We have talked before about how the absence of evidence is not evidence of absence and how to plan sample sizes. This short video by Matt Asher, from the University of Toronto, takes an amusing look at power and sample size. As you can tell, it is written by a frustrated statistician!
If you have never used Endnote here is a short video which shows you how to do some key things.
Your writing will be a mixture of your own conclusions and those of others. How do you clearly indicate which is which? This page from the Learning Advisers at the University of Queensland’s Student Services works through an example to show you how to make it explicit whose idea was whose in your writing.
Looking back on this site over 2016 we have covered a lot! I hope you have found the site a useful source of information and inspiration for your research project. Here is a roundup of the year’s postings.
Productivity and looking after yourself
A thesis or dissertation is a big job and a long-term commitment that can be a struggle to get through at times. From time to time I find sites that give helpful advice about remaining productive and this year these included ones on approaching planning with processes instead of goals, checking your progress each month, avoiding procrastination, and productive writing. In order to be productive you need to look after yourself, and mindfulness can help as well as giving yourself a break.
Critical thinking and a scientific approach
Thinking is the nuts and bolts of your research. It is how you turn ideas into a structure and hold them all together. We discussed science as a way of thinking and critical thinking techniques, and also how the process of writing helps think and structure your ideas.
Understanding statistics so you can critically evaluate
Having a basic understanding of some statistical principles is important for being able to critically evaluate the research you are reading, and also helps you plan your study design. Explanations of basic statistical concepts can help get you started. We also talked about statistical concepts that affect interpretation of results including bias, missing data, effect size, study design, and concepts around causation. The posting about reading epidemiological reports also gave further pointers that help you evaluate clinical papers.
What to say
I came across quite a few sites that give helpful advice about what to say and how to make the argument that your report must make. In two posts this year we talked about the overall structure of your report and what goes where. We also talked about how a research question is important to help you structure literature reviews. Aspects of making your argument include articulating the problem you are writing about, writing defensively, and using counter argument. Effective transitions are an important way to guide your reader through your document and both avoiding hedging and appropriately using boosters help you say something meaningful.
Being creative with figures and tables
There is a real art to constructing tables and figures that convey information elegantly and coherently, so I like to point out sites that help you with this whenever I can. This year two sites attracted my attention, which you will find here and here.
When you are stuck
Editing and revising
It is such a lot of work to get to a first draft stage that it often seems impossible to contemplate revising your work. But this phase of writing can also be very satisfying. You can find some help for spotting problems you need to fix in this post, and another post shows you a technique for revising by chopping up your work into sections.
Getting advice and feedback from other readers is a key piece of advice in writing a great report and when you have received feedback from reviewers you need to take it on board, as discussed in answering your reviewer.
Paying attention to the mechanics of writing can make your writing clearer and more fun to read. Posts about long sentences, paragraph problems, vague antecedents, compound adjectives, long subjects, and using quotes might sound dry and complicated but they cover issues that cloud many a piece of writing.
Using your tools
In my experience, people often feel at a loss with software and don’t really get the best out of it. Computers can certainly be frustrating, but if you know more about how software works you will be much more productive. Some time spent finding out how to do things is well worth the saving in time later.
A word processor and reference management software are absolute musts for writing dissertations, and usually I speak about Word and Endnote which are what I and my students use mostly. This year I pointed you to information about formatting your paragraphs in Word (here and here), and how to use tools such as the comments tool, cross references, and the status bar. Two important skills with Endnote are customising Endnote citations and formatting references so they don’t add extra initials or first names to your in text citations.
I use OneNote a lot, and this year I pointed out the docking feature which helps you take notes on other documents, webpages and so on. Other information that you might find useful includes how to use Google books to find things in your textbooks and how to use the Crossref website to find DOIs for your references.
Probably the most important tool of all when you are writing is having a good back up system. If you are not backing up, check out this post now!
Something for the holidays: an entertaining analysis of the survival of chocolates in hospitals. Enjoy and have a good break with friends and family.
Gajendragadkar RP et al (2013) The survival time of chocolates on hospital wards: covert observational study, BMJ 347 doi:10.1136/bmj.f7198
Cross references are really handy tools in Word when you are writing a long and complex document. They help by automatically keeping track of where things you are referring readers to are located in the document, and they update automatically if you need to change where things are.
So, for example, you may have several figures you need to refer to, and at some point you may need to move these around to different places in your document. What was originally labelled Figure 1, may need to change to be called Figure 3 and all the other figure names may need to change accordingly. Instead of manually having to change all the figure captions as well as all the places in the document you have referred to the figures, Word can do this for you automatically as soon as you move the figure. Can you see how helpful that would be?
This link will show you how to use cross references in your document. http://www.dummies.com/software/microsoft-office/word/how-to-put-cross-references-in-a-document-in-word-2016/
Do you have a tendency to use long words in your writing when you don’t need to? Do you write “commence” instead of just “begin”; “in order that” instead of “so”; “numerous” instead of “many”; “utilise” instead of “use”?
If a simple word accurately reflects what you want to say, then use a simple word. Your writing will be clearer and you will sound less pompous. This document from the Plain English Campaign has a list of simple alternatives to unnecessarily complicated words and phrases.
A stand alone literature review has a different purpose to a literature review that is part of a research study. When a literature review is part of a research study its purpose is to justify the research question that the study addresses. It needs to show readers what is already known, where the gap being addressed by the study is, and why the gap is important to fill.
In contrast, the purpose of a stand alone literature review is to answer a question itself, based on analysis, evaluation, and synthesis of published literature. The question may be a general one like “what is currently known about..…” or “what does current evidence suggest is the best strategy for…..” but it can also be a more specific one such as “what factors are associated with the development of…..” or “which therapy for (condition) has the best long term prognosis…”. The question being answered needs to be an important one to answer and you will need to explain to readers why it is important in the introduction to the literature review.
When planning your literature review, you may start with a general topic, but its important to work on defining a research question early on. In order to define your question you will need to do a lot of reading, and also perhaps create summaries of what you have read, but you will not really have started your review until you know what the question is that your review will answer. The research question provides the focus for your review by defining the topic more specifically and ensuring it is feasible. For more information about formulating a research question, see this post from Sheffield Hallam University.
Not long ago I posted about Hedging—where we qualify what we say or use cautious language that sometimes is so cautious and qualified that it doesn’t really make a point. In this article Pat Thomson talks about using boosters—words that give a sense of authority and strength to what you are saying.
A colleague directed me to a recently published study which examined the relationship between neuter status and joint disease in German Shepherds. We had an interesting discussion about the merits of the research methods, however the most significant flaw I saw in the study was in the conclusions the authors drew about their results.
The researchers found a statistical relationship between neutering dogs before one year of age and the occurrence of some types of joint disease. In their discussion they make it clear that they conclude that this association is causal, and that its direction is from neutering to joint disease. In other words they conclude that early neutering causes an increased risk of joint disease and they go on to propose possible mechanisms.
However, in concluding this the researchers fall into a trap that is easy to fall into. Firstly they assumed that the association they found was causal and secondly, that it was in one particular direction. Their study was designed to reduce the false detection of chance associations, however they did not discuss the (very real) possibility of other reasons for the association. One possibility is a relationships between whether owners are likely to neuter early and whether they are likely to do things which increase the chances of joint disease occurring or being detected. As an example, dogs selected for work, may be neutered because it is the organisation’s policy to do so, and the fact they are in work may increase the risk of joint disease or its detection, compared to pet dogs. This then means that there is a confounding variable—whether the dog belongs to this organisation—which links neutering to joint disease statistically, but with no direct association between neutering and joint disease. Such confounders can be accounted for in study designs, but they were not in this case, and therefore it is premature to conclude the relationship is causal.
Even if there was a reason to suspect a causal relationship, we need to be careful not to assume it is in one particular direction. This paper provides a good example of this. Although one could postulate (as the authors did) reasons why neutering might increase the risk of joint disease, one could also postulate reasons why joint disease might increase the risk of neutering. For example dogs with poor conformation, visible as pups, may be neutered because they are not good for showing or breeding, and then go on to develop detectable joint disease later.
For a previous post about the difference between correlation and causation see here . And here is the reference and link to the article about neutered German Shepherds and joint disease:
Hart, B. L., Hart, L. A., Thigpen, A. P. and Willits, N. H. (2016). Neutering of German Shepherd Dogs: Associated joint disorders, cancers and urinary incontinence. Veterinary Medicine and Science 2: 191–199. doi:10.1002/vms3.34 http://onlinelibrary.wiley.com/doi/10.1002/vms3.34/full