New Entries in the CoasterBuzz Top 100

What ride did it tie with?

Smashing Your Hand With A Hammer: The Ride

hambone:

It would be an interesting logic/programming question to figure out how to use rankings.

Here’s how I’d do it if the goal is a defensible, reproducible “best coasters” ranking.

1) Collect the right kind of opinions (pairwise, not 1–10)

Rating scales (1–10) are easy, but they’re messy: everyone uses the scale differently, gets anchored by hype, and compresses scores.

Pairwise comparisons (“A vs B, which is better?”) are way cleaner because:

People are better at relative judgments than absolute scoring.

It reduces “everyone’s a 10” scale bias.

You can infer a global ranking from incomplete comparisons.

This is the core idea behind “Hawker-style” approaches (head-to-head preference aggregation), and it’s why people still talk about it.

2) Design the survey like an actual experiment (incomplete blocks + adaptivity)

No one has ridden everything, so you’re always dealing with missing data. The trick is making the missingness less destructive.

Practical setup

Each voter imports a “credits” list (or just checks off coasters ridden).

The system only asks them to compare coasters they’ve ridden.

Each session: ~15–30 comparisons (quick, low fatigue).

Make the comparisons smart

Use an incomplete block design mindset so the dataset doesn’t become a bunch of isolated little “my home park” islands. Balanced incomplete designs are a classic way to get efficient comparisons without requiring everyone to see everything.

Then add active selection:

Prefer pairs where the model is uncertain.

Prefer “bridge” comparisons that connect clusters (Europe-heavy voters vs US-heavy voters, wood people vs hyper people, etc.).

This is how you turn a nerd poll into something that behaves like measurement.

3) Use a real model to turn those comparisons into scores

This is the part where you stop doing “cumulative ranking or some ****” and do the normal thing statisticians do with pairwise data.

The baseline model

Bradley–Terry: each coaster has a latent “strength,” and your comparisons estimate the probability A beats B.

That gets you:

A score per coaster

A ranking

A built-in way to handle incomplete matchups

Make it actually robust (the part most polls skip)

Use a hierarchical version:

Add a rater effect (some voters are harsh, some are hype machines).

Add optional covariates like “ridden this year” (recency), because opinions drift and memory lies. (Hawker ballots even tracked “ridden this year” style info.)

Allow ties if you want (or force a pick, which is fine).

This is standard paired-comparison practice, and it’s well studied.

4) Kill the two biggest biases: exposure bias and sample bias

Exposure bias (few riders)

A coaster with 25 voters can “win” the internet if you don’t control for uncertainty.

Fix: shrinkage + minimum data rules

Use Bayesian priors / regularization so low-data coasters don’t rocket to #3 on vibes alone.

Publish a “Main Ranking” that requires:

at least X unique voters, and

at least Y total comparisons involving that coaster

Everything else goes into “provisional” or “insufficient data.”

Sample bias (who is voting)

Your voters are not “all riders.” They’re enthusiasts who:

travel more than average

skew toward newer rides

skew toward whatever regions are overrepresented

Fix options (pick how serious you want to be):

Stratified weighting by region/home country (so Ohio doesn’t become the global electorate).

Weight voters modestly by breadth of experience (someone with 15 credits probably shouldn’t equal someone with 500), but don’t get elitist about it.

Publish the demographic/credit distribution so everyone can see what the sample really is.

5) Publish uncertainty, not just a single sacred list

A “scientific” ranking that outputs one definitive list with no error bars is cosplay.

So you publish:

Rank + 95% credible interval (or bootstrap CI) per coaster

Probability that #5 actually beats #4 (often it won’t be decisive)

Tiers (“these 8 are statistically indistinguishable”)

That makes the list more useful, not less, because it tells people where the real consensus is versus knife-edge fan wars.

6) Make it reproducible (so it earns respect instead of fights)

If you want “scientifically acceptable,” you do the boring grown-up stuff:

Freeze the dataset for “2026 edition”

Publish the rules and model up front (don’t tweak after seeing results)

Release anonymized comparison data and code so anyone can replicate

When people can rerun your pipeline and get the same ranking, the community arguments shift from “rigged” to “ok fine, I hate math.”

7) What the final output looks like (the “useful list” part)

You don’t ship one list. You ship a small set:

Overall Top 100 (with uncertainty bands)

Regional Top 50s (US, Europe, Asia, etc.)

By category (wood, steel, family thrill, etc.)

Most Polarizing (highest voter disagreement)

Biggest risers/fallers year-over-year (with enough data to justify it)

That covers how coaster people actually consume rankings: bragging rights, trip planning, and arguing online.

8) If you want the simplest “best” approach that still counts as legit

Collect pairwise comparisons.

Fit Bradley–Terry with voter effects.

Apply shrinkage + minimum data thresholds.

Publish ranks with uncertainty and tiers.

That’s the shortest path to “this is real analysis” without turning it into a PhD dissertation nobody finishes.

And yes, it will still be fought about, because coaster nerds don’t want truth. They want ammunition.

---

Thank you, AI overlords.

Thought we agreed in the other thread that different people like different things. And that doesn't make anyone wrong. Just different. 😀

Oh, we never agree or resolve anything around here.

That's what makes it fun.

The AI solution is really labor intensive for relatively little gain in the quality of the results. Like I said, the five scale I use should be straight forward:

1. Among the worst
2. Below average
3. Average
4. Above average
5. Among the best

Anything more would be overthinking it.

And here's a fun fact: Despite hundreds of track records, it's looks like about a dozen people actually ranked their list. Glad I spent all that time coding it! (That was like 16 years ago, it's fine.)

Jeff:

The AI solution is really labor intensive for relatively little gain in the quality of the results.

But...but...accuracy! Scientific relevance! Meaningful statistics! Quantifying opinions!

I seem to remember long-winded debates over the Hawker poll on all of the above.

I'd just feed AI the database and see what it spits out.

Honestly, only copy and pasted it to be...well, me. But I do really think this part is an interesting idea to taking the idea of ranking lists to an ubernerdy, but still useable, place:

My finely-tuned LLM said:

So you publish:

Rank + 95% credible interval (or bootstrap CI) per coaster

Probability that #5 actually beats #4 (often it won’t be decisive)

Tiers (“these 8 are statistically indistinguishable”)

It'd create..oh God, I'm gonna say it...sliders for each entry. And there will be varying levels of overlap on the sliders between entries - from complete to none.

Maybe displayed as list of percentiles graphically as bars? Like the old reports you'd get back from achievement tests in school? (Am I that old? Do they still do that? Did they ever?)

But as I talk (type?) it out, all I'm doing at that point is creating the same list (for the most part) and adding a way to visually display the uncertainly between rankings.

I'm not a nerd, you're a nerd!

Like weather forecasts. Not sure that Doppler 5 Million forecasts are any more accurate. But all the graphics, charts, street by street trackers of storms, etc. looks impressive and makes for some striking visuals on the TV screen. Forecasts though are often for between a trace and 5 feet of snow though.

Jeff:

And here's a fun fact: Despite hundreds of track records, it's looks like about a dozen people actually ranked their list. Glad I spent all that time coding it! (That was like 16 years ago, it's fine.)

If wood and steel could be ranked separately, I'd have done it.

Jeff:

it's looks like about a dozen people actually ranked their list.

(Raises hand.)Thank you for coding that. I'm the kind of person that has trouble picking out a toothpast because there are too many choices. I find no joy in picking out a tube of toothpaste, or box of cereal, or ... However, ranking my track list is a really fun experience. I start at the top, and ask myself,

"If I were on a deserted island, and I could only choose one ride between this one and the one under it, which would I choose."

...And then I move to the next one and ask the same thing, and so on and so forth.

And I like to revisit it every year or so. So much fun. For example, last year, I went to KD, and I had to give Grizzly and Racer a huge jump to the top of my list. They are really fun now that they have been retracked.

(I'm a lot better with making choices now that I'm older. I have found what brands and flavors I like, and look for only that.I make other brands and flavors are invisible to me.)

I used the ranking feature to put them in alphabetical order. That's perfectly normal, right? Right?

Big congrats to Adventure Express until somebody opens Aardvark:The Ride.

ArieForce One with a remarkable debut this week. The RMC domination continues.

Our long national nightmare is finally over.

RMC coasters are fun, but I'm over them. Maybe it's because I'm getting older, but I am starting to prefer fun over ripping-your-face-off intensity. It might also be because I am getting even fatter, and they are very uncomfortable.

I love a lot of the RMC's, but they are starting to feel samey. I didn't get much of anything out of Wildcat's Revenge. I also rode SFNE's Superman a few years ago and realized how little "feeling of speed" the RMC's have.

They are definitely top tier coasters, but just not the best of the best. (ed. note: planning to ride SV for the first time next week and haven't ridden IG, so...)

Wow, it's like the "B&M is boring" phenomenon all over again. Except with some of the wildest coasters ever built.

Where I'm starting to sour on RMCs is the restraints. Last month's ride on ArieForce One and my ride 2 days ago on SFGrAm's Goliath (not first time riding) get a lot of fun taken out of it because of how uncomfortable the restraints are. But they are anything but boring.

That, and I'm rapidly souring on the overall home park Steel Vengeance experience. 45 minute Fastlane waits, a terrible locker system, and the usual complaints of "they just tried to do too much" make me skip it half the time I'm there. I realize SV is something truly special and another one like it will probably never get built, but IDK. Yes, that's why I and some others prefer Iron Gwazi (SV, but edited) But better restraints would go a long way on SV as well.

I despise the RMC restraints with a passion, anyone with long legs that also have some meat on them quickly sizes out because of those shin guards. If I don’t fit because it’s my waist that’s stopping the restraint, that’s on me, but if it’s because my shins stop the restraint that’s on the manufacturer. I have zero problem fitting on Iron Rattler (which I know that design has issues, I’m not asking to go back to that,) there has to be a better way.

ApolloAndy:

I love a lot of the RMC's, but they are starting to feel samey.

This is why I got bored with traveling for new rides. It's not that they're boring, but few are unique enough to travel for, to me at least.

My roller coaster tastes have been changing over the last few years. Fun over fear. I still love The Beast. I'm very happy they keep working on smoothing it out.

But there has been this new coaster layout design choice over the last several years that I don't like. Coasters like RMCs, Mystic Timbers, and newer Intamins are great, but they like to ragdoll their riders. They have elements that start before the last element has a chance to finish.

I've been starting to really like classic wooden coasters more, especially when they have had track work done. Like Racer 75 and Grizzly at KD, for example. I might have mentioned Big Bear Mountain somewhere on here a few days ago. It is one of my favorite new coasters. It's just fun.

I changed my top coasters a while back. I think I'll go over and take a second look.