What's new
USCHO Fan Forum

This is a sample guest message. Register a free account today to become a member! Once signed in, you'll be able to participate on this site by adding your own topics and posts, as well as connect with other members through your own private inbox!

  • The USCHO Fan Forum has migrated to a new plaform, xenForo. Most of the function of the forum should work in familiar ways. Please note that you can switch between light and dark modes by clicking on the gear icon in the upper right of the main menu bar. We are hoping that this new platform will prove to be faster and more reliable. Please feel free to explore its features.

Post all your cries whines, objections, complaints here

Re: Post all your cries whines, objections, complaints here

I'm just going to make one last statement about CSC's PIM - 1985 said that their mean was distorted by some outliers. The best way to measure the center or typical value for a data set with outliers is to consider the median value. The median is a resistant measure of center which is not distorted by unusual values. For CSC PIM the median is 18 - not so different from the mean of 19.8. Interestingly enough, the median PIM for Castleton's opponents was 14. I'm not trying to make a value judgement here, just reporting data.

Prof,

Something I'd be interested in knowing is the difference between a team's average penalty minutes over a season and how many penalty minutes they had in games against Castleton.
 
Re: Post all your cries whines, objections, complaints here

I do not think it is appropriate to whine about the whiners on the whines thread. Those that do should be ashamed of themselves. :p
They could call The Big Show and get on the Whiner Line.....
 
Re: Post all your cries whines, objections, complaints here

Prof,

Something I'd be interested in knowing is the difference between a team's average penalty minutes over a season and how many penalty minutes they had in games against Castleton.

16 times the opponent averaged more penalty minutes when playing Castleton then their average penalty minutes...and actually the average is kind of big....there was a difference of 234 penalty minutes over 16 games...so an average of 16 penalty minutes per game more then their original penalty minutes of those 16 games. 10 of those games saw a difference of 8PIM's.

Overall teams averaged 16 PIM per game against Castleton, but only averaged 7.5 overall.....take out their Castleton's game and it would be an even bigger difference....
 
Re: Post all your cries whines, objections, complaints here

Prof,

Something I'd be interested in knowing is the difference between a team's average penalty minutes over a season and how many penalty minutes they had in games against Castleton.

In 16 of Castleton's 27 games, teams took more penalties than their season long average. Statistically this is not a significant difference from what we should expect which would be that this should happen 50% of the time (or 13.5 games). The statement that CSC sucks teams into committing more penalties than they normally would is NOT supported by this data.
 
Re: Post all your cries whines, objections, complaints here

16 times the opponent averaged more penalty minutes when playing Castleton then their average penalty minutes...and actually the average is kind of big....there was a difference of 234 penalty minutes over 16 games...so an average of 16 penalty minutes per game more then their original penalty minutes of those 16 games. 10 of those games saw a difference of 8PIM's.

Overall teams averaged 16 PIM per game against Castleton, but only averaged 7.5 overall.....take out their Castleton's game and it would be an even bigger difference....

It's not a fair analysis unless you also account for the 11 games in which teams took fewer PIMs than their average.
 
Re: Post all your cries whines, objections, complaints here

In 16 of Castleton's 27 games, teams took more penalties than their season long average. Statistically this is not a significant difference from what we should expect which would be that this should happen 50% of the time (or 13.5 games). The statement that CSC sucks teams into committing more penalties than they normally would is NOT supported by this data.

True, but look at how many they take when they go over....even over the 27 games they take twice as many PIM....of those 16 where they went over those teams took on average 16 more minutes......
 
Re: Post all your cries whines, objections, complaints here

True, but look at how many they take when they go over....even over the 27 games they take twice as many PIM....of those 16 where they went over those teams took on average 16 more minutes......

Not statistically significant...
 
Re: Post all your cries whines, objections, complaints here

It's not a fair analysis unless you also account for the 11 games in which teams took fewer PIMs than their average.

and in those 11 games teams only average 4 PIM fewer then their average....compared to the 16 they average when teams go over....
 
Geeeez......just no love for the BullDogs! For your sake, I hope that SNC & Adrian can get at each other for another tilt! I hate seeing you lose sleep dealing with all this anger. :)

I'd take that. That would mean the title would be back in the west.
 
Re: Post all your cries whines, objections, complaints here

I'm just going to make one last statement about CSC's PIM - 1985 said that their mean was distorted by some outliers. The best way to measure the center or typical value for a data set with outliers is to consider the median value. The median is a resistant measure of center which is not distorted by unusual values. For CSC PIM the median is 18 - not so different from the mean of 19.8. Interestingly enough, the median PIM for Castleton's opponents was 14. I'm not trying to make a value judgement here, just reporting data.

Ok bottom line is we agree CSC needs to improve on staying out of the box, statistically they are not the worst team in the country but def need improvement, but I'm not going to buy into the fact that CSC causes the other teams to be undisciplined...I'm sure they would like that power but ....
 
Re: Post all your cries whines, objections, complaints here

you're telling me 8 penalty minutes more per game is not significant over the course of a season??

Too many outliers to justify the use of the t-test with a sample of size less than 30. Using a non parametric test like the one I used is the only statistically responsible procedure, and the results suggest a trend, but are not significant.
 
Last edited:
Re: Post all your cries whines, objections, complaints here

As for USM, I do think they are making good strides and after getting some players back from injuries they had an impressive 4-2-1 record down the stretch, they have seemed to cut their penalty minutes and that is always a good thing......may want to get more than 15 shots on net thou to have any chance against Norwich :)


Prez doesn't know how to count shots: USM had 18!!!! :)

I am pretty sure CSC only had 20 so I wouldn't use that measuring stick!!! :)
 
Re: Post all your cries whines, objections, complaints here

Prez doesn't know how to count shots: USM had 18!!!! :)

I am pretty sure CSC only had 20 so I wouldn't use that measuring stick!!! :)

Ha...26 on the game sheet...and 3 went in the net.......not sure how many guys USM loses next year but if they stay healthy and find a little more O could be interesting
 
Re: Post all your cries whines, objections, complaints here

Too many outliers to justify the use of the t-test with a sample of size less than 30. Using a non parametric test like the one I used is the only statistically responsible procedure, and the results suggest a trend, but are not significant.

I think it's best to defer to the professor on this one. What did you teach again... ;)
 
Re: Post all your cries whines, objections, complaints here

Too many outliers to justify the use of the t-test with a sample of size less than 30. Using a non parametric test like the one I used is the only statistically responsible procedure, and the results suggest a trend, but are not significant.

t-test :confused: This is hockey not golf :p :rolleyes: ;)
 
Re: Post all your cries whines, objections, complaints here

Code:
<table>												
<tr><td>		TEAM	</TD><TD>	</TD><TD>	MIN	</TD><TD>	AVG MIN	</TD><TD>	DIFFERENCE		</TD></TR>	
<tr><td>	[b][color="red"]	St.Anselm	</TD><TD>	</TD><TD>	22	</TD><TD>	14	</TD><TD>	8	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	NEC	</TD><TD>	</TD><TD>	16	</TD><TD>	15	</TD><TD>	1	[/color][/b]	</TD></TR>	
<tr><td>		Becker	</TD><TD>	</TD><TD>	10	</TD><TD>	17	</TD><TD>	-7		</TD></TR>	
<tr><td>		Brockport	</TD><TD>	</TD><TD>	10	</TD><TD>	15	</TD><TD>	-5		</TD></TR>	
<tr><td>		Colby	</TD><TD>	</TD><TD>	8	</TD><TD>	13	</TD><TD>	-5		</TD></TR>	
<tr><td>	[b][color="red"]	Bowdoin	</TD><TD>	</TD><TD>	23	</TD><TD>	18	</TD><TD>	5	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	Skidmore	</TD><TD>	</TD><TD>	14	</TD><TD>	13	</TD><TD>	1	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	Norwich	</TD><TD>	</TD><TD>	10	</TD><TD>	9	</TD><TD>	1	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	Morrisville	</TD><TD>	</TD><TD>	72	</TD><TD>	21	</TD><TD>	51	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	J&W	</TD><TD>	</TD><TD>	59	</TD><TD>	28	</TD><TD>	31	[/color][/b]	</TD></TR>	
<tr><td>		Trinity	</TD><TD>	</TD><TD>	10	</TD><TD>	14	</TD><TD>	-4		</TD></TR>	
<tr><td>		Wesylan	</TD><TD>	</TD><TD>	10	</TD><TD>	17	</TD><TD>	-7		</TD></TR>	
<tr><td>	[b][color="red"]	Potsdam	</TD><TD>	</TD><TD>	33	</TD><TD>	19.5	</TD><TD>	13.5	[/color][/b]	</TD></TR>	
<tr><td>		UMASS Boston	</TD><TD>	</TD><TD>	8	</TD><TD>	13	</TD><TD>	-5		</TD></TR>	
<tr><td>	[b][color="red"]	Babson	</TD><TD>	</TD><TD>	14	</TD><TD>	13	</TD><TD>	1	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	Hamilton	</TD><TD>	</TD><TD>	39	</TD><TD>	15	</TD><TD>	24	[/color][/b]	</TD></TR>	
<tr><td>		Amherst	</TD><TD>	</TD><TD>	8	</TD><TD>	12	</TD><TD>	-4		</TD></TR>	
<tr><td>	[b][color="red"]	Tufts	</TD><TD>	</TD><TD>	26	</TD><TD>	18	</TD><TD>	8	[/color][/b]	</TD></TR>	
<tr><td>		Conn College	</TD><TD>	</TD><TD>	14	</TD><TD>	17	</TD><TD>	-3		</TD></TR>	
<tr><td>	[b][color="red"]	S,Maine	</TD><TD>	</TD><TD>	25	</TD><TD>	15	</TD><TD>	10	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	UNE	</TD><TD>	</TD><TD>	69	</TD><TD>	22.3	</TD><TD>	46.7	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	Norwich	</TD><TD>	</TD><TD>	25	</TD><TD>	9	</TD><TD>	16	[/color][/b]	</TD></TR>	
<tr><td>		St.Michaels	</TD><TD>	</TD><TD>	14	</TD><TD>	17	</TD><TD>	-3		</TD></TR>	
<tr><td>		Williams	</TD><TD>	</TD><TD>	8	</TD><TD>	13	</TD><TD>	-5		</TD></TR>	
<tr><td>	[b][color="red"]	Middlebury	</TD><TD>	</TD><TD>	24	</TD><TD>	11	</TD><TD>	13	[/color][/b]	</TD></TR>	
<tr><td>	[b][color="red"]	NEC	</TD><TD>	</TD><TD>	18	</TD><TD>	15	</TD><TD>	3	[/color][/b]	</TD></TR>	
<tr><td>		Babson	</TD><TD>	</TD><TD>	12	</TD><TD>	13	</TD><TD>	-1		</TD></TR>	</TABLE>
 
Re: Post all your cries whines, objections, complaints here

Too many outliers to justify the use of the t-test with a sample of size less than 30. Using a non parametric test like the one I used is the only statistically responsible procedure, and the results suggest a trend, but are not significant.

Can you regress it across other teams? Or is that what you did?
 
Back
Top