structural equations models, Satorra-Bentler (SB) scaling corrections are available in standard software. However, when testing restrictions implied by a null model on a less restricted model, the difference between two SB-scaled test statistics does not yield the correct SB scaled difference test statistic. Satorra (1999) developed a formula for scaling the difference test statistic but it has practical limitations due to heavy computations. The purpose of this paper is to provide an easy way to compute the scaled difference chi-square statistic from the scaled goodness-of-fit test statistics of two nested models. A Monte Carlo study is provided to illustrate the performance of the competing statistics. The paper describes goodness-of-fit tests in weighted least squares analysis and the corresponding SB scaling corrections. It then presents a procedure for computing the SB scaled difference test statistic. The paper concludes with an illustration using a regression model with errors in variables. The results show that the SB scaled difference test statistic performs better than alternative robust test statistics in small samples and models with large degrees of freedom. The paper also discusses the application of the procedure to various modeling settings and estimation methods. The results indicate that the SB scaled difference test statistic is a useful tool for evaluating specific restrictions in moment structure analysis.This paper proposes a scaled difference chi-square test statistic for moment structure analysis. Satorra and Bentler (1994) introduced a family of scaling corrections to improve the chi-square approximation of goodness-of-fit test statistics in small samples, large models, and nonnormal data. For structural equations models, Satorra-Bentler (SB) scaling corrections are available in standard software. However, when testing restrictions implied by a null model on a less restricted model, the difference between two SB-scaled test statistics does not yield the correct SB scaled difference test statistic. Satorra (1999) developed a formula for scaling the difference test statistic but it has practical limitations due to heavy computations. The purpose of this paper is to provide an easy way to compute the scaled difference chi-square statistic from the scaled goodness-of-fit test statistics of two nested models. A Monte Carlo study is provided to illustrate the performance of the competing statistics. The paper describes goodness-of-fit tests in weighted least squares analysis and the corresponding SB scaling corrections. It then presents a procedure for computing the SB scaled difference test statistic. The paper concludes with an illustration using a regression model with errors in variables. The results show that the SB scaled difference test statistic performs better than alternative robust test statistics in small samples and models with large degrees of freedom. The paper also discusses the application of the procedure to various modeling settings and estimation methods. The results indicate that the SB scaled difference test statistic is a useful tool for evaluating specific restrictions in moment structure analysis.