As I currently am the NPM for PISA in Colombia, I must assist to several meetings dealing with the proper implementation of this assessment in my country. Few of them are devoted to the analysis of this kind of data (coming from IRT models). As usual, OECD has hired organizations with high technical standards. The … Sigue leyendo 3PL models viewed through the lens of total probability theorem (updated)
Computing Sample Size for Variance Estimation
The R package samplesize4surveys contains functions that allow to calculate sample sizes for estimating proportions, means, difference of proportions and even difference of two means. It also permits the calculation of sample error and power level for a fixed sample size.Here four functions are introduced for the estimation of a population variance and for conducting … Sigue leyendo Computing Sample Size for Variance Estimation
Highlighting R code for the web
When blogging about statistics and R, it is very useful to differentiate the body text to R code. I used to manage this issue by highlighting the code and pretty-R was a valuable instrument from Revolutions Analytics to accomplish this. However, as you may know, Microsoft acquired that company, and now this feature (dressing R … Sigue leyendo Highlighting R code for the web
How important is that variable?
When modeling any phenomena by including explanatory variables that highly relates the variable of interest, one question arises: which of the auxiliary variables have a higher influence on the response? I am not writing about significance testing or something like this. I am just thinking like a researcher who wants to know the ranking of … Sigue leyendo How important is that variable?
Lord’s Paradox in R
In an article called A Paradox in the Interpretation of Group Comparisons published in Psychological Bulletin, Lord (1967) made famous the following controversial story:A university is interested in investigating the effects of the nutritional diet its students consume in the campus restaurant. Various types of data were collected including the weight of each student in … Sigue leyendo Lord’s Paradox in R
Intercept or not? That’s the question!
My current passion is statistical modeling. While each model requires the researcher to make a proper contextualization of the problem he/she is addressing, which means that no model is equal to another, there is a common question that the researcher should answer before estimating model parameters.Do I fit the model with an intercept or not?While … Sigue leyendo Intercept or not? That’s the question!
Data Literacy
Once again I have decided to pimp my blog. This time is a significant change: the name. This blog began a long time ago. It was 2006; I was 22-year-old, and I was enrolled in a Master of Science in Statistics. I had plenty of doubts about statistics, data science, and uncertainty (fortunately, some of … Sigue leyendo Data Literacy
Sublime Text 3: an alternative to RStudio
It was a Saturday morning; I was lecturing my students of my Item Response Theory class when I decided to run some R scripts to introduce my students with the JAGS syntax and the estimation of parameters in a Bayesian logistic regression setup.As it was usual, I opened RStudio because it was my favorite R … Sigue leyendo Sublime Text 3: an alternative to RStudio
Multilevel Modeling of Educational Data using R (Part 1)
Linear models fail to recognize the effect of clustering due to intraclass correlation accurately. However, under some scenarios force you to take into account that units are clustered into subgroups that at the same time are nested within larger groups. The typical example is the analysis of standardized tests, where students are grouped in schools, … Sigue leyendo Multilevel Modeling of Educational Data using R (Part 1)
#PredictiveCOL – Forecasting Colombia’s peace plebiscite (final update)
For sure, this is the more exciting forecast I have ever done. On one hand, I am Colombian guy, and I really want to live in a peaceful country, and I do want a better place for raising my children. On the other hand, I am very serious when it comes to forecasting.Maybe you have … Sigue leyendo #PredictiveCOL – Forecasting Colombia’s peace plebiscite (final update)
My talk in Bogotá – Pvalues: use and abuse
Did you know that American Statistical Association (ASA) made a disclaimer about the proper use of p-values? Moreover, ASA (the oldest scientific association in the USA) claimed that: P-values can indicate how incompatible the data are with a specified statistical model. P-values do not measure the probability that the studied hypothesis is true, or the … Sigue leyendo My talk in Bogotá – Pvalues: use and abuse
My talk in Sincelejo – Small area estimation and multiple imputation
My second talk in Sincelejo deals with fascinating topics: Statistical methods in education in conjunction with sample surveys and small area estimation. I am leading this research since last year, and the results are very consistent.Maybe the future of the assessment of education will rest on this kind of predictive methods. In fact, the use … Sigue leyendo My talk in Sincelejo – Small area estimation and multiple imputation
Muestreo, encuestas y estadísticas oficiales 