You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Hey Statistics experts, I cannot think of the name for it but what would be the inverse of "survivor bias"? As in, it's not "you think the poison isn't deadly because you only see survivors" but "you think the fertilizer works because you don't see the dead plants".
Or actually, more like "you think the fertilizer works because you only see the tall plants". As in, all the plants are surviving, but you only see the tallest plants and assume the fertilizer is working, rather than seeing all the normal height plants to see it's not working.
How about: The Simpleton's Fallacy or Argument from Ignorance? http://utminers.utep.edu/omwilliamson/ENGL1311/fallacies.htm …
No, not quite. That says you assume something is false because you lack the knowledge to know it's false. It's similar but this is more like you assume something is working because you only see where it's working? I guess it's a specific class of that kind of fallacy.
Sounds like a form of Confirmation Bias. You expect the fertilizer to help plants grow, so you over-value plants that have grown tall in observations.
Could also be a form of Simpson's Paradox, where the way you aggregate samples can cause important differences to disappear.
Observation bias?
Well, isn't survivor bias a kind of observation bias? But I think observation bias is someone willfully ignoring the whole observable set, whereas survivor bias is that you actually can't see the whole set. But observation bias might fit better.
Poor sampling?
Type I Error, I believe. "More simply stated, a type I error is to falsely infer the existence of something that is not there (conforming to common belief with false information)" https://en.m.wikipedia.org/wiki/Type_I_and_type_II_errors …
In the case of the grass, it would be biased sampling with no effort made towards establishing meaningful averages (mean, median, and mode). A bell curve of grass height could be created, along with the standard deviation (the tall grass being largely on the outer right edge).
Victim Bias.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
