Math 216: Statistics for Engineering

"anyqs" Where are they getting the data for the music? Most listened to on radio? Pandora? Youtube searches? Also, what does the size of each square represent?

anyqs Is there any definition to the points above and below the "x-axis"? Were these the Top 10 chart hits for these various years, or where did these songs come from? In my opinion, there is a strong lacking of representation for popular country in recent years, as country music has gained popularity in the past decade and a half, or so. Finally, where are the definitions for these genres coming from? For example, I'm not entirely sure I'd classify Rihanna as an R&B musician.

*By having the size of the dot represent the amount of times it was favorited and its location on the y-axis represent its popularity aren't you factoring in how well liked the song is multiple times? How do you differentiate between pop and vocal pop, or any two genres for that instance? Can a song be counted in multiple genres? anyqs

That's a pretty nice segmented bar chart on the right.

anyqs: I would like to know how big the sample size was. Also, how many of the participants are actual college students? I'd like to see the data on purely college students.

anyqs: I would definitely like to see some more info on this, the things mentioned above as well as what N/A actually means. Does it mean non drinker? Also I'm guessing that they did not poll anyone under 21. I think there's more non-drinkers than drinkers under 21 but including that group would certainly change things (most likely lessen the wine numbers). Finally, it's not a big deal but the 36% for beer in 2011 appears higher up on the graph than the 36% in 2005.

Worldwide locations and sales of Starbucks and McDonalds

anyqs Is the growth of Starbucks in multiple countries similar to what McDonald's growth was earlier? If so, how closely do the growths match, and can we expect Starbucks to eventually be as ubiquitous as McDonalds?

anyqs The size of each bubble is confusing. The size of the ones for McDonald's and Starbuck's are very similar, but if looked at closely, are actually different. This leads to questions about the relative presence of each corporation in each region. Also the range that is covered by the McDonald's circles are greater than that of Starbuck's. I know that this visualization is just to show the relativity in size between the two companies, but the information given is hard to translate. My question is, did they make the circles similar on purpose to show the similarities between the spread of the companies, or was it just because the overall range of Starbuck's presence was smaller than McDonald's?

Subjective

Probability:  This article uses mainly the axiomatic notion of probability but touches on the subjective and empirical notions as well. 

Empirical Probability, its eggselent!!

anyqs Simple question really. What size did the designer of this chart intend it to be? It would have to be pasted onto the moon for anybody to be able to read the font. #thinkofyouraudience

anyqs Do the bubbles in the middle that account for the average national debt of the economy take anything else into account? For example, the percentage of GDP that the national debt is would be a better statistic, in my opinion.

Why are straws included in the most loved things at McDonalds? Wouldn't straws be included in Shakes? Although I guess you can eat a shake with a spoon :P Secondly, McDonalds is ubiquitous. How can they make conclusions about customer's "loyalty" when some people may not even have a chipotle, the restaurant with the lowest "loyalty", near them? anyqs

anyqs I'm curious about the socioeconomic status of the customers and how they order off the menu. From my experience as a McDonald's employee, the lower-income bracket orders off the dollar menu, while families order value-meals and kids-meals, but that's just personal observations. I am curious to see if there is an actual relationship between the two.

anyqs Im curious as how they can even begin to compare McDonalds and Chipotle in the first place? It would have been easier for them to just compare them to eating at a non fast food restaurant than a specific one. SOme of the people sampled might not even enjoy chipotle. Also, I dont understand why the hot sauce portion is even included in the data. It doesn't seem to correlate with the rest of the data.

anyqs How has the tree distribution has changed since 2002? It would be valuable to see areas of recent over-logging in red and areas of new growth in a lighter green.

anyqs This visualization is pretty interesting however I feel its lacking something to compare it to. I wonder how this tree distribution differs from the pre-industrial revolution distribution? Is today's tree distribution worse than before because of pollution and over-foresting? I also agree with Taylor, I think a different color like red to show recent over-logging would be very valuable to the viewer. anyqs

anyqs I wonder how the distribution of trees in the North West would change if we counted trees, not Biomass in tonnes, since so many of the trees there are large Redwoods which are considerably heavier trees due to their size.

My professor showed this video in my Computer Graphics class. Had to share.

A little trippy, and very interesting.

1960-1980... Can't keep up!

Statistically shows who should be considered the greatest basketball players of all time based on different accomplishments.

"anyqs" This is a very cool way to see how players from the past rack up to one another. One of my questions is how did they come up with a a methodology to rank the award achievement points, and do they believe this method can be used to rank all players versus one another? It seems like using this method, guys who have played with multiple championship teams who are not considered stars could then rank really highly, even though they might not have played a huge role in the championships won (NBA championships are the most achievement points). If all the NBA players were put on this chart, then some people could be mislead, as a guy like Charles Barkley could rank lower than say Derek Fisher, even though Fisher would is not considered on the same star level as Barkley.

anyqs How was the scoring of the achievement decided? For example, why is the pointage for Playoff Appearances 0? And it seems like there's a significant penalty for people who've never won a championship, despite their skill level. Is it fair to discount a player's all time greatness, if they were never on a team good enough to win a championship? Like John Stockton, one of the greatest point guards of all time. Leads the league in career assists by over 4000 (with 15,000+), but is given a very low ranking for his skill and effect on the game, because of his lack of rings. There's an odd skew, and while championship rings are a massive deal, they're not everything.

For decades, the World Database of Happiness has tracked how happy people are.

anyqs Immediately when I see statistics on human emotions, I find myself asking, rather skeptically, how do they know how happy someone is? If I say that I am the highest level of happiness today, i.e. a 4, and then tomorrow I win the lottery, then I'm still stuck saying I'm a 4. I wonder what the statistics would have looked like if they gave their populations a greater range to choose from than 1 to 4? Perhaps 1 to 100? Would the people have rated themselves happier or less happy? Does forcing the sampling population into discrete values with a resolution of only four values affect how they respond? Further, the graph mentions that some countries weren't even surveyed some years... Perhaps they weren't surveyed during the worst years when everyone would have been very unhappy? \ The creators also gave "suggestions" as to why the counties got happier or sadder. For example, they believe that France became sadder as a whole country because we renamed Freedom Fries back to French Fries.. Really??? Is this website meant to give statistics or just to be funny? Consider the title, its even a joke. anyqs

xkcd delivers another great data visualization, this time of the ocean depths

The illustration may look less than scientific, but the concept and the presentation are really cool.

I'm not much of a gamer but I found this interesting. Note the inferred correlations between juvenile crime and videogame usage in the lower charts.

Subjective probability, however simulations can be run large numbers of times to give a more empirically subjective probability.

I know its not from the news but I couldn't resist. 50%: empirical 89%: subjective

So, so true...

This has something to do with that... http://joedullblog.files.wordpress.com/2011/11/usb-4th-dimension1.gif

Nuclear Explosions since 1945

anyqs It is interesting to note the relationship between the locations of the nuclear explosions and the population densities around those regions. Furthermore, it seems that there is also a relationship between the frequency of nuclear detonations and how long ago they were detonated (i.e. there were several nuclear detonations 50 years ago, but just 2 in the last 10 years). Lastly, it is interesting to see that the UK and France conducted the majority of their nuclear explosions in their colonies during the 1960s and 1970s, away from their population.