eurotrash

Eurobricks Dukes
  • Content count

    2050
  • Joined

  • Last visited

1 Follower

About eurotrash

  • Rank
    Put the FUN in funicular

Profile Information

  • Gender
    Male

Extra

  • Country
    Missouri
  • Special Tags 1
    http://www.eurobricks.com/forum/uploads/monthly_10_2013/post-6705-0-65561600-1380833358.png
  • Special Tags 2
    http://www.eurobricks.com/forum/uploads//gallery/album_241/gallery_8966_241_2675.png
  • Special Tags 3
    http://www.eurobricks.com/forum/style_images/flags/townboy.gif

Recent Profile Visitors

1587 profile views
  1. You're very welcome and, of course, if there's anything I can help with then please don't hesitate to reach out to me.
  2. No worries mate! Luckily I get paid to be an applied statistician and mathematician. AND I build things in Lego. So, here’s a MOC to help with the problem. Both charts contain the same amount of data (studs) and I’ve shown the +1/-1 Standard deviation in red and the mean with the black tile. The top chart shows data that is normally distributed and the lower chart shows skewed data. The same amount of tan and red plates straddle the mean but the shape is very different. Top Chart; Mean = 6.5, Standard deviation = 1.5, AVG +1/STDEV = 8, AVG -1/STDEV = 5 Bottom Chart; Mean is 8.5, Standard Deviation = broken and meaningless because the data asymmetric, but AVG +1/STDEV = 9, AVG -1/STDEV = 7. So the usual methods for calculating the STDEV just do not work for skewed data. However if we can mathematically manipulate the shape of that lower chart (using a formula) into something that resembles the top chart then we can calculate the STDEV thresholds and then using the same formula backwards we can calculate the thresholds for the skewed data. Luckily Im a lazy applied statistician so I use Excel to calculate the =skew()* of the data then create a simple power function like y=x^N and ‘Goal seek’ to find me a legitimate value of N that gives me a zero skew data set. Then I calculate STDEV as for ‘normally distributed data’ work out the thresholds (in this case the first 9 plates and the last 9 plates would be outside of +1/-1 STDEV . Then I can determine where those thresholds are on the actual skewed data by that running the inverse of that original power function..... good grief I’m boring myself to sleep here. 😀 TL:DR Open up the tool you’re using to crunch the numbers and google ‘How to calculate STD in skewed data sets in Tool X’ And as for useful links Wikipedia’s section on Stats is awesome! I’d start with Skewness and Data Transformation (Statistics) and see where that leads you. As I said before Congratulations on an awesome job! * I worry about =KURT() as well and also adjust for that in the power function. Kurt is kurtosis; the pointiness of the data set.
  3. First of all, this is an awesome amount of work. Congratulations it’s very impressive. My only minor quibble is with the approach you’ve used for the standard deviation. We have here a dataset that is on a percentage basis (0% to 100%). These are rarely normally distributed - typically there’s a negative skew and so in order to calculate a +1/-1 Standard deviation you’ld have to transform the source data using some form of power function (like a y=a + b^c or a log-based version). Then you calculate the STD, then you reverse transform it back into values in the source data. You’ll end up with a -1 STD that is further away from the mean than the +1 STD but that’s okay, that’s what it should be for negative skew. As i said ‘just a minor quibble’ and I don’t want it to detract from the serious amount of fine work you’ve put into this. Excellent job!
  4. I started off with the intention of building Neil Armstrong’s boot print on the moon, but a heavy diet of Film Noir movies lead me in a different direction. Hope you enjoy it.
  5. eurotrash

    MOC: The Brixton Hotel

    Very effective color palette and chock full of great design. I really like the step down lounge area, the clean-lined front desk, and the SNOT floor, but it’s elevators that just look perfect. Excellent job!
  6. eurotrash

    Lester's Big Adventure Voting

    10 - 1 point 12 - 2 points Great effort everyone!
  7. eurotrash

    MOC: Cove Market, fish and vegetable harbor market

    I'm a huge fan of the old and discoloured bricks! Great job!
  8. MOC: A 1930's Stud-baker I found an old faded sepia photograph of a 1930's Stud-baker. I think it'd be perfect for Lester! More stuff and nonsense on Flickr https://www.flickr.com/photos/eurotrash48903/
  9. eurotrash

    [LESTER] Adventure Jeep

    Nice looking vehicle. I particularly like the technique you’ve used for the windscreen.
  10. eurotrash

    Night Outing in NINJAGO City

    Excellent work! Very atmospheric.
  11. I had been on the fence about this set. Even today I had it in my shopping basket but replaced it with something else at the last minute. Your review has convinced me to buy it tomorrow - maybe even two sets ?
  12. eurotrash

    {MOC} Small city diorama

    Beautifully executed, plenty of detail and I love the color palette you've used.
  13. eurotrash

    LEGO dissertation survey

    Done! Good luck with the survey and your dissertation. One thought though; the color palette of bricks has changed substantially since the early days. We've gone from bold primary colors to a more subtle, highly extensive color range (e.g. the humble 1x1 brick now comes in 50+ colors). It might be interesting to explore the actual distribution of color used in sets through the ages. You could rank or score the available colors based on perceived gender, grab all the inventories of the sets under consideration (perhaps limiting it to sets within a specific price range through the years), develop a set gender score (some weighted algorithm that calculates the proportion of perceived-masculine colors to perceived-feminine colors) and see how that has drifted through the years. It'd would be number crunch, but it's easy enough. (Disclosure: I'm a data analyst)
  14. eurotrash

    How to Design a Modular or a Non-Modular Building?

    I'm not entirely sure I belong in such illustrious company, but thanks for including me. As far as my build process is concerned it's very much based on handling raw bricks. I find LDD and the other tools kind of cumbersome and slow to work out details and to me there's nothing quite as satisfying as thinking of an architectural feature and then replicating it with real bricks. I always start with the facade being built flat on its back with no side walls and I tend to position the features in the above ground floors first. That way I can get the windows and 'stuff' aligned before I commence work on the ground floor. I build using EPIC (Existing Pieces Ignore Color) and only swap out the temporary colors when I've got to a point where I want to solidify the design. There's sometimes a far amount of rework involved but that's never a problem - it just means that I've got a better idea I want to explore. Once the facade is finished I'll mesh it up to a pre-built three-walled structure (two side walls and the rear) and start work on the roof and greebling (the waterpipes, the a/c units, the duct work, any signage, etc.). As for any interiors they will be built separately and lowered into place for any photographs. If I'm just freebuilding the design will come together quickly, but if it's based on a real building (or TV show like Bob's Burgers) then the research part can take months. For my three Bob's Burgers builds I scoured the interweb for images, hints, and details, reached out to the production crew and the animators for obscure views (getting a clear shot of the rear of Morty's Funeral Home was a real pain in the megablocks). It's fair to say I became obsessive and couldn't watch an episode without my finger on the pause button waiting for a specific detail to be resolved. That's the build process and to be honest it's probably not too different from the other AFOLs methods. What's more interesting to me, at least, is the inspiration for the builds and that can come from anywhere and everywhere. I've just spent an hour or so scrolling through the forty-odd Modulars I've got on my Flickr account and as I was doing that I was trying to recall some of the thought process behind each build. So, in no particular order my most satisfying builds have come from: a challenge or a bet. One of my favorite sentences to hear is "I bet you couldn't do that in Lego". They may well be correct, but it doesn't mean I'm not going to try my hardest. bad jokes and terrible puns. a specific architectural detail I know I can replicate in Lego (and the more NPU the better). an exhibition deadline. Nothing concentrates the mind quite as much as committing to build five distinctive Toontown modulars for Kansas City Bricklab's "Who framed Roger Rabbit?" display at Brickworld 2017 peer suggestions. The LUG I belong to has an active Facebook group and the other modular builders there are a great source of ideas and inspiration. We'll use Facebook to show WIPs, share details, seek suggestions and that way the builds become more collaborative and effective. bulk lego. What am I going to do with six Car hoods in medium blue? or eight others in sand green and 12 puppies? or 24 left handed wedge pieces? If I stare at my inventory pile long enough then an answer will emerge. I wrote earlier that inspiration can come from anywhere and everywhere and that's it. You've just got to keep clicking them bricks together..... "Bet you can't do it.... "
  15. Thanks Cop Mike for organizing this again. Here's my contribution. Jack Sparrow and his crew decorating the Palm Tree. Selfie: Decorating the Pirate Palm tree by Chris Goddard, on Flickr