Research Design
Before starting with data collection, the research team should work with the field team to design and code high frequency checks, as part of the data quality assurance plan.
Depending on whether data is collected in-person or remotely, there are two methods of primary data collection - remote surveys and field surveys.
In phone surveys or computer-assisted telephone interviews (CATI), the enumerator calls the respondent and asks them the questions over telephone. The enumerator enters these responses onto a programmed digital survey, which is then shared electronically with the research team. Phone surveys have 2 major advantages.
Data license agreements (DLA), or data use agreements (DUA) are documents that describe what kind of data is being shared with recipients. A DLA clearly states the purpose and duration of access being provided to the recipient, along with restrictions and security protocols that the recipient of the data must follow. Other contracts, such as a non-disclosure agreement (NDA), may also be used to guarantee confidentiality of sensitive data.
This article covers the procurement process for the data collection agency.
The process of structuring a survey pilot involves agreeing upon the logistics (or practical aspects) of a survey pilot, including duration, approvals, review sessions, and training. In order to conduct a successful pilot, the impact evaluation team (or research team) must discuss each of these aspects in detail to ensure that the sur
Questionnaire translation refers to the process of translating survey instruments (or questionnaires) into all local languages spoken in the study area. It is a vital component of a high quality survey.
A randomized controlled trial (RCT) is a method of impact evaluation in which all eligible units in a sample are randomly assigned to treatment and control groups. The treatment group receives or participates in the program being tested, while the control group does not. Given a sufficiently large number of units, an RCT ensures that the control and treatment groups are equal in both observed and unobserved characteristics, thus ruling out selection bias.