Syndicate content

Recent comments

  • Reply to: Weekly links April 17: Reducing open defecation, pre-publication replication, free TORs, and so much more   1 week 9 hours ago

    Our team has produced videos on toilet building in India. Check them out here:

    and short versions here:

  • Reply to: Tips for Randomization in the Wild: Adding a Waitlist   1 week 1 day ago

    Thanks a ton, David.

    I will take a look at this.

  • Reply to: Tips for Randomization in the Wild: Adding a Waitlist   1 week 1 day ago
    There are two issues here:
    1) How to ensure you don't lose your whole control group by having them win in the next drawing;
    2) How to deal with multiple lotteries in the analysis.

    For the second point I blogged about this a while back:

    On the first point, it really depends how popular your program is - if you have 1000 applicants for 200 positions, then even if your control group reapplies in the next round, most of them still won't win, and you are fine provided you deal with point 2). If on the other hand there isn't much demand for the program, and everyone in the control group wins in the second drawing, you are much more stuck. Then standard methods to try to boost application rates are your best approach.
  • Reply to: Tips for Randomization in the Wild: Adding a Waitlist   1 week 2 days ago

    Dear David,

    I am faced with the following situation:

    Courses (Electrical work and air condition repairs) are to start in June 2015. Duration is three months. Eligible applicants are divided into treatment, waitlist and control groups. This is all fine. Idea is to assess the short-term and long-term impacts.

    But those who are now in the control group can not be prevented from applying again 3 months down the line when new batch/ course begins. This implies that a portion of current control/ waitlist group might actually get enrolled in the courses.

    How do I think of impact evaluation? Your thoughts?

    Thank you so much,

  • Reply to: Presenting to policy vs. academic audiences: some thoughts   1 week 4 days ago

    Translating research and evidence into the language policy makers understand is really a difficult act particularly if you are use to academic discourse. In that sense this is very useful set of tips that should guide anyone attempting to attract the attention of policy makers. From my experience I noted two things that are essential in the preparation to present process.
    1. Understand the possible make up of the audience and anticipate their dominant position on the subject. If the evidence you are presenting will dislodge the dominant position the presentation should seek to address the issue but preserve the constituency's integrity as holding an alternative view
    2. Some words mean different things in different contexts particularly when different disciplines will have interest in the policy proposition. It is important to research the key words that will be used to present the policy proposition to be sure that they don't mean different things to different people. If so, use pictorial illustrations to re-enforce the conceptual understanding ofthe policy proposition.
    One question: How do you deal with presenting evidence to an audience who are diametrically opposed to a third way when the alternatives they hold is stack against the evidence you presenting though your external validity stacks up nicely