| 摘要: | 氣候變遷正發生於中美洲，極端事件的強烈及高頻率的變化就是一種表現方式。根據IPCC(政府間氣候變化專門委員會)的報告指出，太平洋沿海將會有更嚴重氣候變化，也相當於薩爾瓦多所在地。在薩爾瓦多，大部分的生產活動基於廣大的自然生態系統。主要行業中，氣候變化的影響可能是重要的自然生態系統、水資源、海岸帶、農業、經濟以及人類健康。氣候變遷在許多方面將面臨更多的挑戰。然而，農業是最不容爭辯受氣候變化的影響 (IPCC, 2007)。藉由這個理由，為了尋找玉米、豆類、咖啡和甘蔗在薩爾瓦多產品的趨勢以及尋找與氣候因素的關聯性而設計了這項研究。另一方面，在薩爾瓦多，農業的部分在國家經濟發展是特別的重要。尤其在最近十年中，農業在每年所佔總GDP值往往超過11%，甚至在2014到達12% (Avelar 2015)。因此這項研究也分析了氣候因素對於一些經濟指標的影響。
首先，透過使用簡單的移動平均、加權移動平均值，並為每個氣候，農業和經濟指標累計移動平均預測模型設計。之後，藉由尋找均方根誤差為每個指標來探究及比較其模型的精確性。這項結果顯示出在給定變數的情況下，這三種逼近法之中最準確的理論是簡單移動平均，因為其包含較低的均方根誤差的結果。
最後，這項研究透過散佈圖分析、標準差以及平均值等統計分析，探討在不同的氣候因素對於經濟指標及農業生產指標之間的關聯性。從指標觀察到的相互關聯性將在各章節中做詳細之說明。
;Climate change is occurring in Central America, and one manifestation is changes in the frequency and intensity of extreme events. According to the IPCC (Intergovernmental panel of climate change) the effects of climate change will be more severe along the Pacific coast of Central America where El Salvador is located. In El Salvador, most of the country’s production activities are based on its extensive natural ecosystems. Major sectors in which the impacts of climate change could be important are natural ecosystems, water resources, coastal zones, agriculture, economy, and human health. Climate change will augment the challenges in many dimensions. However, agriculture is inarguably the sector most affected by climate change (IPCC, 2007). For that reason, this study is designed in order to find the production trends of corn, bean, coffee and sugar cane in El Salvador and to find their correlations with climatic factors. On the other hand, in El Salvador, the agricultural sector is especially important in the economic development of the country. In this decade its contribution to the total GDP has always been higher than 11%, reaching 12% in 2014 (Avelar, 2015). Therefore, this study also analyses the impacts of the climatic factors on some economic indicators.
First, by using simple moving average, weighted moving average, and cumulative moving average as a forecasting approach for climatic, agricultural and economic indicators is carried out. After that, we explored and compared the accuracy of each moving average method by finding the root mean square error for each indicator. The results indicate that for the given variables the most accurate theory among three approaches is the simple moving average because the lower root mean square error results are obtained with it.
Finally, this study explores the correlations among the different climatic factors on the economic indicators and agricultural production indexes by applying a statistical analysis using scatter diagrams. The correlations among indicators are explained in details to conclude the three interrelations among climatic, agricultural and economic indicators. |
