Skeptics with a K: Episode #148


Internet time, Light Night, brain-boosting orange juice, and seminiferous tubules. Plus decapsulated testes, learning to swim, disappointing books, and two hours of pornography. Still buffering, it’s Skeptics with a K.

Play
  1. #1 by Tom Williamson on May 21, 2015 - 16:22

    Surprised a certain Linus Pauling didn’t get a mention in the orange juice story.

  2. #2 by Mr56 on May 29, 2015 - 10:10

    On p values (34 minutes in, ish) – a p value of 0.05 doesn’t mean a 95% chance that the null hypothesis is false, it means that the probability of the result would be 5% if the null hypothesis were true. This is nitpicky, but quite an important distinction.

    P values are based on the false positive rate (1-specificity). We can think of this as the proportion of variables for which the null hypothesis is true which we can expect to appear significant for a given threshold of significance. If we have a large number of variables, all of which are “null” (no causal relation to our dependent variable of interest), we can expect 5% of them to be significant at p<0.05. This means that 95% is actually the proportion of "null" variables which we correctly identify as null.

    What Marsh refers to is the positive predictive value (or precision) of the test, which we can derive from a p value if we also know the true positive rate (sensitivity or power of test) and the prior probability of our null and alternative hypotheses using Bayes theorem, awkward to write in comments box so here's some LaTeX – http://imgur.com/9iNIHzQ

  3. #3 by Mr56 on May 30, 2015 - 09:08

    Though having said that, I made a mistake in that image and it’s going to drive me up the pole if I don’t correct it – http://imgur.com/ZCARtfj

  4. #4 by Declan on May 31, 2015 - 03:56

    Your patron complaining about an access ramp sounds like a cracker.

    As a fully grown male electric wheelchair user I suspect I’m a bit heavier than his daughter who he’s happy to carry about.

    If only Glasgow Skeptics would hold their meetings in an accessible venue. I’ve been asking them for literally years and no fucks have been given on any day. According to them, there is nowhere the right size in Britain’s third city that has either a lack of stairs or a lift.

    I’ve missed dozens of talks including those by Marsh which – as a long-time SWAK lover – I’ve surely have enjoyed.

    I also miss out on meeting like minded skeptics. Instead, as an MS sufferer, I do get the chance to meet like minded demyelinated people in charities who can provide me with reflexology, aromatherapy, hyperbaric therapy and more.

    It sucks. It really fucking sucks.

    So, well done to the MSS for putting a ramp in. If you have any influence over at Glasgow then please ask them to get it together – they’ve stopped answering my polite emails.

(will not be published)