Causal Design

## Grad Fellow Notes: How to Check If Survey Respondents Are Paying Attention

When companies need to know what their consumer base is thinking, surveying is often the only scalable way to find out this information. Nevertheless, surveys take up a lot of time and can be incredibly boring. As the respondents’ patience gets zapped by the umpteenth question and their willpower dies, they employ coping strategies known as “satisficing”— a fancy way of saying that respondents just try to meet the lowest threshold of acceptability for an answer, rather than making the time to give the best response. This can be seen when questionnaires come back with all answers being “5/5”, “extremely happy”, or other arbitrary patterns that call to question their authenticity and potentially hurt data quality.

CategoriesAnalysis Research Statistics

## Grad Fellow Notes: Interaction Terms in STATA

While using hashtags is simpler than generating the interaction term as a new variable, there is a necessary rule to remember: use the variable prefixes. In Stata, -i.[variable]- indicates that the variable is categorical, and -c.[variable]- indicates a continuous variable. Because the hashtag code assumes the variables in the interaction term are categorical, it is necessary to define numerical variables as numerical with the -c.- prefix.
Wage = β0 + β1Education + β2Minority + β3Education*Minority + ε

## Grad Fellow Notes: STATA Command -inspect-

On a recent project, the client wanted an idea of the skew of each of a large number of variables. The data originated from a satisfaction survey (1=very dissatisfied; 5=very satisfied). On our Excel presentation sheet, we were to choose from the following options to describe the population’s view regarding each variable: right-skewed (generally very dissatisfied), left-skewed (generally very satisfied), U-shaped (most were either very dissatisfied or very satisfied, with few being neutral), or normal-shaped (most were neutral, with few being either very dissatisfied or very satisfied).

## Grad Fellow Notes: Data Science & Development

According to a 2015 report by the UN’s International Telecommunication Union, 2/3rd of global internet users come from the developing world. In some countries, like India, mobile phone use is as high as 75%. These trends are generating large amounts of data, which present a new opportunity for tech-savvy development practitioners. Governments and NGOs can utilize the data to make well-informed decisions and provide more effective services at a cheaper price. The question however, is how to do this.

CategoriesBlog Post Graduate Fellow RCT Research

## Grad Fellow Notes: The Impact of “No Impact” Evaluations

With the steady rise of the number of impact evaluations (IEs) per year, it should come as no surprise that not every single IE will show a positive impact. The authors of “no impact” evaluations will understandably be worried that their work will not be academically published nor be used for public policy. There is, however, still value in such information. Evidence that a particular program does not work paves the way for alternative interventions to happen. Licona (2017) provides several examples where null results in Mexican education programs encouraged the tweaking of aspects such as selection criteria, consolidation of redundant programs, and budget optimization.

## Grad Fellow Notes: STATA Tips

Managing multiple editors in STATA: For this week’s blog post, it seems useful to cover some code I’ve learned for Stata.  This first useful trick allows multiple users who are going to use the same dofile to run that file without having to first customize the filepath code.  By copying the individual usernames and filepaths […]

CategoriesRCT Research sampling Statistics

## Applied Research Challenges: Working with Small Samples

We work with clients who are running poverty interventions in the field. These are not experiments – where the program is designed around an experiment – these are impact evaluations that have to be designed around a development program that has already been designed or is in progress. As such, often times the sample size […]

## Linear Probability Models

Introduction It is often the case in Impact Evaluation that we have a need to analyze binary, qualitative variables such as savings behavior (saves vs. does not save), voting behavior (votes vs. does not vote), or gender (male vs. female). In general, we are interested in whether a condition exists or does not exist, rather […]

## Innovations for Development with Enrique Rubio

I was thrilled to be able to sit down with a friend and colleague, Enrique Rubio, a few weeks ago to talk about some of my personal takes on innovation in development. Take a half out and listen to the resulting Podcast. Enrique’s show is already 7 episodes in, so be sure to add it to your […]

CategoriesCommunity Opinion

## Shift to Emperics

I was just forwarded a Bloomberg article by a good friend along with a note that she finally understood -kinda- what it is we do. Many, my own family included, believe that economists spend their days coming up with theoretical models for what could happen in the market. I’ve spent a fair amount of time trying to explain […]