In the last post, I described some common misconceptions and problems with the use of null-hypothesis significance tests and P-values. In this post, I'll show more common ways that P-values are often misapplied, including how a significant result under alpha = 0.05 can have more than a 50% chance of being wrong.
OpenChannels has a team of dedicated bloggers addressing targeted aspects of ocean planning and management, including communication, technology, ocean uses, and more. Our bloggers are experts in the field, drawing from their own knowledge and experience.
The OpenChannels community can also benefit from your knowledge and experience. We appreciate the diversity of perspectives in this field and welcome the use of OpenChannels for sharing these views. Do you have a perspective on ocean planning you would like to share? We'll help you do that right now: just click the button above and follow the prompts. If you are interested in blogging but have questions, please email Raye Evrard at raye [at] octogroup.org. We look forward to your contribution!
The OpenChannels Team
Calling everything with p < 0.05 "significant" is just plain wrong
The practice of statistics in the sciences often takes the form of drawing scientific conclusions from cargo-cult application of inappropriate or outdated statistical methods, often to the exclusion of prior evidence or plausibility. This has serious consequences for reproducibility and reliability of scientific results. Perhaps the number one issue is the over-reliance and lack of understanding of null-hypothesis significance testing, and blind faith in the reliability of the P-values these tests provide.
By Spencer Showalter
Mark your calendars for 2020—it could be the beginning of the largest dam removal project in American history. While dams in California have been used for generations to stabilize long-term water availability to settlers, their inherent role of restricting flow affects humans and ecosystems downstream. Because of these impacts, four dams in the Klamath River Basin are slated to be removed in a $450 million project that would re-open 500 miles of spawning grounds to coho and Chinook salmon. The gains from the removal could be huge. Reopening spawning grounds would help rebuild depleted salmon fisheries, and higher flow would mean cleaner water with fewer viral infections and toxic algae blooms. Because the future costs of upkeep of the dams represent a net loss to their owner, PacifiCorp, removal would be economically positive in a corporate sense. Additionally, the water and salmon fisheries were historically used by native tribes of the Klamath Basin, including the Yurok and Karuk Tribes, who stand to regain clean water and increased harvests if the dams are removed.
By Samantha Farquhar
Take a breath….and thank the trees.
Now take another breath…..but this time thank the ocean.
Yes, the ocean. It has been estimated that 50% of the global oxygen supply comes from the ocean.
How does the ocean do this? By providing a home to plant-like organisms called phytoplankton.
By Danielle Edelman
A few weeks ago, I found myself sitting behind a table covered in bottles of sea water, pH-test kits, and posters with pictures of pitted and dissolving snail shells. I had a coffee in one hand and a bowl of steamed clams and mussels in the other. As I looked around at the booths next to mine, I spotted a family with two kids. I smiled and asked “would you like to do a science experiment?” The two kids glanced at my booth, then looked away and walked with their parents toward the ice cream stand.
By Katie Keil
On April 26, 2018, the US Food and Drug Administration (FDA) approved an application for a genetically engineered (GE) salmon facility in Indiana, paving the way for “frankenfish” to be commercially produced on US soil for the first time. These “frankenfish”, containing genetic information from three different species, were first demonstrated in 1989 but have had difficulty garnering consumer support.