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

The following figure shows the probability distributions of vote intentions for the main candidates after distributing the stock of undecided voters. As Marina (PSB) is getting back to her track, a question that comes to light is whether Dilma will get more votes than the sum of the others, and what is the probability that she will take it all without a runoff.

Based on the latest polls and simulations (100k) her chances of avoiding a runoff are not that great. There is a 98% chance of seeing a runoff between Dilma and Marina as indicated in the bottom line in graph below. However, if she gains this (most likely) proportion of the undecided voters and “steal” a few more from the other candidates, then that will increase her probability of winning even in the first round.

To make it more concrete, in other to avoid a runoff with Marina, Dilma needs to hold a plurality of the late deciders (which is theoretically likely as the undecideds tend to preserve the status quo) and soak up around 3% from the other candidates. Not much but it would end up being a 50/50 chance then.

**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...