B055b - Caseload history v3.0
Caseload history
9,000
8,000
7,000
6,000
5,000
4,000
FOI
3,000
DP
2,000
1,000
Total
0
9
9
9
9
0
9
I
0
9
0
0
0
0
0
0
0
0
1
0
O
0
0
0 F
r
 
2
 
2
 
2
t
 
2
 
2
 
2
p
n
g
c
c
b
r
 
2
A
J
u
u
e
e
p
A
O
D
F
A
FOI caseload trends
DP caseload trends
8,000
1,600
7,000
1,400
6,000
1,200
5,000
1,000
DP
FOI
4,000
Smoothed
800
Smoothed
1,467
1,447
1,506
7,073
1,418
1,374
6,688
6,958
1,338
6,576
Holt Winters
1,295
Holt Winters
6,326
6,445
6,348
6,222
6,304
6,511
3,000
600
5,796
1,155
1,048
1,044
1,057
2,000
400
200
1,000
0
0
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
2009 2009 2009 2009 2009 2009 2009 2009 2009 2009 2009 2009 2010
2009 2009 2009 2009 2009 2009 2009 2009 2009 2009 2009 2009 2010
Smoothed
Exponential smoothing is used to give an idea of the trend of the caseload, based on a weighted average of past values. This weighting is more biased toward recent figures, so that the results of the latest few months affect the trend more 
strongly.
Holt-Winters
Non-seasonal Holt-Winters exponential smoothing also weights for trend, further smoothing away any oscillating results. This use of trend also allows the future caseload for the next three months to be estimated.
This report was prepared for you by the Operations Support Team

---