I've been pondering a question for a while, and I can't figure out the answer. Because it's odd and analytical, I thought I'd talk about it here. It comes from a digital card game I play a bit, but the question applies more broadly.
Suppose you have a deck of cards which has been properly shuffled and dealt from. Some effect or game mechanic instructs a player to look through the deck and pull out any one card whose suit is Spades then shuffle the deck.
Now suppose you are playing the same game on a computer. The same effect or mechanic is used. Because it is on a comuter, the game can show you the player his or her options without revealing the order of the deck. Because the player does not gain any information about the order of the deck, the game does not shuffle the deck after. The deck's order is left exactly the same, save one card has been removed.
The question I've been pondering is, are these two approaches effectively the same? In terms of effective randomness, does removing a card from a randomized deck have the same effect as removing the card then shuffling the deck? If both approaches were used many times in many games, would there be any difference in the overall effect on games and the order cards are drawn in them?
Last week, I demonstrated how the mathematics which go into calculating "correlation scores" is relatively simple. Today, I'd like to look at some of the steps involved to better understand what correlation scores actually mean.
I've been struggling (a lot) with a series of posts I'm trying to write, and I recently realized the problem is I need to start at the beginning. These posts are supposed to be about how "correlation scores" are being misused and abused within the scientific community. The problem is, what are "correlation scores"? That's where we'll begin today.
People familiar with my writing know I have discussed work by a man named Stephan Lewandowsky quite a bit. The short version of the discussion is he has behaved unethically, published false statements and, most importantly generated bogus results by misusing what is relatively simple mathematics.
I'm not the only person to say such, but the discussion has been spread out across many locations over several years. Today, I'd like to start working on collecting the information into a single resource by beginning with a discussion of the gross misuse of simple statistics.
Whatever one may believe about Lewandowsky and his behavior, the indisputable truth is the methodology he relied upon to publish several papers fabricates results because f how he misused it. Results he published are completely and utterly without merit.
My last couple posts have examined how it appears data used in two scientific papers, making up a significant portion of a PhD dissertation by Kirsti Jylha, has been tampered with. I don't want that issue to dominate the discussion though. While data tampering would obviously be a serious problem, I want to remind people this work was complete nonsense even without concerns of data tampering.
In my last post, I asked for help explaining correlations between Rater IDs for people who took a survey and the responses they gave to that survey. The order in which people take a survey should not affect how they respond to the survey, yet according to a data set I was examining, they do.
Today I'd like to go further and show even more inexplicable results. I don't like accusing people of fraud or tampering with data, but I can't come up with any other explanation. Perhaps someone else can help me come up with one.
I do not like making accusations of dishonesty. I have done so plenty of times, but each time I did, I first put significant effort into trying to find an alternative explanation. Today's post is for that. I have encountered data with properties I cannot explain. I am hoping someone can find an explanation for me that isn't, "Someone fabricated data."
Hey guys. It's time to resume the series of posts I'm writing about a series of papers, and a PHD dissertation based on them which got halted because I've been playing too many games of Rock, Paper, Scissors (if you want to know why I've been playing that, see here). Today I will be discussing how not only are the results the authors published based upon a inappropriate methodology, but fail a basic sanity check.
Today I'd like to take a break from my recent topics of discussion and look at an example of why people shold be skeptical of the messaging by global warming advocates. This post isn't about science. I'm not going to argue about any facts or theories. I'm not going to question or put forth facts or evidence.
None of those things matter today. Regardless of what one believes about global warming, everyone should be able to agree on a basic principle: Results should be presented in an accurate manner that does not create a misleading impression of what the results show. And based upon that principle, everyone should be able to agree this display is rubbish:
I'm not questioning the data used to make this display. The data doesn't matter today. What matters today is the data is being displayed in a misleading manner.
Hey guys, as you may have picked up on from my last couple posts, I was fairly sick this week. I'm not completely over it, but I have had the energy to do more than lie around all day doing nothing. Naturally, one of my top priorities has been playing Rock, Paper Scissors (RPS).
I'm not going to re-visit the history leading up to today's post. You can read the last post I wrote on this subject here. The short version is it seems no matter what I do, I keep beating a computer opponent that makes random choices. This shouldn't be possible. The odds of winning, losing or tying in RPS should be 1/3 when one opponent picks options at random.
Today's post is about an update to my methodology and the results it leads to. I've played 10,000 matches after the update, and I have won 3,454 of those matches. That gives me a win rate of 34.54%, a result that is "statistically significant" at the 99% level.