Syndicate content

Your go-to regression specification is biased: here’s the simple way to fix it

Berk Ozler's picture

Today, I am writing about something many of you already know. You’ve probably been hearing about it for 5-10 years. But, you still ignore it. Well, now that the evidence against it has mounted enough and the fix is simple enough, I am here to urge you to tweak your regression specifications in your program evaluations.

Weekly links Feb 9: tracking Ghanaian youth as they age, envying Danish data, coding better, communicating less badly, and more....

David McKenzie's picture
  • DEC has a fantastic lecture series going on at the moment. This week we had Pascaline Dupas. Videos of the talks are online. Of particular interest to our readers, will be her discussion of the techniques used for how they managed to re-interview 95% of Ghanaian youth after 10 years; and of how they messed up asking about labor market outcomes the first time they tried due to the sporadic nature of work for many youth (and something I hadn’t thought about – people working for the government whose payments have been delayed, so are owed back wages, but didn’t actually get paid in the last month).
  • In VoxEU, revealed vs reported preference – when asked if they saved or spent their stimulus payments, people’s answers were qualitatively informative of actual behavior seen from observed spending data; and when asked how much they spent, gives a reasonable measure of average spending propensity – but these questions aren’t so good at capturing which households respond more.

Beyond the trite “I was there” photo: Using photos and videos to communicate your research

David McKenzie's picture

One signature feature of many academic presentations by development economists is the use of photos. Go to a labor or health economics seminar and you will almost never see a photo of a U.S. worker or U.S. family participating in some early childhood program, but go to a development seminar and odds are incredibly high that you will see shiny happy people holding hands. This is often the source of much eye-rolling among non-development economists (and even among ourselves), so I thought I’d speak up a little in defense of the use of photos, as well as share some recent experiences with trying to use them better.

Weekly links Feb 2: hit the beach, develop a country! Female economists, go visit your alma maters! A Stata command round-up, and more...

David McKenzie's picture

What’s new in education research? Impact evaluations and measurement – January 2018 round-up

David Evans's picture
Here is a selected round-up of recent research on education in low- and middle-income countries, with a few findings from high-income countries that I found relevant. This is mostly but not entirely from the “economics of education” literature. If I’m missing recent articles that you’ve found useful, please add them in the comments!

What is education good for?
  • Education saves lives, but only some of them! “Education is strongly associated with better health and longer lives.” But is that mere correlation, or is a causal link? It depends! This review finds no impact on obesity, inconsistent impact on smoking, and “an effect of education on mortality exists in some contexts but not in others, and seems to depend on (i) gender; (ii) the labor market returns to education; (iii) the quality of education; and (iv) whether education affects the quality of individuals’ peers” (Galama, Lleras-Muney, and van Kippersluis).

I just signed my first referee report

Berk Ozler's picture

I once received a referee report for a journal submission that said, “In fact, in my view its contribution to science is negative…” The report continued with comments about how the paper lacked “proper and sound scientific inquiry” and was “…unsuitable for publication pretty much anywhere, I think.” Just in case the four-page assault was not sufficient, the report ended with encouraging the authors to “…move onto the next project.” It was hard to avoid the feeling that the referee was suggesting a career change for us rather than simply giving up on this paper… The paper was subsequently published in the Journal of Health Economics, but the bad taste of receiving that report lingered long afterwards…

Weekly links January 26: learn to machine learn, that wellness program might only help with your multiple testing correction, working beats saving, and more...

David McKenzie's picture

Can predicting successful entrepreneurship go beyond “choose smart guys in their 30s”? Comparing machine learning and expert judge predictions

David McKenzie's picture

Business plan competitions have increasingly become one policy option used to identify and support high-growth potential businesses. For example, the World Bank has helped design and support these programs in a number of sub-Saharan African countries, including Côte d’Ivoire, Gabon, Guinea-Bissau, Kenya, Nigeria, Rwanda, Senegal, Somalia, South Sudan, Tanzania, and Uganda. These competitions often attract large numbers of applications, raising the question of how do you identify which business owners are most likely to succeed?

In a recent working paper, Dario Sansone and I compare three different approaches to answering this question, in the context of Nigeria’s YouWiN! program. Nigerians aged 18 to 40 could apply with either a new or existing business. The first year of this program attracted almost 24,000 applications, and the third year over 100,000 applications. After a preliminary screening and scoring, the top 6,000 were invited to a 4-day business plan training workshop, and then could submit business plans, with 1,200 winners each chosen to receive an average of US$50,000 each. We use data from the first year of this program, together with follow-up surveys over three years, to determine how well different approaches would do in predicting which entrants will have the most successful businesses.

Pages