Sangtien Youthao *, Mullica Jaroensutasinee , Krisanadej Jaroensutasinee
CX-KURUE & Computational Sience Graduate Program, Institute of Science, Walailak University, 222 Thasala District, Nakhon Si Thammarat, 80160, Thailand.
This study tested the forcasting model from Timeseries of influenza cases per month data in Nakhon Si Thammarat between 1994 to 2003 with a total of 120 months. Calculating forcasting values from 7 timeseries forcasting models by Mathermatica. In this study calculated forcasting values from each model and calculated error values between actual values and forcasting values. After calculated that to compare error values from each models by using analysis of variance and calculated post test by using Student Newman Keuls method for checking the good model and different or not from other model. The result from this study showed that minimum error values from SES0.8 model (Single Exponential Smoothing Model by using constant values 0.8 ) and not different from Single Exponential Smoothing Model by using constant values 0.8 and start value at 0.2 (SES0.8,0.2) but result of two model different from other model and maximum error values from Global Linear Trend Model (GLT).
Methodology: Timeseries forcasting models in this study were chosen from more than 20 models as follow in table.
Table 1 Timeseries model
Model |
Name |
1 |
Global Constant Mean Model (GCM) |
2 |
Single Moving Average Model (SMA) |
3 |
Single Exponential Smoothing using constant value 0.8 Model (SES0.8) |
4 |
Single Exponential Smoothing using constant value 0.8 start at 0.2 (SES0.8,0.2) |
5 |
Global Linear Trend Model (GLT) |
6 |
Double Moving Average Model (DMA) |
7 |
Brown’s Linear Exponential Smoothing Model (BLES) |
Calculation all of forcasting values from 7 models by using statistics and mathermatics command from Mathermatica. The technique were chosen in this study for checking different of error value from forcasting value and actual values in 120 month of influenza cases per month data were ANOVA (Analysis of Variance). In post test of ANOVA technique were chosen Student Newman Keuls technique for comparison mean test to find different or not from 7 models.
Table 2 and SD of error values from model
Error of Model |
Mean( ) ± SD |
GCM |
36.8206 ± 57.512 |
SMA |
45.6102 ± 56.8118 |
SES0.8 |
12.145 ± 15.5268 |
SES0.8,0.2 |
12.6777 ± 15.8907 |
GLT |
98.6625 ± 101.172 |
DMA |
68.9368 ± 85.5289 |
BLES |
22.7559 ± 28.6806 |
Table 3 Comparison mean of error value from model
Source of Variation |
df |
SS |
MS |
F |
Model |
3 |
26.2935 |
8.7645 |
6.12795* |
Error |
16 |
22.884 |
1.43025 |
|
Total |
19 |
49.1775 |
|
|
Table 4 Comparison Mean of error from seven models by Post test ANOVA Student Newman Keuls technique
Error of Model |
Rank |
StudentNewmanKeuls Test |
SES0.8 |
1 |
|
SES0.8,0.2 |
2 |
|
BLEBrown’s Linear Exponential Model |
3 |
|
Global Constant mean Model |
4 |
|
Single Moving Average |
5 |
|
Doble Moving Average |
6 |
|
Global Linear Trend Model |
7 |
|
Figure 1 Observal Influenza cases 1994-2003 and its forcasting values from SES0.8 Model
Results, Discussion and Conclusions
From table 2 data of influenza cases in Nakhon Si Thammarat taken in seven model to study. The result showed the Single Exponential Smoothing Technique Model used constant value 0.8 (SES0.8) had minimum error value.
From table 3 testing by ANOVA calculated to test comparison means of error values had significant at 0.01 (F 3,16 = 6.12795 , P<0.01). Result from ANOVA test that showed the error value of one pair or more had different error value.
From table 4 taken Student Newman Keuls test for check error values of forecasting value and data of Influenza cases resulted showed that the Single Exponential Smoothing Technique Model use constant 0.8 not different from error values by Single Exponential Smoothing Technique Model use constant 0.8 and start at 0.2 but two models took the error value different from other models. Number of influenza cases in Nakhon Si Thammarat had pattern nearly Single Exponential Smoothing Model.
Result of this study when we try to take double exponential smoothing in Brown’s Linear Exponential Model for give the new forcasting value its had more error from single smoothing method. Its happen in the both technique Exponential smoothing and Moving average. The Global Linear Trend Model (GLT) had maximum error values showed that the data of influenza cases in Nakhon Si Thammarat had not pattern in linear.Acknowledgement: This study was supported by CX-KURUE WU Thailand. We thank the Nakhon Si Thammarat Province Health Office, Ministry of public Health for influenza data.
1.Lohjeerachunkul W., Sutayarukwit S., Jitathawat J. and Pinsukanjana A. (1996). Forcasting Technique. Applied Statistics Centre: NIDA, Bangkok,16-111.
2.Mugglin, A.S.,Cressie,N. and Gemmell,I.(2002). Hierarchical statistical modeling of influenza epidemic dynamics in space and time. Stat. Med., 21, 2703-2721.
ไม่มีความเห็น