The University of the Philippines School of Statistics (UP STAT) warns the public about “ kalye surveys” and online polls with unclear techniques, urging them to be critical of such audits or studies that may generate biased results. (Photo from the official website of UP Diliman School of Statistics / stat.upd.edu.ph)
MANILA, Philippines — The University of the Philippines School of Statistics (UP STAT) again warned the public about “ kalye surveys” and online polls with unclear techniques, urging them to be critical of such audits or studies that may generate biased results.
The UP STAT called out the “pervasive abuse” of survey methodologies by online content creators who share the output of their analysis on social media.
“We have been observing these practices, including surveys not based on random sampling, such as videos of ‘kalye surveys’ being done by some vloggers and suspicious online surveys, especially on Twitter and Facebook,” the faculty said in a statement Thursday.
READ: Truth in biased documents
The UP STAT also expressed dismay over these creators’ “cavalier disregard” for proper data gathering – and the publication of these suspicious surveys by public relations companies, private individuals, and media organizations despite the hazy methodologies used in the audit.
“The quality of any inference cannot rise above the quality of the methodology it is based upon. Sample selection strategies can generate bias in the data collected in surveys,” it stressed.
READ: Be critical of ‘kalye surveys,’ statisticians warn public
The UP STAT explained that data collection may generate bias when the survey’s sample, or the particular set of people being chosen to answer the survey questionnaires or interviews, favors a specific population segment.
Surveys may also be biased when an interviewer intentionally affects the respondents’ answers.
“Biased methodologies will only give biased results. Thus, we call on the public to be critical of surveys in this respect. Do not immediately accept survey results as they are,” the UP STAT faculty said.
READ: Survey says: Not all pre-election polls are reliable
According to the statisticians, the public must ask questions when encountering survey results, including how the survey’s sample was selected, which sectors of the population are being represented, what events surrounded the period of data gathering, and the survey’s level of confidence, among others.
“We aspire for a statistically literate country that uses surveys for illumination and sound decision-making,” it added.