Final Supporting Statement B_Kansas

Permanency Innovations Initiative (PII)

Pretesting of Evaluation Surveys

(OMB 0970‑0355)

Supporting Statement Part B

September 2011

B. STATISTICAL METHODS (USED FOR COLLECTION OF INFORMATION EMPLOYING STATISTICAL METHODS)

B.1. Respondent Universe and Sampling Methods

The sample for the pretest will include 60 families that are identified during the baseline pretest period (December 2011 – February 2012) as meeting the eligibility criteria (child age 3-18 has a Serious Emotional Disturbance or SED and is placed in foster care) for the intervention. Half the families will be in the treatment group (receive the intervention) and half in the control group (receive services as usual).

B.2. Procedures for the Collection of Information

Sampling Procedures

The 60 families will comprise a convenience sample identified at the four participating private providers in five Kansas regions and then randomly assigned to treatment or control conditions. The provider agencies will obtain consent from the parents for participating in the pretest.

Data Collection Procedures

The data collection period for the pretest will begin in December 2011 and conclude in August 2012. The battery of instruments will be administered in its entirety. The first administration will be when a child is placed in foster care, then there will be a follow-up administration 4-6 months later. Data will be collected by trained assessors for the battery. The assessments include direct interviews with and observations of parents, as well as interviews with the families’ caseworkers and review of their case files. We estimate that it will take approximately 1.75 hours per family to complete the assessment battery, and .5 hours per caseworker interview.

B.3. Methods to Maximize Response Rates and Deal with Nonresponse

We do not anticipate any major problems with response rate and nonresponse for this pretest. The private agencies are highly motivated to participate in this intervention, and have been involved from the beginning in selecting instruments and procedures. We will continue selecting the sample until 60 families are participating.

B.4. Test of Procedures or Methods to be Undertaken

The University of Kansas will pretest new procedures for administering a battery of instruments on child functioning, parenting skills, and family readiness for reunification. The focus for the pretest will be on respondent receptivity, how well procedures work, timings, administration issues, and training issues. Any difficulties we encounter with respect to our procedures, materials, or instruments will be discussed with the evaluation contractor, and suggested revisions to the evaluation plan will be outlined. Information from the pretest will be used in data collector training for the full evaluation.

B.5. Individuals Consulted on Statistical Aspects and Individuals Collecting and/or Analyzing Data

The team is led by Maria Woolverton, federal project officer; Andrea Sedlak, project director; and Mark Testa, principal investigator. Additional staff consulted on statistical issues at Westat include David Judkins, senior statistician.