7. Morgenstern and coworkers wish to test the efficacy of Intensive Care Management (ICM) for reducing substance abuse in women receiving Temporary Assistance for Needy Families (TANF). Women were recruited from welfare offices in urban Essex County, New Jersey. Welfare workers screened all women who applied for TANF benefits. Only women who 1) have been diagnosed with substance dependence 2) were TANF eligible, 3) entered New Jersey's welfare-to-work program, and 4) were able to speak English well enough to complete an interval were eligible for the study. All eligible women applying for TANF support between September 1999 and May 2002 were asked to participate in the study. A total of 302 women were recruited into the study; this was 95.9% of of eligible participants. Study subjects were randomly assigned to one of two treatments: 1) Intensive Care Management (ICM) and 2) Usual Care. After 15 months, alcohol dependence was measured using the Addiction Severity Index (low scores indicate high dependence), yielding the following data: ICM Usual Care n 161 141 221.53 85.92 231.82 67.15 (a) (4pts) Which of the following procedures is most appropriate for testing the null hypothesis of equality of treatment means? O One-Sample t-test O Paired t-test O Two-Sample t-test (b) (4pts) Suppose that we found that there are outliers in the data. Then which of the following procedures is most appropriate for testing treatment impact? O One-Sample t-test Paired t-test Wilcoxon Signed-Rank O OO Two-Sample t-test Wilcoxon Rank-Sum