The Possible Impacts of Climate Change on Food Insecurity

Research Question / Hypothesis

H0 = there is no statically significant linear model that can predict food insecurity in both least developed and developed countries as the result of the global climate change.

Ha = there is a statically significant linear model that can predict food insecurity in both least developed and developed countries as the result of the global climate change.

Is the slope significantly different than 0? (t-test)

• Ho = b1=0, b2 = 0, b3 = 0
• Ha = b1?0, b2 ? 0, b3 ? 0

METHOD

To examine the relationship between food insecurity and the exposure to disasters (floods, droughts, and extreme weather events), thirty countries have been randomly selected. For this experiment, food insecurity is viewed as the effects of which floods, droughts, and extreme weather events that each country may experience over the course one year—2009. The percentage of droughts, floods, and extreme weather recorded in percentage is used to predict the food insecurity that each country was reported by FAO (2014). Dataset for both variables are from the same year of 2009.

This paper intends to make analysis on the global exposure of climate change in 30 countries using the percentage of droughts, floods and extreme weather events under the effects of climatic conditions. A dataset of 30 countries for the percentage of flood, droughts, and extreme events were combined with a national food insecure in 2009. To run this analysis, two continuous variables are used, these variables are (1). Food insecurity people experience in each country (in percentage) which is the dependent variable; (2). The predictor (IV) – percentage of population that experiences droughts, floods, and extreme weather events.

Results

After running a simple linear regression, the overall measure shows an association reflecting in this model, the dependent variable (food insecurity) could be explained by the independent variable (IV-- the percentage of population experienced droughts, floods, and extreme temperatures). According to the model summary (figure 1), R-Squared value indicates that the correlation between the observed and predicted values of food security is 27.8%. My model explained 27.8% of the variability of food insecurity.

The F statistic (figure 2) was greater than one. A statistically significant model was built to predict the level of food insecurity in a country using the percentage of population experience droughts, floods, or extreme temperature. There is a linear model to predict the level of food insecurity in a country based on the percentage of population experience droughts, floods, or extreme temperature. My model explains more variance than it leaves unexplained and is statistically significantly better than the mean at explaining the amount of lead in the park’s soil based on its distance from the road. F(dfM, dfR) = F (1, 28) = 2.345, p 0.05.

Discussion/ Analysis

The values of the gradient and intercept shows that the slope (b1 = -0.515) is significantly different from 0 (t=.1531, p

Cite this page