News:

Welcome to the Golf Club Atlas Discussion Group!

Each user is approved by the Golf Club Atlas editorial staff. For any new inquiries, please contact us.


JLahrman

  • Karma: +0/-0
Re:You must be kidding !
« Reply #75 on: May 09, 2006, 11:57:54 AM »
The analysis I provided you suggests there is no significance to the difference in the correlations between 1980 and 2005.

Just when I thought I was out, they pull me back in.

Bryan,

I have a question.  In my experience there is no way to test for a significant difference between two correlations.  The only significance test one can do on a correlation is to test to see if it is signficantly different from zero.  I do not believe that you can take the p-values from two independent correlation significance tests and compare them.  In effect, I do not believe you can test correlations in the way you appear to be describing above.  Could you explain?

I apologize if you've already described the method, as I noted before the thread is getting hard to follow.

David, I agree.  Others should be performing these analyses.

Paul Payne

Re:You must be kidding !
« Reply #76 on: May 09, 2006, 12:14:05 PM »
JAL,

I run Minitab all the time and you are correct. However after reading your question I would think there certainly would be a way. Unfortunately my wife is the math genius so I'll have to defer to her.

But, if you drew a line through your first correlation, then took the equation for that line and made it equal to zero, you should be able to run a second correlation study against that line. The result of course would be highly dependent on the strength of your first correlation study. If it was a .99 you would likely get a decent result on the second. If it was .09 it may be a bit squishy.


Bryan Izatt

  • Karma: +0/-0
Re:You must be kidding !
« Reply #77 on: May 09, 2006, 12:41:21 PM »
JAL,

I described the method in post #68. It's from a prof at North Carolina state University.  See what you think of it.

JLahrman

  • Karma: +0/-0
Re:You must be kidding !
« Reply #78 on: May 09, 2006, 01:13:35 PM »
Bryan, thanks for the reference.  I'll take a look (oh, the fun things I do with my life).

Paul, you hit on what I think would be the problem with your approach.  Just using the regression line doesn't take into account the strength of the regression at all.

DMoriarty

Re:You must be kidding !
« Reply #79 on: May 09, 2006, 05:30:32 PM »
I think I understand how outliers can skew the data.  Nonetheless, I dont think these qualify as outliers.   By your description, outliers are "atypical" and "infrequent observations."   The success of Mickelson, Singh, and Woods is not atypical or infrequent, but rather typical and frequent.  They earned bigger shares of the success pie, and excluding them would only unjustifiably skew the results.

Here is some of what the Engineering Statistics Handbook says about outliers:

Outliers should be investigated carefully. Often they contain valuable information about the process under investigation or the data gathering and recording process. Before considering the possible elimination of these points from the data, one should try to understand why they appeared and whether it is likely similar values will continue to appear.

Quote
Is there a different slope in the 1980 line vs the 2005 line? And remember that the outliers have a large effect on the slope, but less on the r-squared.
 
I'll try to supply this later when I get a chance.

Quote
What I mean is that if you analyzed $ vs putting for instance, you might get an r-squared of 20% and that would suggest that putting accounts for more of the variation in earnings than does driving distance.

That may well be, but really what I am concerned with is the how the correlation for driving has changed over the years.  

Nonetheless, golf monetary success is dependent upon so many variables that I just dont think that 8% is very low in the greater scheme of things:   Putting, Chipping, Driving Accuracy, Sand Saves, Recovery Shot, GIR, Experience, Age, Equipment, Bounceback, Health, state of mind, confidence level, Reaching Par 5s, strength of field, starts, purses, etc.  Many of these factors likely overlap.  For example, Longer drives might mean higher GIR so part of the GIR percentage attributable to driving would have to be subtracted out so the total sum is equal to 1.   For example, Longer drives might mean higher GIR so part of the GIR percentage would have to be subtracted out.  

Quote
The 2% to 8% change you report is not quite a lot, as I tried to point out in the following.  It's not statistically significant.
 
I still do not think you can link the magnitude of the correlation to its statistical significance.  If I figured more years and the observation held up, I assume that we could acheive a statistically significant comparison even with relatively low rsq.  

Quote
Is the r-squared of 0.02 what you got by analyzing the 1980 data or is it hypothetical?
 Both.  

Quote
Did you mean 2005 in the last sentence?  I don't have a particular r-squared in mind as being "important".  8%, or 6% if you remove the outliers, is not convincing.
 

I have trouble accepting the rejection of these numbers without any sort of methodology attached to that rejection.  Finding out what would be convincing and why would surely help us define the issue, wouldn't it?  How about 10%?  20% 30%? 80%?  

Quote
The analysis I provided you suggests there is no significance to the difference in the correlations between 1980 and 2005.  

I dont think that is what your analysis suggests.  Rather, I think your analysis suggests that  that the data we have thus far studied is inconclusive about whether the difference between the years is fluky or whether it actually means something. This is a key distinction, I think.  

I'll try to provide the least squared lines later.  

Also, send me your email via IM and I'll send you the data.

john_stiles

  • Karma: +0/-0
Re:You must be kidding !
« Reply #80 on: May 09, 2006, 06:32:38 PM »
Geez,  maybe someone should analyze how many courses have not been lengthened to host US Open or The Open, or the PGA since the ProV was introduced.

I do not have the data but make the suggestion anyway.

And while everyone is analyzing to see if distance is an issue in some off tangent matter,  let's plot something else.

Maybe someone should plot the number of tees added, holes lengthened, number of bunkers and greens moved, and the associated costs for capital improvements and the additional maintenance.  This would need to include all courses in the world.  Remember that courses are being lengthened for top amateur events, college events,  as well as PGA, Nationwide, and senior PGA events.

The USGA is trying to gather the noose around the issue but the rules makers are always behind the manufacturing innovators.  Fact of life.  

USGA tests what they receive. USGA isn't manufacturing anything except for charts and graphs.  USGA is probably duplicating the charts and graphs that the manufacturers have already produced.  

The USGA is loading up the machines with the balls and clubs that they receive in the mail.

Sometimes you just need to roll back the equipment, or buy a larger field.

All this work for a $2 ball is such a mess and I ain't kidding.

Doug Siebert

  • Karma: +0/-0
Re:You must be kidding !
« Reply #81 on: May 09, 2006, 11:21:34 PM »
Damn, this thread has turned into something that reminds me of my college stats courses, but I made sure to drink heavily after the final and kill off all the brain cells that knew about calculating r and r squared.

Where is Brent Hutto when you need him?!
My hovercraft is full of eels.

Jim Nugent

Re:You must be kidding !
« Reply #82 on: May 10, 2006, 07:27:57 AM »
Doug, we got a bit sidetracked from the main point of this thread.  Which is, how do we reign in runaway technology?  

I doubt anyone can, just as they couldn't hold back the steel shaft or the gutta over the feather, or the rubber center over the gutta.  
I also wonder how many people really want to.  Does the golfing public as a whole care much whether the U.S. Open is held at Merion or, God forbid, the new 7647 yard Trump International?  

Patrick_Mucci

Re:You must be kidding !
« Reply #83 on: May 10, 2006, 01:35:06 PM »


Geez,  maybe someone should analyze how many courses have not been lengthened to host US Open or The Open, or the PGA since the ProV was introduced.

I do not have the data but make the suggestion anyway.

And while everyone is analyzing to see if distance is an issue in some off tangent matter,  let's plot something else.

Maybe someone should plot the number of tees added, holes lengthened, number of bunkers and greens moved, and the associated costs for capital improvements and the additional maintenance.  This would need to include all courses in the world.  Remember that courses are being lengthened for top amateur events, college events,  as well as PGA, Nationwide, and senior PGA events.

The USGA is trying to gather the noose around the issue but the rules makers are always behind the manufacturing innovators.  Fact of life.  

USGA tests what they receive. USGA isn't manufacturing anything except for charts and graphs.  USGA is probably duplicating the charts and graphs that the manufacturers have already produced.  

The USGA is loading up the machines with the balls and clubs that they receive in the mail.

Sometimes you just need to roll back the equipment, or buy a larger field.

All this work for a $2 ball is such a mess and I ain't kidding.




John Stiles,

You bring up good points.

If distance isn't a problem, what's the reason almost every golf course is being lengthened at nearly every level, for regular and tournament play ?

Why not let the PGA Tour Pros, the greatest golfers in the world, play from the 1959 tees at WFW, just like they did when Billy Casper won, instead of lengthening it substantially ?
[/color]

PThomas

  • Karma: +0/-0
Re:You must be kidding !
« Reply #84 on: May 10, 2006, 01:42:15 PM »
Patrick - at the beginning of this thread you replied to me that the USGA would act if they were aware of the higher swing speeds generated today

you really don't think they are aware?? ???  how can they not be, with their testing equipment, the fact that their lives are devoted to golf which means they surely are more aware of many things happening in the game that guys like I am, the fact that they know so many people in the game, etc.....

I just cannot buy that argument Patrick

199 played, only Augusta National left to play!

Patrick_Mucci

Re:You must be kidding !
« Reply #85 on: May 10, 2006, 02:54:35 PM »
Paul T,

I think the support for the argument is reflected in the swing speeds chosen for the USGA's testing.

You may recall the issue of "lag", when Iron-Bryon was calibrated at speeds that were slower then those being swung in the field (golf course)

Before you change the standard calibration on your testing equipment to higher speeds, you have to acknowledge and accept that these speeds are valid.

Not increasing the standard calibration would seem to indicate an element of denial, wouldn't you think ?

PThomas

  • Karma: +0/-0
Re:You must be kidding !
« Reply #86 on: May 11, 2006, 04:36:25 PM »
Patrick  - I think we are saying the same thing:  that the USGA is aware of these higher swing speeds but is choosing to ignore or deny them
199 played, only Augusta National left to play!

TEPaul

Re:You must be kidding !
« Reply #87 on: May 11, 2006, 05:12:03 PM »
I just came back from the Pa State Match Play Championship at a Rees Jones course in Greensburg called Totteridge---really good match play course. The course was nice and firm and fast (it was just about at the "Ideal Maintenace Meld" ;) ) so the rollout was pretty good but all the guys were pounding it around 300 and some of the big hitters unloaded some around 350 or more. Problem was you didn't really want to get them in the rough on some holes and it was a bit hard to control the direction. There's a lot of interesting shaping on the fairways on that course that can take the ball all over the place when firm and fast like that.

But my point on this post is you're not kidding it isn't just the driver---these guys were hitting 6 irons into 220 yard par 3s and one guy smoked a 5 iron from around 235 and flew it right onto the green of a par 5 green and it was considerable UPHILL.

Pete Lavallee

  • Karma: +0/-0
Re:You must be kidding !
« Reply #88 on: May 11, 2006, 05:29:07 PM »
You see, the USGA was right, modern elite players don't hit their 5 irons 200 yards; they hit them 235 yards uphill :o.
"...one inoculated with the virus must swing a golf-club or perish."  Robert Hunter