What's new

An analysis of North America's coaster selections (Part 2: Strongest top ends)

Matt N

CF Legend
Disclaimer: This post is extremely long, and if you don't like data analysis and geeky maths talk, I'd suggest you run for the hills and don't look back, because this post has quite a bit of it!
Hi guys. Some of you might remember that I recently did a multi-part data analysis investigation on Europe's major coaster selections (topic is here if you don't know what I'm on about: https://coasterforce.com/forums/thr...part-3-quantoverqual-and-qualoverquant.45455/), where I asked numerous different questions about Europe's major coaster selections. So I thought that a natural next step would be to try North America; it would be rude of me not to pay the Americans a visit given how many coasters and parks are in the USA alone, let alone the rest of North America!

But for those of you who have no idea about my previous data analysis investigation, let me just introduce what I'm doing...
Introduction
There are a lot of theme parks in North America, as well as a lot of roller coasters. So naturally, people (myself included) tend to ask questions like “which park has North America’s best roller coaster lineup?” or “which parks are quality-over-quantity and which parks are quantity-over-quality?”, amongst others. As such, while it’s not really a discussion thread as such, I thought it might be fun to try to take a quantitative look into some of these questions and try to answer them using some data science techniques. So join me as I attempt to perform a quantitative, multi-part analysis of North America’s major coaster selections! I'll split my investigations into a couple of posts, one for each question, to make it a little more digestible.

Before we start, let me set out a few prerequisites and explain some of the facts regarding the investigation…
Prerequisites of the Investigation
  • I am using the coaster ratings on Captain Coaster (https://captaincoaster.com/en/) as of May 2022 to perform this investigation. If you look at each ride’s page on CC, it has a % score out of 100; this is what I have used and converted into ratings out of 10. For the rating out of 10 of a ride, I converted the percentage into a rating by dividing by 10 (so for instance, a ride rated 87% would have an average rating of 8.7/10).
  • Building upon the ratings stuff; all ratings are rounded to the nearest 0.1 (so to 1dp).
  • As a rule of thumb of what’s considered major, I went with; to be considered, a park must have 5 scoreable roller coasters. If you’re wondering why I get so specific in saying “scoreable roller coasters”, it’s because Captain Coaster does not score what it considers to be “kiddie coasters”, so not every ride in a park's lineup is scored. As such, this means that parks with 5 kiddie coasters wouldn't be eligible for this investigation; my rule ensures that a park in the study has 5 family/family thrill coasters, at the very least. It also doesn't score rides where the ridership is too low, but the effect of that upon this investigation is quite minor; only 1 or 2 parks/rides were affected. Off the top of my head, Tumbili at Kings Dominion and Wonder Woman Coaster at Six Flags Mexico (bizarrely given it opened in 2018) are not scored on CC due to their ridership being too low, therefore the investigation excluded them, but all the other new rides that have opened are counted. So the likes of Iron Gwazi, Ice Breaker, Pantheon, VelociCoaster etc are all included.
  • However, one inconsistency is that Captain Coaster has a somewhat inconsistent definition of what it considers a kiddie coaster. Using some examples from my home continent of Europe, things like the Steeplechases at Blackpool are considered kiddie coasters, but Blue Flyer in the same park, which I personally would consider a kiddie coaster, isn't. I could have taken kiddie coasters into account, but I could not think of a fair way to do it, as rides that fall into this bracket that slipped through the cracks seem to have wildly varying scores.
  • The site also has rides listed on it that some probably wouldn't count as roller coasters, but some do, such as SuperSplash at Plopsaland and Fuga de Atlantide at Gardaland. I just decided to go with the site's scores and the rides that the site scored, as even though I could calculate the mean rating of some unscored rides, I don't think CC's scoring system only uses mean rating, as I seem to remember it being mentioned that members' rankings are also factored in, so me attempting to meddle with CC's system risks introducing bias and skewing the data the wrong way, which you definitely don't want in a data investigation. However, I did think this was something I should raise before we begin.
  • The most important prerequisite of all is that the results of this investigation are not necessarily the final answers to the questions I raised in my introductory paragraph by any stretch. All of this still comes entirely down to personal opinion, of course.
Right then; I think that's everything, so let's dive into the dataset...
The Dataset
When searching through RCDB for theme parks that met my criteria, as well as cross-referencing with Captain Coaster to ensure that the criteria were met in terms of scoreability, I found 41 theme parks with 358 roller coasters between them. These parks, as well as the number of scoreable roller coasters they each contain, are as follows:
  1. Six Flags Magic Mountain (USA, California): 16
  2. Canada's Wonderland (Canada): 16
  3. Cedar Point (USA, Ohio): 16
  4. Six Flags Great America (USA, Illinois): 14
  5. Kings Island (USA, Ohio): 14
  6. Hersheypark (USA, Pennsylvania): 14
  7. Six Flags Great Adventure (USA, New Jersey): 13
  8. Carowinds (USA, North Carolina): 13
  9. Kings Dominion (USA, Virginia): 12
  10. Six Flags Over Texas (USA, Texas): 11
  11. Six Flags Over Georgia (USA, Georgia): 10
  12. Six Flags New England (USA, Massachusetts): 10
  13. Busch Gardens Tampa (USA, Florida): 10
  14. Six Flags Fiesta Texas (USA, Texas): 9
  15. Lagoon (USA, Utah): 9
  16. Knott's Berry Farm (USA, California): 9
  17. Six Flags St Louis (USA, Missouri): 9
  18. Busch Gardens Williamsburg (USA, Virginia): 9
  19. Six Flags Discovery Kingdom (USA, California): 8
  20. Six Flags America (USA, Maryland): 8
  21. La Ronde (Canada): 8
  22. Dollywood (USA, Tennessee): 8
  23. Six Flags Mexico (Mexico): 8
  24. Kennywood (USA, Pennsylvania): 8
  25. Six Flags Darien Lake (USA, New York): 7
  26. Valleyfair (USA, Minnesota): 7
  27. Morey's Piers (USA, New Jersey): 6
  28. Worlds of Fun (USA, Missouri): 6
  29. Michigan's Adventure (USA, Michigan): 6
  30. Silver Dollar City (USA, Missouri): 6
  31. Dorney Park (USA, Pennsylvania): 6
  32. SeaWorld Orlando (USA, Florida): 6
  33. Kentucky Kingdom (USA, Kentucky): 6
  34. Luna Park (USA, New York): 5
  35. Indiana Beach (USA, Indiana): 5
  36. Great Escape (USA, New York): 5
  37. SeaWorld San Antonio (USA, Texas): 5
  38. Knoebels (USA, Pennsylvania): 5
  39. Disney's Magic Kingdom (USA, Florida): 5
  40. Nickelodeon Universe Theme Park (USA, New Jersey): 5
  41. Disneyland (USA, California): 5
I think that just about covers everything, but if you feel I’ve missed an obvious one, then don’t be afraid to tell me.

Let's move on to some fun stuff now... I'll start analysing some different common questions and see what answers I come out with. I'll use this first post to do...
What is North America’s most consistently strong coaster selection?

Yes, I’ll be finding out which coaster selection in North America is the most consistently strong! For clarity, this focuses on the entire scoreable selection and sees the consistent strength of a park’s lineup. This is not weighted solely towards a park’s more highly rated coasters (I’ll be examining the top ends of selections on their own in a separate question), but instead considers the consistent strength of a park’s whole selection. I’m basically asking “to what extent does each park in the dataset have a consistently strong, good quality lineup?”.

There are numerous data science techniques we can use to find this out.

Let’s start with the first one…
Mean
The first statistical method we can use is the mean. For those that don’t know, the mean is a calculated average, where the sum of all a park’s coaster ratings is calculated and then divided by the number of scoreable coasters in that park to work out the average rating. The formula for the mean is as follows:
Mean Rating = Sum of all Ratings/Number of Scoreable Coasters

When applying the mean to each park in the dataset, the top 10 most consistently strong coaster selections in North America were as follows:
RankingParkMean (to 1dp)Number of Scoreable Coasters
1Silver Dollar City7.56
2Busch Gardens Williamsburg7.39
3Dollywood7.08
4SeaWorld Orlando7.06
5Cedar Point6.616
6Six Flags Magic Mountain6.616
7Busch Gardens Tampa6.510
8SeaWorld San Antonio6.45
9Six Flags Fiesta Texas6.49
10Kennywood6.48

But mean is not the only statistical measure I can use…
Median
Another statistical measure we can use is the median. For those that don’t know, the median is the middle value in a dataset; the midpoint, if you like. For instance, in a dataset of 9 scoreable roller coasters, the median value would be the 5th highest rated coaster, because there are 4 coasters rated higher than it and 4 coasters rated lower than it.

When applying the median to each park in the dataset, the top 10 most consistently strong coaster selections in North America were as follows:
RankingParkMedian (to 1dp)Amount of Scoreable Coasters
1Silver Dollar City8.66
2Busch Gardens Williamsburg8.39
3SeaWorld Orlando8.16
4Busch Gardens Tampa7.410
5Dollywood7.38
6Six Flags Great Adventure7.213
7Cedar Point7.216
8Disney’s Magic Kingdom7.05
9Dorney Park7.06
10Six Flags Magic Mountain6.916

However, there’s one final statistical measure of my own that I’d like to test out…
The Matt N Formula for Consistent Strength
So far, I have used two pre-existing statistical measures; the mean, a calculated average, and the median, the midpoint value. However, each of these has its own flaws and things that it doesn’t really consider.

The mean is flawed in that it can be quite easily skewed by a small number of data items on the extreme ends of the spectrum, thus not providing an accurate picture of the whole selection. Whereas the median, while possibly providing a more accurate picture of the general quality of a selection, does not take the extreme ends of the spectrum into account at all; if a park's coaster selection had a median rating of 6/10, the top value could be a 7/10 or a 10/10 and it would make no difference.

With that in mind, I decided to come up with my own formula to determine the consistent strength of a selection. A formula that takes into account both the extreme ends of the spectrum and the general quality across the board. So let me present The Matt N Formula for Consistent Strength; the formula is as follows:
Matt N Formula for Consistent Strength = (Highest rating + Upper quartile)*(Lowest rating + Lower quartile)

I included the highest rating and the lowest rating to take into account the extreme ends of a selection, while I also integrated quartiles to provide a stronger picture of general quality throughout a selection.

Those of you who followed my Europe data analysis might remember that I initially attempted to use this formula to work out strength in general without really quantifying what strength was, but I later decided that this particular formula would work better to determine consistent strength.

When I applied the Matt N Formula for Consistent Strength to each park in the dataset, the top 10 most consistently strong coaster selections in North America were as follows:
RankingParkHighest RatingUpper Quartile (to 1dp)Lowest RatingLower Quartile (to 1dp)Matt N Formula Score (to 1dp)Quantity of Scoreable Coasters
1Dollywood9.98.03.96.4183.08
2Silver Dollar City9.79.33.56.0180.76
3Kennywood9.37.24.25.2155.38
4SeaWorld San Antonio8.87.63.45.6147.65
5Knoebels9.47.52.75.9145.35
6Busch Gardens Williamsburg9.79.01.16.4140.39
7SeaWorld Orlando9.68.90.76.7135.86
8Cedar Point10.08.91.55.4130.616
9Six Flags Magic Mountain9.87.81.35.4117.916
10Disney’s Magic Kingdom7.17.11.96.3116.45

Let’s now summarise what we’ve learned…
Summary
So, what did we learn from this investigation?

Well, while the methods used did differ the results somewhat, there were some names that universally appeared in the top 10 regardless. And there was one park in particular that did shine, scoring highly on all 3 measures.

As it came top when using 2 of the 3 measures and came second in the measure that it didn’t win, I am saying that my data concludes that Silver Dollar City has North America’s most consistently strong coaster lineup. When a park comes out on top 2 out of 3 times and comes second the 3rd time (and a very close second, at that), it’s hard not to declare it the winner!

I’m aware that the results might not be what some expect, and in some ways, they weren’t what I would have expected either, but it is worth me reiterating that this is asking what North America’s most consistently strong coaster lineup is rather than what the strongest coaster lineup is in terms of the park’s highest rated coasters. If I honed in exclusively on each park’s strongest rated coasters (which I will do in a separate question), I can sense these results would look very different.

Also, just because my algorithm is saying that Silver Dollar City wins this, that’s not “the correct answer” by any means; it’s all down to personal opinion. The answer I’m showing here is merely the conclusion that my data analysis came to based off of the average opinions of a subset of coaster enthusiasts.

Just for reference, here is a box plot I created using Python’s MatPlotLib library to show the spread of ratings for each coaster selection and how they compare to one another in a visual way:
North-American-Coaster-Lineups-Boxplot.png

I’m aware that that’s a bit of a mess, so just for some idea, here is the order in which the parks appear, from left to right (the number at the side is the number of scoreable coasters the park has:
  1. Six Flags Magic Mountain (USA, California): 16
  2. Canada's Wonderland (Canada): 16
  3. Cedar Point (USA, Ohio): 16
  4. Six Flags Great America (USA, Illinois): 14
  5. Kings Island (USA, Ohio): 14
  6. Hersheypark (USA, Pennsylvania): 14
  7. Six Flags Great Adventure (USA, New Jersey): 13
  8. Carowinds (USA, North Carolina): 13
  9. Kings Dominion (USA, Virginia): 12
  10. Six Flags Over Texas (USA, Texas): 11
  11. Six Flags Over Georgia (USA, Georgia): 10
  12. Six Flags New England (USA, Massachusetts): 10
  13. Busch Gardens Tampa (USA, Florida): 10
  14. Six Flags Fiesta Texas (USA, Texas): 9
  15. Lagoon (USA, Utah): 9
  16. Knott's Berry Farm (USA, California): 9
  17. Six Flags St Louis (USA, Missouri): 9
  18. Busch Gardens Williamsburg (USA, Virginia): 9
  19. Six Flags Discovery Kingdom (USA, California): 8
  20. Six Flags America (USA, Maryland): 8
  21. La Ronde (Canada): 8
  22. Dollywood (USA, Tennessee): 8
  23. Six Flags Mexico (Mexico): 8
  24. Kennywood (USA, Pennsylvania): 8
  25. Six Flags Darien Lake (USA, New York): 7
  26. Valleyfair (USA, Minnesota): 7
  27. Morey's Piers (USA, New Jersey): 6
  28. Worlds of Fun (USA, Missouri): 6
  29. Michigan's Adventure (USA, Michigan): 6
  30. Silver Dollar City (USA, Missouri): 6
  31. Dorney Park (USA, Pennsylvania): 6
  32. SeaWorld Orlando (USA, Florida): 6
  33. Kentucky Kingdom (USA, Kentucky): 6
  34. Luna Park (USA, New York): 5
  35. Indiana Beach (USA, Indiana): 5
  36. Great Escape (USA, New York): 5
  37. SeaWorld San Antonio (USA, Texas): 5
  38. Knoebels (USA, Pennsylvania): 5
  39. Disney's Magic Kingdom (USA, Florida): 5
  40. Nickelodeon Universe Theme Park (USA, New Jersey): 5
  41. Disneyland (USA, California): 5
And here is the spreadsheet with the complete raw dataset, for your viewing pleasure:
Thanks for reading part 1 of my analysis of North America’s major coaster selections! I’m hoping part 2 will be on its way before too long, and in that one, I’m planning to dive a bit deeper into the top end of these parks’ coaster selections, to see which parks have the strongest top tier; part 1 focused on the selection as a whole, but I know there is a lot of interest in the top tier of these coaster selections in isolation.

But if any of you have any suggestions for questions about this dataset you’d like me to try and answer, then I’m very happy to accept suggestions!
 
The answer is definitely yes.
But what was the question again Matt?
The question was "Which parks in North America have the most consistently strong coaster selections?", and it's not really one that can be answered in a yes/no fashion. My conclusion was that Silver Dollar City had the most consistently strong coaster selection in North America, but that is not necessarily "the correct answer"; others may come to a different conclusion.
 
Great stuff here @Matt N ! Maybe it's a Matt thing? ;)

One suggestion to dig further - play around with calculating the standard deviation of rankings; this can be a helpful way to sus out any potential outliers that may throw off park rankings (e.g. a VERY basic kiddie cred in the middle of an awesome park). Here's a quick example of my personal rankings, broken out as average rank and standard deviation. Ultimately, the better the average rank and smaller the standard deviation - the more tightly grouped the coaster rankings would be (again, versus having a really amazing/really poor coaster tanking a park's ranking):

ManufacturerAVERAGE of RankSTDEV of Rank
190.33333331.527525232
Arrow144.111111153.95035705
B&M57.6511627933.73911374
CCI86.234.65111831
Chance36#DIV/0!
Dinn Corp.130.333333347.22569922
Dollywood205.50.7071067812
Dynamic Attractions130.33333338.504900548
E&F Miler Industries198#DIV/0!
GCI63.0909090931.71578328
Gerstlauer140.62536.26859129
Giovanola1077.071067812
Gravity Group96.2102.2800078
Intamin71.663.43201914
International Amusement Devices111#DIV/0!
Mack176.714285744.67554993
Maurer17073.18469785
Morgan88.3333333340.05413004
National Amusement Device Company193.33333332.081665999
Philadelphia Toboggan Coasters, Inc.153.777777821.30010433
Premier117.733333332.83392554
Reverchon184#DIV/0!
RMC9.4285714296.502746672
S&S40.526.1629509
SBF Visa Group214.50.7071067812
Schwarzkopf155.7539.06679262
Vekoma157.928571444.92294991
Vettel115#DIV/0!
William Cobb & Associates177#DIV/0!
Zamperla179.7512.52663828
Zierer104.666666761.84927917
 
Interesting read! I'm looking forward to part 2. I wonder what would happen if you were to compare each park to every other park, but only counting the number of coasters for the park with the smaller lineup. For example, what happens when you compare the top six coasters at Cedar Point with all six coasters at Seaworld Orlando? The top 4 coasters at SWO with all 4 coasters at IOA? The top 4 coasters at CP with all 4 coasters at IOA etc. Maybe you are already planning to do something like this in part 2.

Edit: I now realize that since IOA only has 4 non-kiddie coasters, it isn't part of the analysis, but you get the idea.
 
Interesting read! I'm looking forward to part 2. I wonder what would happen if you were compare each park to every other park, but only counting the number of coasters for the park with the smaller lineup. For example, what happens when you compare the top six coasters at Cedar Point with all six coasters at Seaworld Orlando? The top 4 coasters at SWO with all 4 coasters at IOA? The top 4 coasters at CP with all 4 coasters at IOA etc. Maybe you are already planning to do something like this in part 2.
For part 2, I was planning to do exclusively the top 3s/top end of each park in the dataset, so a focus upon the higher tier of a park's coaster selection is coming.
 
Right then; it's about time I did part 2! And in part 2, I'll be working out... what coaster selections in North America have the strongest top end?

Yes, I'll be focusing solely upon the parks' most highly rated coasters in this question! As I got a few comments about the slightly weird results in part 1, I'm thinking that this question should hopefully correct that and produce results more akin to what you might typically expect, as I'm focusing only upon "the interesting stuff" here!

So how did I work this out?

Well, I used 3 different ways of attempting to measure this.

The first method I used was...
Mean of Top 3
The first method I used was calculating a mean of each park's top 3. For those of you that don't know, the mean is the calculated average of each top 3, and the formula is as follows:
Mean of Top 3 = Sum of All Ratings/3 (as the top 3 is being focused upon here, the count of ratings will always be 3)
When this formula was applied to each park's top 3, the highest rated top 3s came out as follows:
RankingParkMean Rating of Top 3 (1dp)Top 3 Coasters in Park (with ratings out of 10)
1Cedar Point9.8
  1. Steel Vengeance (10.0)
  2. Maverick (9.9)
  3. Top Thrill Dragster/Millennium Force (tied at 9.6)
2Six Flags Magic Mountain9.6
  1. Twisted Colossus (9.8)
  2. X2 (9.7)
  3. Tatsu (9.4)
3Busch Gardens Tampa9.5
  1. Iron Gwazi (10.0)
  2. Montu (9.4)
  3. SheiKra (9.1)
4Six Flags Great Adventure9.4
  1. El Toro (9.9)
  2. Nitro (9.2)
  3. Kingda Ka (9.1)
5Six Flags Fiesta Texas9.3
  1. Iron Rattler (9.7)
  2. Wonder Woman Golden Lasso Coaster (9.5)
  3. Superman Krypton Coaster (8.8)
6Kings Dominion9.3
  1. Twisted Timbers (9.9)
  2. Intimidator 305 (9.8)
  3. Dominator (8.2)
7Hersheypark9.3
  1. Skyrush (9.8)
  2. Storm Runner (9.2)
  3. Candymonium (8.9)
8Busch Gardens Williamsburg9.3
  1. Pantheon (9.7)
  2. Griffon (9.2)
  3. Alpengeist/Apollo's Chariot (tied at 9.0)
9Silver Dollar City9.3
  1. Outlaw Run (9.7)
  2. Time Traveler (9.5)
  3. PowderKeg (8.6)
10Canada's Wonderland9.2
  1. Leviathan (9.4)
  2. Behemoth (9.3)
  3. Yukon Striker (9.0)

Let's move on to the second measure...
Median of Top 3
The second measure I applied was the median of the top 3. The median is the midpoint of a dataset (i.e. the middle value), so as we're talking about top 3s, the median value is the 2nd highest rated coaster at each park. When I searched for the median of each park's top 3, the top 10 were as follows:
RankingParkMedianTop 3 Coasters in Park (with ratings out of 10)
1Cedar Point9.9
  1. Steel Vengeance (10.0)
  2. Maverick (9.9)
  3. Top Thrill Dragster/Millennium Force (tied at 9.6)
2Kings Dominion9.8
  1. Twisted Timbers (9.9)
  2. Intimidator 305 (9.8)
  3. Dominator (8.2)
3Six Flags Magic Mountain9.7
  1. Twisted Colossus (9.8)
  2. X2 (9.7)
  3. Tatsu (9.4)
4Six Flags New England9.5
  1. Wicked Cyclone (9.8)
  2. Superman the Ride (9.5)
  3. Batman the Dark Knight (7.2)
5Six Flags Fiesta Texas9.5
  1. Iron Rattler (9.7)
  2. Wonder Woman Golden Lasso Coaster (9.5)
  3. Superman Krypton Coaster (8.8)
6Silver Dollar City9.5
  1. Outlaw Run (9.7)
  2. Time Traveler (9.5)
  3. PowderKeg (8.6)
7Kentucky Kingdom9.4
  1. Storm Chaser (9.7)
  2. Lightning Run (9.4)
  3. Kentucky Flyer (6.2)
8Busch Gardens Tampa9.4
  1. Iron Gwazi (10.0)
  2. Montu (9.4)
  3. SheiKra (9.1)
9Six Flags Over Georgia9.3
  1. Twisted Cyclone (9.7)
  2. Goliath (9.3)
  3. Batman The Ride (7.8)
10Canada's Wonderland9.3
  1. Leviathan (9.4)
  2. Behemoth (9.3)
  3. Yukon Striker (9.0)

After those two measures, I used one final measure of my own...
Matt N Formula for Top End Strength
The final measure I used was my own formula. You might remember that I used my own formula to denote consistent strength in part 1. The formula for top end strength is slightly adjusted compared to that, only taking into account the highest rating and the upper quartile. The formula I'm using to work out top end strength is as follows:
Matt N Formula for Top End Strength = (Highest Rating + Upper Quartile)/2
This formula does require me to touch upon the entire selection again as opposed to just the top 3, but the use of the upper quartile and highest rating mean that I can hone in exclusively on the more highly rated coasters while also considering the strength of the top end as a whole. For all intents and purposes, it's the average of the highest rating and the upper quartile, so the lowly rated coasters within a park's lineup still aren't considered.

When this formula was applied, the top 10 parks were as follows:
RankingParkMatt N Formula Score (1dp)Highest RatingUpper Quartile (1dp)Number of Scoreable Coasters
1Busch Gardens Tampa9.510.09.010
2Silver Dollar City9.59.79.36
3Cedar Point9.510.08.916
4Six Flags Great Adventure9.49.98.913
5Carowinds9.49.98.813
6Busch Gardens Williamsburg9.49.79.09
7Six Flags Fiesta Texas9.39.78.89
8SeaWorld Orlando9.29.68.96
9Kentucky Kingdom9.29.78.66
10Hersheypark9.19.88.314

So, what did we learn in this part of the investigation?

Well, I can quite decisively crown a winner for the park with the strongest top end based on my 3 measures, and that is Cedar Point. The park came out on top in 2 of the 3 measures, and even in the measure it didn't win, it still came 3rd. And I'll be honest, Cedar Point was literally a hair away from the top spot; the difference between Cedar Point and the winner in that measure, Busch Gardens Tampa, was only 0.05. (The reason the top 3 are all listed as 9.5 is because I rounded the Matt N Formula Score to 1 decimal place; there was a difference between each of their exact scores, albeit a very small one)

Before I close off, here's my spreadsheet once again, so that you can peruse my workings at your pleasure:

Thank you all for reading part 2 of my investigation into North America's major coaster selections, where I attempted to find the coaster selections with the strongest top end. I hope you found it interesting, and I hope the results are more in line with what you were originally expecting than they were in part 1!
TL;DR: I attempted to find the North American coaster selections with the strongest top end. I used 3 different measures to calculate this: the mean of the top 3, a calculated average; the median of the top 3, the midpoint value; and the Matt N Formula for Top End Strength, which calculated the average of the park's highest rating and the upper quartile. The winner was determined to be Cedar Point, which won 2 of the 3 measures and came an extremely close 3rd in the measure it did not win.
 
Last edited:
Yup, sounds about right if you're looking at coasters only. :p
 
Top