Publications by apeescape
Cherry Picking to Generalize ~ retrospective meta-power analysis using Cohen’s f^2 of NASA temp + visualization
Previously, I plotted a grid of NASA GISS global temps in ggplot2 to show general trends by the brute force method. Here, I will again use the brute force method to do a simple power analysis on a portion of the data (data here). The general aim is to figure out what the minimum sample size is needed to show strong confidence in the significance ...
5498 sym R (3861 sym/1 pcs) 30 img
R and Google Earth ~ comparing tuna tracks vs. Gulf of Mexico oil spill extent
There is a lot of interest in how the Gulf of Mexico oil gusher will affect the ecosystem and its marine species. One such species is the Western Atlantic bluefin tuna that holds the Gulf of Mexico as one of its major spawning grounds. Recent tag data show that the location of the gusher is also very close to its spawning ground both spatial and ...
1972 sym R (1789 sym/1 pcs) 18 img
Global Temperature Proxy Reconstructions ~ Bayesian extrapolation of warming w/ rjags
Update: fixed projection. There are a bunch of “hockey sticks” that calculate past global temps. through the use of proxies when instrumental data is absent. There is a new one out there by McShane and Wyner (2010) that’s creating quite a stir in the blogosphere (here, here, here, here). The main take out being, that the uncertainty is too ...
5743 sym R (11680 sym/2 pcs) 22 img
Global Temperature Proxy Reconstructions ~ now with CO2 forcing
Previously, I did a simple Bayesian projection of recent temperature using proxy data and the methods shown in McShane and Wyner (2010). I showed that when you take out the last 30 years of data (1969~1998), the projection does not track the recent uptick in temperatures well. The “projection” is a simple unparametric bootstrap which draws pa...
5416 sym R (8256 sym/2 pcs) 22 img
Parametric Bootstrap Power Analysis of GISS Temp Data
Previosly, I calculated a bunch of ad-hoc power curves from GISTEMP data. Power is essentially a reframing of the p-value, to see the significance of the trend lines in the global temps. However, power calculations are inherently very noisy, hence, my ad-hoc way of aggregating the data. Another method is to bootstrap through the responses from th...
2931 sym R (2192 sym/1 pcs) 20 img