TheJakartaPost
Please Update your browser
Your browser is out of date, and may not be compatible with our website. A list of the most popular web browsers can be found below.
Just click on the icons to get to the download page.
Polls, quick counts, credibility and reality
While waiting for the final official count from the General Elections Commission (KPU), political party officials, as well as amateur observers, debate about previous polls and quick-count results.
Change Size
Night reader: A local poll administrator (KPPS) uses a smartphone to check ballots during the vote count at Lolu Utara, Palu, Central Sulawesi. (Antara/Basri Marzuki)
I
ndonesians have just finished placing their votes at polling stations across the country — one of the largest democracies in the world. While waiting for the final official count from the General Elections Commission (KPU), political party officials, as well as amateur observers, debate about previous polls and quick-count results.
Those who do not claim victory nor shout in protest are the social scientists, statisticians and research experts as they are the ones who actually understand and can make sense of the data.
Most of the arguments made against pollsters and quick count data would either be that the methodology used is invalid or insufficient to represent the true population (as the studies used are based on samples) and that the institutions conducting these studies were commissioned by malicious groups to mislead public opinion in favor of the opponent.
The first objection has to do with knowledge (or lack thereof) of research and statistics; the second borders between conspiracy theory and being a sore loser.
True statisticians and data scientists understand limitations of figures and command expertise in analyzing and interpreting what the figures mean.
First and foremost, research and poll agencies need to uphold their reputation and credibility by consistently demonstrating their integrity by showing that their results are as close as possible to reality.
Once an institution displays an intentional bias toward one side, it immediately loses this credibility; that side would also fail to understand the reality on which they need to make decisions. Therefore, any company involved in polling or quick counts will try to adhere to the strictest research and statistic standards.
