**Daniel MarcelinoDaniel Marcelino » R**, and kindly contributed to R-bloggers)

Election is coming soon in Brazil and this is told to be The Election for both the ruling party and the opposition. However, I don’t believe to see any surprise in the reelection plans of the incumbent president, Dilma Rousseff, though all past demonstrations, poorly on economic scorecard, and the atypical election where the two main adversary candidates will eventually cooperate in an run-off. If so, they may ultimately take PT off from the Presidency.

The following chart is based on the last four polls available, which were stockpiled into a “super-poll” to calculate these distributions. I tested what is the probability for Dilma has more than whoever comes second and that her own support is higher than 35%. The Dirichlet model returns a high probability that she holds at least 35% of the electorate. Actually, the stochastic median is on 40%. This quantity can be directly compared to the others who have less than 20%.

Whether the “leftist bonanza” is getting to the end in the government after an eventually second term of Dilma, it is important to note that in the Congress parties appealing towards the left are getting popular and their hungriness for seats won’t stop in the next election. Therefore, the left may continuous gain power in the Legislative while the right and the centre lose them. As the trend shown in the next picture.

**leave a comment**for the author, please follow the link and comment on their blog:

**Daniel MarcelinoDaniel Marcelino » R**.

R-bloggers.com offers

**daily e-mail updates**about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...