NEWxSFC - Interim Summary…as of 25 FEB 2010					AVG SUMSQ				AVG STP					AVG Total Absolute				AVG Absolute				Mean RSQ
Previous Ranks	Rank	Forecaster	Class	Total STN 4casts	Error (")	Error Z	% MPRV over AVG	Rank	4cast (")	Error	Error Z	% MPRV over AVG	Rank	Error (")	Error Z	% MPRV over AVG	Rank	Error (")	Error Z	%MPRV over AVG	Rank	RSQ	RSQ Z	% MPRV over AVG	Rank	Forecaster
1,1	1	ilibov	Senior	120	403	-0.903	41%	5	128.7	8.0	-1.110	77%	2	56.67	-0.728	19%	7	2.39	-0.861	25%	6	60.2%	1.089	32%	7	ilibov
3,3	2	donsutherland1	Chief	126	282	-0.894	56%	2	145.8	18.3	-0.640	49%	6	54.25	-1.063	35%	2	2.17	-1.054	35%	2	70.8%	0.988	37%	2	donsutherland1
2,2	3	Shillelagh	Senior	104	523	-0.691	24%	8	107.9	35.7	0.339	-23%	14	61.56	-0.832	19%	7	2.90	-0.496	13%	9	65.4%	0.821	24%	7	Shillelagh
5,6	4	millersville_bauers	Rookie	120	421	-0.667	30%	6	130.7	30.3	-0.051	7%	10	66.69	-0.376	11%	9	2.71	-0.518	15%	7	58.0%	0.538	19%	6	millersville_bauers
6,4	5	herb@maws	Senior	116	440	-0.658	37%	6	143.4	18.4	-0.560	41%	8	61.99	-0.650	21%	5	2.72	-0.533	18%	6	59.4%	0.412	15%	6	herb@maws
10,9	6	Donald Rosenfeld	Senior	126	438	-0.457	31%	6	127.5	25.9	-0.211	15%	7	60.54	-0.715	22%	4	2.42	-0.769	24%	4	54.6%	0.393	17%	5	Donald Rosenfeld
9,10	7	weatherT	Intern	126	352	-0.430	26%	6	99.3	40.5	0.088	-6%	10	61.76	-0.314	14%	6	2.42	-0.518	18%	6	55.5%	0.567	22%	6	weatherT
12,11	8	TQ	Senior	118	400	-0.182	15%	9	97.3	31.3	-0.219	13%	9	65.46	-0.189	9%	8	2.77	-0.083	6%	9	45.1%	-0.172	-1%	9	TQ
4,5	9	Raven	Senior	116	571	-0.036	-9%	7	160.5	31.1	0.079	8%	10	74.39	0.060	2%	9	3.23	0.197	-1%	10	59.0%	0.276	12%	6	Raven
11,12	10	Mitchel Volk	Senior	117	781	-0.014	2%	13	158.8	42.6	0.333	-23%	14	83.40	-0.312	4%	11	3.53	-0.171	2%	12	54.9%	0.002	0%	13	Mitchel Volk
15,13	11	Roger Smith	Rookie	131	711	0.166	-13%	10	202.8	66.1	0.769	-71%	12	98.64	0.408	-15%	11	3.75	0.229	-10%	10	59.6%	0.298	13%	8	Roger Smith
13,14	12	snowman	Senior	116	953	0.584	-19%	15	116.2	35.4	0.325	-21%	12	95.63	0.279	-9%	13	4.13	0.479	-13%	14	37.9%	-1.012	-32%	16	snowman

There have been seven (7) snowstorm forecasting Contests to as of 25-FEB-10. Under the ‘two-thirds’ rule…forecasters who have entered at least five (5) forecasts are included in this interim summary.

To qualify for ranking in the Interim and final ‘End-of-Season’ standings…a forecaster must enter at least two-thirds of all Contests.  If a forecaster has made more than enough forecasts to qualify for ranking…only the lowest SUMSQ Z-scores necessary to qualify are used in the computing the average.  IOW…if you made nine forecasts…only your six best SUMSQ Z-scores are used to evaluate your season-to-date performance.  You can think of it as dropping the worse quiz score before your final grade is determined.  The reason we have this rule is to 1) make it possible to miss entering a forecast or two throughout the season and still be eligible for Interim and ‘End-of Season’ ranking and 2) encourage forecasters to take on difficult and/or late-season storms without fear about how a bad forecast might degrade their overall 'season-to-date' performance score(s).

The mean normalized ‘SUMSQ error’ is the Contest/s primary measure of forecaster performance.  This metric measures how well the forecaster/s expected snowfall 'distribution and magnitude' for _all_ forecast stations captured the 'distribution and magnitude' of _all_ observed snowfall amounts.  A forecaster with a lower average SUMSQ Z Score has made more skillful forecasts than a forecaster with higher average SUMSQ Z Score.

The 'Storm Total Precipitation error’ statistic is the absolute arithmetic difference between a forecaster/s sum-total snowfall for all stations and the observed sum-total snowfall. This metric…by itself…is not a meaningful measure of skill…but can provide additional insight of forecaster bias.

The 'Total Absolute error' statistic is the average of your forecast errors regardless of whether you over-forecast or under-forecast. This metric measures the magnitude of your errors.

The 'Average Absolute Error' is the forecaster/s ‘Total Absolute Error’ divided by the number of stations where snow was forecast or observed.

The ‘RSQ error’ statistic is a measure of the how well the forecast captured the variability of the observed snowfall. Combined with the SUMSQ error statistic…RSQ provides added information about how strong the forecaster/s ‘model’ performed.