Dusting off the blog

It sure has been a while since I last thought about this blog. Over the last couple of days, I have been dealing with a statistics college class project. This project, I figured I would do some weather analysis for Maine.

One of the biggest stories in the news today is Global Warming or Climate Change. You can catch up on it on Wikipedia. As part of my project, I wanted to evaluate whether we can see evidence of it here in Maine.

My data source was the National Climatic Data Center which holds climate data recorded in the United States. I chose Augusta, Maine's surface observations to explore since they had an observational record from 1948-present.

My first interest was determining if the Month of July was getting hotter over time. After compiling the data, I graphed this chart:

The trend line shows that July is not getting hotter. Although, some early 1950 years did throw this off, namely the heat waves in July 1952 and 1955. But in general, we can't easily see if global warming is impacting the month of July.

So, I fell back to looking at this more broadly. What if I simply averaged the highs for the entire year? This produced a chart:

In this data, the linear trend line clearly indicates a warming trend. While the 1950s were warm, they are fewer in number than compared to the years 2000 and beyond.

The IPCC report states the following:

From 1906 to 2005, Earth's average surface temperature rose by 0.74±0.18 °C. The rate of warming almost doubled in the last half of that period (0.13±0.03 °C per decade, against 0.07±0.02 °C per decade). ("Climate Change 2007: Working Group I: The Physical Science Basis". IPCC AR4. 2007.)

Does this data set relate to the IPCC's observation that the global temperatures have been rising 0.126°F (0.07C) every ten years? Yes, but not quite at the same rate. In this data set, annual high temperatures at Augusta, ME have been rising 0.1°F (0.05C) every ten years. A slightly lower rate than observed by the IPCC.

I have yet to compile the probability and confidence interval statistics, but I thought this was interesting enough to share.