Impact Evaluation of Charter School Strategies--Student, Parent, Principal, and Authorizer Survey (KI)

u. s. dEPARTMENT OF eDUCATION

institute of education sciences

National Center for Education Evaluation and regional assistance

to: Rachel Potter, Brian Harris-Kojetin

from: Marsha Silverberg

subject: Request To Increase Incentives: Evaluation of the Impact of Charter

School Strategies (OMB# 1850-0799)

date: 4/20/2007

This memo requests approval to increase the parent/student incentives currently in use as part of the Charter School Impact Study, the first large-scale randomized trial of charter schools ever conducted.

Current Approved Plan for Incentives

The parent and student surveys are conducted by phone (usually at the same time) and each is estimated to take 15 minutes to complete. The surveys are an important source of outcome measures, such as satisfaction with school, school safety, time spent on homework, student behaviors, and parent involvement. As approved by OMB on 3/10/2006, a modest payment of $10 is sent to the parent of each sample member if they complete the phone interview.¹

Proposed Change and Justification

We are toward the end of the final year of the surveys. We would like to increase the payment to $20, to aid in our achieving acceptable response rates and, particularly, to attempt to close the gap between Treatment and Control group members in their responses.

Current Survey Response Rates

	Treatment Group	Control Group	Overall Sample
Parent Survey	78%	72%	75%
Student Survey	71%	64%	68%

As you know, the greater the difference in response rates between the Treatment and Control groups, the more it undermines the analytic advantages of the random assignment. The difference is currently statistically significant.

We propose to offer the higher payment to both the Treatment and Control groups. Because more control group members have not responded, we believe we can bring the response rates for the two groups closer together. In addition, we expect the increased incentive to help us achieve overall response rates of above 80 percent.

We strongly believe that this is the best option for increasing the response rates in this very important study.

We have approximately one month left to be able to reach sample members before school vacations interfere with our contacting the families. We therefore would like to implement the revised incentives as soon as possible so they can have maximum effect.

We look forward to hearing from you soon.

1 During the approval process, you had inquired about whether we could pre-pay the incentive, but we described the challenges of doing so (this is not a mail survey so the pre-payment and the completion of the survey could be weeks apart, about 30% of the addresses we have are inaccurate, etc).

2