Download presentation
Presentation is loading. Please wait.
1
Global Warming: Is It True? Peter Fuller Odeliah Greene Amanda Smith May Zin
2
What is Global Warming? Global warming is the increase in the average temperature of the Earth's near-surface air and oceans since the mid-twentieth century, and its projected continuation.
3
Data We’re Using Our data showed monthly average temperatures in England from 1850-2008
4
Forecasting Goal Our purpose is to explore the validity of Global Warming with regards to temperature change in England.
5
Trace
6
Histogram
7
Correlogram
8
Unit Root Test ADF Test Statistic-14.22821 1% Critical Value*-3.4368 5% Critical Value-2.8635 10% Critical Value-2.5679 *MacKinnon critical values for rejection of hypothesis of a unit root. Augmented Dickey-Fuller Test Equation Dependent Variable: D(TEMP) Method: Least Squares Date: 06/02/08 Time: 03:02 Sample(adjusted): 1850:02 2008:04 Included observations: 1899 after adjusting endpoints VariableCoefficientStd. Errort-StatisticProb. TEMP(-1)-0.1919710.013492-14.228210.0000 C9.3749220.66801914.033910.0000 R-squared0.096427 Mean dependent var0.006635 Adjusted R-squared0.095950 S.D. dependent var5.168794 S.E. of regression4.914569 Akaike info criterion6.023338 Sum squared resid45818.22 Schwarz criterion6.029182 Log likelihood-5717.159 F-statistic202.4420 Durbin-Watson stat1.081641 Prob(F-statistic)0.000000
9
How we go about fixing the data We seasonally differenced the model using a new variable: SDTemp=Temp-Temp(-12)
10
Our best model Our best model is: SDTemp C AR(1) AR(2) MA(12) AR(19) w/ ARCH (1) and GARCH (0)
11
Estimation Output
12
Actual, Fitted Residual Graph
13
Histogram
14
Correlogram
15
ARCH LM Test ARCH Test: F-statistic7.80E-05 Probability0.992956 Obs*R-squared7.81E-05 Probability0.992951 Test Equation: Dependent Variable: STD_RESID^2 Method: Least Squares Date: 06/02/08 Time: 03:41 Sample(adjusted): 1852:09 2008:04 Included observations: 1868 after adjusting endpoints VariableCoefficientStd. Errort-StatisticProb. C1.0005820.04527422.100450.0000 STD_RESID^2(-1)-0.0002040.023149-0.0088300.9930 R-squared0.000000 Mean dependent var1.000378 Adjusted R-squared-0.000536 S.D. dependent var1.681044 S.E. of regression1.681494 Akaike info criterion3.878313 Sum squared resid5275.970 Schwarz criterion3.884236 Log likelihood-3620.344 F-statistic7.80E-05 Durbin-Watson stat2.000032 Prob(F-statistic)0.992956
16
Within Sample Forecast
17
Recoloring our Within Sample Forecast
18
Forecasting Ahead
19
Recoloring our Forecast of the Future
20
Seasonal Dummies
21
Conclusion We must look to other data such as rainfall, sea levels, ocean temperatures, C0 2 data to say that global warming does exist.
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.