WEBVTT

00:00:00.000 --> 00:00:05.100
<b><h4>What sort of data are you collecting and what methods are you using to analyse your findings?</h4></b>

00:00:05.100 --> 00:00:05.190
<b>Dr Erika Mancini, Reader in Biomedical Structural Biology, University of Sussex</b>

00:00:05.190 --> 00:00:31.510
In my field of research, the primary outputs are images of protein structures and that are obtained via X-ray crystallography and cryo-electron microscopy and we complement that with a variety of other techniques. The images that we collect are used to produce three-dimensional models of protein structures. And we then are able to analyse them and to compare them between each other. 

00:00:31.510 --> 00:00:46.560
So, for example, you could look at a protein and compare it to different proteins, or you can look at a protein, and you can compare it to different stages of its life inside the cell. So it's almost like providing atomic snapshots of the protein. 
<hr />

00:00:46.560 --> 00:00:52.620
<b><h4>How do you measure/assess significance? Do you ever drop or ignore some data/findings?</h4></b>

00:00:52.620 --> 00:01:16.090
<b>Dr Erika Mancini:</b> In my field of structural biology there are several ways in which we assess significance of the data. So, for example, coming back to cryo-electron microscopy, in order to obtain a protein model, we collect lots of raw data. The raw data is then divided into two separate data sets, and each of these data sets will be used to produce a independent model. 

00:01:16.090 --> 00:01:40.350
We then compare these two models. And the extent to which these two models are similar or the same gives us a measure of the significance, of the exactness, of this protein structure model. In some cases, it is appropriate to drop some of the data when it's done for a reason, and it's very well documented. 
<hr />

00:01:40.350 --> 00:01:46.000
<b><h4>Do you consider different ways of interpreting your findings?</h4></b>

00:01:46.000 --> 00:01:46.050
<b>Dr Pete Etchells, Reader in Psychology and Science Communication, Bath Spa University</b>

00:01:46.050 --> 00:02:12.100
I think it's right to think about different ways in which you actually interpret your findings. I think that's fine to do as long as you don't do it after you've collected your data too much and start fishing around so, again, a really good reason to have pre-registration plans as it really forces you to think about what the right hypothesis is, what direction that hypothesis might go in is, and try and stick to that as much as you can. 

00:02:12.100 --> 00:02:34.190
What I'm very concerned about in psychology is when we collect data, we have a vague hypothesis, and we collect data, and then we change our hypothesis based on what the data tell us. I think that's a really dangerous route to go down. So that's not to say that you can consider alternative reasons why you might get the finding that you've particularly got, but you still need to look at it in the context of that original hypothesis that you devised. 
<hr />

00:02:34.190 --> 00:02:39.860
<b><h4>What do you do to try to avoid bias?</h4></b>

00:02:39.860 --> 00:03:05.810
<b>Dr Erika Mancini:</b> It is very important to avoid bias, and that is at every stage of our research, so starting from the planning, the way we asked the question, through to what measurements we do, onto the analysis of data, and finally, at the stage of publication. I think the best way to avoid bias is by working as a team, by introducing many people looking at the same data with lots of different pairs of eyes. 

00:03:05.810 --> 00:03:39.660
So I usually try to avoid bias by having a team of people working on similar subjects so that they can all work towards hypotheses together and not having one preferred option over another and by surrounding myself by a team of collaborators, external colleagues that help me guide through research. It is always important to present your data at conferences, small meetings so that you can discuss your ideas, and you can try and avoid bias as much as possible. 