January 2023 Mid-Long Range Disco

[MN Transplant]

Here's a really boring stat comparing the 1980s to 2010s.

• Total snowfall of every day in the 1980s:  183.0"
• Total snowfall of every day in the 2010s:  155.7"

[psuhoffman]

34 minutes ago, MN Transplant said:

About that

 

Calendar Year	Single digit snowfall years
1884-1918	4
1919-1953	7
1954-1988	9
1989-2022	16

This X1000000. 
How anyone can argue with that is beyond me.  Yea we can still get an anomalously snowy winter like 2010 and 2014 that skews an “average” but the odds of getting less snow in any given year are going up and I think many have been clear that’s what we’re talking about. 

[nw baltimore wx]

3 minutes ago, Stormfly said:

Add not getting just snow to the list!  It's hard to have a storm that stays all snow from start to finish.

Heck, I’d kill for a 3-5” front end thump to rain/dry slot these days.

[MN Transplant]

30 minutes ago, WinterWxLuvr said:

I’m guessing the long range looks great after reading this page 

I keep thinking back to this old Family Guy episode.  Just switch the movie for this winter.  Even the map reference is right on.

[Brian, working as a Seeing Eye dog, sits beside his blind guy in a movie theater]

Brian: Okay, they're-they're in the woods...the camera keeps on moving...Uh, I think they're, they're looking for some witch or something, I-I don't know, I wasn't listening...nothing's happening, nothing's happening, something about a map, nothing's happening, it's over, a lot of people in the audience on AMWX look pissed.

[CAPE]

2 minutes ago, nw baltimore wx said:

Heck, I’d kill for a 3-5” front end thump to rain/dry slot these days.

One of the reasons last Jan was an epic month for eastern areas. 3 winter storms, all snow.

[psuhoffman]

[WesternFringe]

14 minutes ago, psuhoffman said:

You’re all over the place.

1) Earlier you said “10 years isn’t a big enough sample” and now you’re basing this analysis on 10 years. 
 

2) 1980s avg DC snow 17.1” Median 17.8 with 3 single digit seasons

Most recent 10 years avg DV snow 12.3” median 10.5 with 5 single digit seasons.

By what metric were you saying the 80s were worse???

 

3) If what you mean is you’re comparing 1980s to 2010s then you are still dealing with the 10 year sample size issue, but then my point why I don’t care about the mean cones up.  Yes the 1980s (which you cherry picked because they were a previous snow minimum) mean was slightly lower at 17.1 to 17.2.  But the 2010s were severely skewed by 2010 and 2014.  But the median and single digit snowfalls tell the story.  The median snow in the 2010s was only 13.5” compared to 17.8” in the 1980s.  There were 4 single digit seasons compared to 3 in the 80s.  So even cherry picking the previously worse minimum period and comparing to the 2010s which included 2 extremely anomalous snowy winters…the odds of less snow in any given season were still higher in the 2010s compared to the 1980s which is what I’m talking about.  
 

I don’t care about the rare once in 9 years huge seasons that skew and inflate the mean.  I’m talking about the fact that in any given season the odds of DC getting less snow (or a single digit season to make the concept simple) is going up and that’s a fact no matter how you try to slice up the data.  

 

If you call looking at the slope of annual snowfall data recorded from DCA 1880 to present cherry picking or ‘slicing up the data’ lol

[Maestrobjwa]

11 minutes ago, CAPE said:

One of the reasons last Jan was an epic month for eastern areas. 3 winter storms, all snow.

I'd like to see your snowfall numbers for the last decade...I'm curious, lol

[TSG]

19 minutes ago, WesternFringe said:

If you call looking at the slope of annual snowfall data recorded from DCA 1880 to present cherry picking or ‘slicing up the data’ lol

It's not, but it doesn't tell nearly the whole story.

 

An example: DC gets slightly more rain (~40") annually than Seattle (37"), but fairly close. Those locations hit those totals in very different ways. How we're getting to these averages is as important as the value itself as that is the weather we experience on the ground. We don't "feel" 10 year averages.

[Chris78]

We really need snow at this point.

[North Balti Zen]

1 hour ago, Ji said:

The only place where snow is down is i95 from Raleigh to Philadelphia. It's up everywhere else.

Um. no. also low to nothing from Philly to Boston as well. The whole eastern seaboard is effed, really. 

[Amped]

The PAC jet is cranking through day 10 at least. It starts to slow down a little after that.

[Twilly05]

1 hour ago, Maestrobjwa said:

I'm sure there's some denial here...and I totally get it. Nobody here likes to see these stats....but I mean, you can't dispute the incremental drop in average. Like I said, we had 3 consecutive decades have 4 single digit snow seasons...I mean that's the simplest way to see it. I mean yeah it's depressing, but what can ya do?

All the more reason to enjoy the heck out of the big ones (and DON'T complain when we get them)

Who is doing the measuring? Seems to me that the airport ALWAYS has a lower than surrounding area measurement. Almost like they are trying to prove a point. Same with temps. Do you know they round up from .1?

So if temp tops out at 86.1, they round up to 87. Or low temp is 22.1, they round up to 23. 

[CAPE]

54 minutes ago, Maestrobjwa said:

I'd like to see your snowfall numbers for the last decade...I'm curious, lol

Only documented in the threads here. Pretty much all over the place. Off the top of my head- a bit over avg last winter, exactly median the winter before, the winter before that, well . Then another median. The 17 and 18 Nina years, one was just under median, the other close to mean. That's 6 I think lol. 2015-16 was the super (warm) Nino. Right around average. Last above avg years were 2013-14, and again in 15. Long term avg for here is 18.5".

[87storms]

1 hour ago, nw baltimore wx said:

Heck, I’d kill for a 3-5” front end thump to rain/dry slot these days.

Or a good ol' Alberta Clipper that actually produces precip once it crosses the Apps and Blue Ridge.

[WesternFringe]

1 hour ago, WesternFringe said:

If you call looking at the slope of annual snowfall data recorded from DCA 1880 to present cherry picking or ‘slicing up the data’ lol

by that slope DCA is getting 3/100 of an inch less per year from 1880 to present. Or 17/100 of an inch more per year since the 1980s to present.

[87storms]

Was out all afternoon, but I think it's important regarding the stats that the data we're working with is a population, not a sample.  I wasn't even really considering confidence intervals because we just don't know enough about how the long-term cycles impact snow totals.  If we're assuming the data since 1887 is a sample size, then anything over 100 is large enough and, per the CLT, all you need is 30+ data points to estimate the mean.  For fun, the 95% CI using all datasets from 1887 on the true population mean (of forever lol) would be about 15-20" which is still under (edit: above) the mean we've experienced since 1990.

I understand where both sides are coming from.  It looks like WF is thinking in longer term data than 1887, but if we're looking strictly at data since 1887, then there's a clear trend and it's not the one we really want (however, it's just a correlation, not a causation).

[Maestrobjwa]

38 minutes ago, CAPE said:

Only documented in the threads here. Pretty much all over the place.

Man what? Forgive me for not having a photographic memory to remember every snow total over last decade from an area that's not even mine, and somehow pick out all said totals by memory from 1000s of post. Shame on me! All I remember is your 30-something inches last year. Stray snark detected...lol

[psuhoffman]

Last time it got this salty in here I got my biggest snow of the last 6 years so I’m liking the vibe. 

[ravensrule]

2 hours ago, nw baltimore wx said:

Heck, I’d kill for a 3-5” front end thump to rain/dry slot these days.

I'd kill for any thump at my age. 

[cbmclean]

26 minutes ago, 87storms said:

If we're assuming the data since 1887 is a sample size, then anything over 100 is large enough and, per the CLT, all you need is 30+ data points to estimate the mean.

The CLT only applies if the variables are independent and identically distributed.  I suspect that this does not apply to at least some aspects of weather/climate.

[WesternFringe]

3 hours ago, psuhoffman said:

The problem has nothing to with the number of years/sample size.  The issue is you aren't looking at what I am talking about.  I am talking about how DC is getting more single digit snowfall seasons than before and you are looking at a mean which can be skewed by a minority of seasons to hide that phenomenon.  We are two ships passing in the night.  Neither of us is refuting the other...we are simply focusing on two completely different phenomenons. 

Mean of 136 numbers isn’t skewed easily by a few numbers.

[Terpeast]

16 minutes ago, psuhoffman said:

Last time it got this salty in here I got my biggest snow of the last 6 years so I’m liking the vibe. 

Well then, lets bring on the salt!

[WesternFringe]

2 hours ago, psuhoffman said:

Seriously?   All you have to do is look at the DC snowfall data.  From 1888 to 2000 a single digit snowfall season was fairly rare, then suddenly they are happening more often than not.  You want me to waste time throwing that into chart just to prove what you can see from a 10 second look at the data? 

Yes, I want you to prove it with numbers, rather than emotion

[SnowenOutThere]

1 minute ago, WesternFringe said:

Yes, I want you to prove it with numbers, rather than emotion

Where have you been the last three pages? 

[WesternFringe]

2 hours ago, psuhoffman said:

You’re all over the place.

1) Earlier you said “10 years isn’t a big enough sample” and now you’re basing this analysis on 10 years. 
 

2) 1980s avg DC snow 17.1” Median 17.8 with 3 single digit seasons

Most recent 10 years avg DV snow 12.3” median 10.5 with 5 single digit seasons.

By what metric were you saying the 80s were worse???

 

3) If what you mean is you’re comparing 1980s to 2010s then you are still dealing with the 10 year sample size issue, but then my point why I don’t care about the mean cones up.  Yes the 1980s (which you cherry picked because they were a previous snow minimum) mean was slightly lower at 17.1 to 17.2.  But the 2010s were severely skewed by 2010 and 2014.  But the median and single digit snowfalls tell the story.  The median snow in the 2010s was only 13.5” compared to 17.8” in the 1980s.  There were 4 single digit seasons compared to 3 in the 80s.  So even cherry picking the previously worse minimum period and comparing to the 2010s which included 2 extremely anomalous snowy winters…the odds of less snow in any given season were still higher in the 2010s compared to the 1980s which is what I’m talking about.  
 

I don’t care about the rare once in 9 years huge seasons that skew and inflate the mean.  I’m talking about the fact that in any given season the odds of DC getting less snow (or a single digit season to make the concept simple) is going up and that’s a fact no matter how you try to slice up the data.  

 

Since 1984, DCA has averaged 0.17” more snow more per year annually.  I didn’t go by decades. Nor did I change my analysis based on that. That is a lie. I went by year markers until present with all of my analysis.

[WesternFringe]

5 minutes ago, SnowenOutThere said:

Where have you been the last three pages? 

I have been here, with no one showing me statistical analysis of DCA getting less snowfall on average other than noise since 1888.  I can show you the equation of the line of best fit.  Where have you been?

ETA:  teach me all you know about linear regression, SnowenOutThere.  I will wait while you Google.

[CAPE]

35 minutes ago, Maestrobjwa said:

Man what? Forgive me for not having a photographic memory to remember every snow total over last decade from an area that's not even mine, and somehow pick out all said totals by memory from 1000s of post. Shame on me! All I remember is your 30-something inches last year. Stray snark detected...lol

Chill man lol. I mean I don't keep detailed documentation. It literally only exists here. I did at one time years ago, but after a trashed computer and failed back up drive  I didn't bother after that. I originally got the historic snowfall data back when the NCDC was a thing, all free, with long term climo data for even small towns like Denton and Centreville. 

eta- just under 20" here last year, all in Jan.

[87storms]

13 minutes ago, cbmclean said:

The CLT only applies if the variables are independent and identically distributed.  I suspect that this does not apply to at least some aspects of weather/climate.

Yea, true, though it does feel like we're better off just flipping a coin each season to determine the over/under lol.

[SnowenOutThere]

2 minutes ago, WesternFringe said:

I have been here, with no one showing me statistical analysis of DCA getting less snowfall on average other than noise since 1888.  I can show you the equation of the line of best fit.  Where have you been?

ETA:  teach me all you know about linear regression, SnowenOutThere.  I will wait while you Google.

Could you please show me that?