“No Help, No Violation/YB”1. In this equality design, test takers were randomly assigned to take the old and new forms of the test. Kin and Kolen (2010) pointed out that population invariance was used to ensure that the scale was fixed across all forms of testing. However, using the non-equivalent groups of common elements design would be more appropriate since non-repeaters and repeaters differ in their capabilities. The use of common or anchor elements will indicate the performance of non-repeaters relative to repeaters (Kolen and Brennan, 2004).2. According to Livingston (2004), the unsmoothed equipercentile equation (USEE) is generally used when the sample size is large. Kim and Kolen (2010) indicated that non-repeaters are more skilled than repeaters; this could create irregularities in the data. Kim and Kolen (2010) pointed out that the unsmoothed method is the most appropriate in the study to avoid the influence of the smoothed equipercentile equation method (used to remove irregularities) on the population invariance. For example, smoothing may produce smaller standard errors than USEE Kolen and Brennan (2004). Therefore, the unsmoothed equipercentile equation method was used.3. Equally weighted expected square root (ewREMSD) was used in the study to give equal weight to all scores and to examine the impact of subgroups on test takers' pass or fail designations. The standardized square root difference (RSD) was used to determine the equation difference between subgroups, where the RSD index compares the equation functions for non-repeaters and repeaters to the total groups. The RWSD compared the subgroups by pairing and assigning them an index and detecting...... half of the sheet ......and 51.8% (n=2905) of the study, while 42% came from the higher SES (n=2699). Table 1 also shows that 51.9% of students are female. Racial/ethnic groups were divided into six categories (White, African American, Hispanic, American Indian, Asian or Pacific Islander, and other races). Whites represent 50.7% (n=2844), while African Americans represent 28% (n=1622). The results revealed that the principal has a high school completion rate of 91.3% and an arrest rate of 6.0% for students before the age of 18. Logistic regression specified that there were several factors that contributed to students' high school completion and number of arrests before the age of majority. 18. The results are displayed in Tables 3 and 4. Only significant variables were included in the analysis. The Hosmer Lemeshow Test for High School Completion indicated an acceptable fit for the data