While adding information I had gleaned from several new papers I have read over the last week I realised that I had made an error in my analyses. The power analysis of trend is a method of detecting the power of a time series based on simple linear regression models and was developed by Gerrodette in 1987. The coefficient of variation (CV) which is the standard deviation (SD) divided by the mean, is central to this analysis. I noticed this evening that I had been rounding this value incorrectly and when I corrected this flaw it made all of the lower precision data unusable as they were no longer able to accurately show any change. I have now realised that I have been calculating these statistics incorrectly as well. In that I have been rounding these smaller values by digits rather than significant figures.
Rounding by significant figures is different in that the information stored within a number means more than simply what the numbers are. Their placement around the decimal place and how many zeroes are in front of any real numbers is relevant, too. So data collected with a precision of 0.1 must have more than one significant figure past the decimal. But I have incorrectly been rounding by decimal places this whole time, meaning if the SD of a time series with a precision of 0.1 is found to be 0.043443778…, I have been rounding it down to 0.0 as this is the closest value at a precision of 0.1 however!; it would be more appropriate to round this value to 0.04. If the precision had been 0.01, then it would be best to round the previous example to 0.043, and not 0.04 as I would have done previously. This is a pretty stupid mistake to have made and is really going to allow my analyses to run a lot more smoothly… but then I noticed something even worse.
As mentioned previously, CV is at the heart of the power analysis of trend. This is clearly explained in Gerrodette (1987, 1991) and I assumed was the case with the function from the fishmethods package in R. Boy was I wrong! 🙁 It turns out they use proportional standard error (PSE) which is calculated by taking the standard error (SE) and dividing that by the sample size. This number is much much smaller than the SD for these same time series and so will likely cause the power of every time series to increase greatly. Why the authors of this package chose to use PSE rather than CV is confusing and unclear. And frankly rather annoying. I must now redo all of my analyses and re-write up my entire paper. Thankfully I have done everything in R so the analyses should be able to be reworked within a few hours. And much of the re-write will be small. But the work is there to do and must be done.
I have committed to wrapping up the necessary edits to my Chapter 2 before Saturday afternoon of this week. I am going to a Pink Floyd tribute show in Botrivier and would like to have my mind free of these issues for at least a day or two.
I have made quite a few changes to the code I am implementing and will likely make a few more before the week is out. Correcting what I have written previously to accurately reflect these changes is proving to be a slow process, but I am chipping away at it and the methodology and results section are finished.
Besides these edits I have been searching for articles to help with my 0.1C conundrum and may have found several, but I will need to read their methodologies to be sure. I have also finally come to terms with the fact that I must read the entirety of the IPCC report. This 167 page monster sums up everything that is currently known about climate change. I am 1/3rd of the way through it and picking away at it each day. I intend to incorporate much of what I learn here into my current article as well as most if not all of my future work. I really should have read this sooner. I believe it will hold the answers to several of the questions I am currently struggling with.
The current article I am working on is at least 90% done. Getting that last 10% is proving to be as much work as the first 90%. Many of the snags I have been passing over must now be addressed and a thorough search of the literature has not helped as I had hoped. I also need to redo a bit of the code, which may change some results. I also need to give the discussion more thought and write most of the conclusion. This is all proving to be rather daunting and is inhibiting my normal levels of can do spirit.
Though never one to sit still, I have been taking opportunity of my avoidance to get back into the Advanced R book. As I worked through the chapters I convert them into R code that my students can peruse to help sharpen their abilities. I will also be able to use what I learn in my personal studies as well as future classes/ courses. That is another thing I would like to see happen. I need to make that a reality at UWC. I have gone through the first five chapters of the book (out of 20), and chapter 6 covers functions. That is going to be exciting! I am considering teaching my lab mates how to write functions, but am deterred by the frank realisation that they will likely never use that knowledge… and I should rather focus on real things they will be able to use.
The PSSA was a very exciting experience. The range of topics covered in the lectures was massive. Much more than I had expected. I also succeeded at getting a lot of networking done and apparently did a pretty good job of making myself known as I was elected to serve as the PSSA student representative until the next PSSA in January of 2017, which will be held in De Hoop. I didn’t win any awards for my talk, unfortunately, but I will regroup and focus on having more kelp related science in my next one.
AJ was elected president and has big plans for the next conference. It will be the 30th PSSA and Rob Anderson and John Bolton are retiring that year. This will have a dramatic effect on the algal landscape of South Africa and we intend to make an event out of it worth remembering.
Team kelp has also taken strides forward. Besides showing a high level of spirit, we also had quite a few solid entries. People know who we are now and it gives us a good platform from which to move forward. One of the first steps is to get ourselves a clothing item. The logo and motto have already been sketched up and with a little refining they will be ready to go. We are currently looking at getting them put on hoodies. After this plan succeeds it can be taken a step further by looking for sponsors that want to have their brand associated with us. This relationship can take on many different forms and I have a lot of ideas brewing in my head.
But before I get too carried away with things I’m not really supposed to be focussing on I need to finally finish the first chapter I have been writing. I went through the chapter again today in it’s entirety to re-familiarise myself with it. There is still quite a bit of work to do, unfortunately I thought I had completed more of it than I have… I have also been scouring the literature looking for other papers that have talked about instrument precision for the last couple of days to no effect. As I still have a quite a bit of work to do to finish the paper I am going to get cracking on that before spending more time searching for corroborating literature.
The next paper is already in the works. Though I mustn’t get to far ahead of myself. I am going to look for any possible heat waves that may have occurred along the coast of South Africa since our records began. I;ll be using the in situ data as well as the satellite data for what will be my first of many papers comparing the discrepancies between the two.