Today I was giving a lecture on sample surveys and observational studies. When I was saying that surveys involving people are only observational and do not take part into the experimental world, some people refused to accept that fact. They argued that some researchers actually do experiments with people in the context of public policy. … Sigue leyendo Why we do not experiment with people in surveys?
Common support graphics in propensity score matching (using ggplot2)
Common support is a must check when doing impact evaluation of public policies (or - more widely - when verifying the causation of some factors over a population). The seminal paper of Rosenbaum and Rubin (1983) defines the propensity score as a measure of balance. Moreover, when doing matching, we must assure that propensity scores … Sigue leyendo Common support graphics in propensity score matching (using ggplot2)
Proper Inference in Public Policy Evaluation
I know, I know... Did you miss me alot? I did miss you.This time I am going to write about a the role of the statistician in Public Policy evaluation. This have captured my attention during the last four years. This is what I do in my consulting at DNP. It is not easy but it … Sigue leyendo Proper Inference in Public Policy Evaluation
Propensity Score Matching in R (My first post in blogger)
My first post in blogger is about Propensity Score Matching (PSM) in R. In this post I will introduce the R packages MatchIt and Zelig. The first one is devoted to perform different PSM algorithms and the other one is used in order to estimate the average treatment effect (ATE) and the effect of the … Sigue leyendo Propensity Score Matching in R (My first post in blogger)
Our Talk in Lima
In this talk, we want to introduce the study of Small Area Estimation (SAE) by means of demographic and some simple statistical methodologies. The example of interest is the estimation of the size of Chocó (one of the poorest departments in Colombia). Enjoy it!
My talk in Cartagena
In these slides you will find my talk about design-unbiased estimation of gross flows that take into account the complex sample along with a two-stage Markov Chain model to describe the nonresponse process.
Our poster in CLAPEM
In this poster we introduce the bayesian modeling of the Gini coefficient per locality in Bogotá by using a Beta regressión. R-codes are available after requesting to the first author. Enjoy it!
Removing data from Workspace in RStudio (in MAC)
In order to remove the data saved (maybe by mistake) in your workspace from RStudio, you gotta find the route in the first message that you can see when opening Rstuido. For example, in my case I can read the following sentence when opening the program: Workspace loaded from ~/.RData. Then, open the terminal and write the … Sigue leyendo Removing data from Workspace in RStudio (in MAC)
My talk in Bogotá
In this talk we consider the problem of estimating the Gini coefficient having into account the sampling weights induced by a complex sampling design. We carry out several Monte Carlo simulations and found that the estimator is design-unbiased under the considered scenarios.
#PredictiveFIFA (Final)
Today is the final match for the first place of the FIFA 2014 World Cup. The match is Argentina vs. Germany. The probabilities of the final results are shown in the following plot.The most likely scores are shown in the following chart (probabilities in percentage are shown inside each cell):Make your bets! Yours truly,Andrés Gutiérrez (@psirusteam) & Alex Zambrano (@alexjzc).
The success of #PredictiveCOL
#PredictiveCOL not just predicted the winner (Santos), but also we were so close to the final values. This was the most accurate methodology in the Colombian presidential election.This is a not a long story. Initially, we wanted to create a predictive model in order to involve young students of statistics in the role of this … Sigue leyendo The success of #PredictiveCOL
#PredictiveCOL – Final prediction
Adhesions are ready: Ramírez is now supporting Zuluaga and López is supporting Santos. Peñalosa has given freedom to his voters. However, there is something interesting that can change the future of the election: Santos voters were less than voters of Unidad National voters to the congress. That is somehow explained because the abstention in the … Sigue leyendo #PredictiveCOL – Final prediction
Muestreo, encuestas y estadísticas oficiales 