Traditionally within the different disciplines of earth science the scientists are divided into two groups: modelers and observationalists. In this view the modellers are those who do theory, possibly with pen and paper alone, and the observationalist go into the field and get dirty hands. That this view is a little bit outdated, won’t be anything new. In my opinion, it really started with the establishment of remote sensing that this division reunited (Yes, reunite, because in the old days, there were a lot of scientists who did everything). As I am a learned meteorologist, from my view it is quite common that this division is not really existent anymore. Both types of scientists sit in front of their computer, both are programming and both have to write papers with a lot of mathematical equations. In other fields, the division might be still more obvious (e.g. Geology), but for many its only the type of data someone is working with, which classify someone as observationalist or modeller. For me this division is sometimes quite problematic. It is common to get the question which type of scientist you are and the only true answer for myself is “non of them”. Or is it “both of them”? As many colleagues I am in the end a data scientist (I will in a future post explain in more detail what that means), perhaps not as specialised for one side of the data as others, but still I am working with observations as well es with models.
Statistics, which got in the past decade a real push forward, is something which does not fit into the traditional classification. In general it sits between the two fields as a middleman, perhaps leaning more to one of the two sides, depending on the field and the scientists within it. It is the methodology, which brings both together, combine or compare them and deliver a different view on the physical system at hand. Nevertheless, there are a lot of prejudices on statistics still present. Some still think statistics is objective and others that its results are absolute. Both is of cause outdated, but it is still quite common to either read it in the literature or see the use of these assumptions in the justification of some work.
These and other misunderstandings led to the view that statistics are just some tools, which correctly applied lead to the “correct” result. I would argue that it is more than that. In my view (which is of cause heavily biased), it is a field within earth science on the same level as observations and modelling. This does not mean, that observers or modellers cannot do statistics. As I have written above, the divisions in some heads are not necessarily existent anymore anyway. It means that it has its own philosophy, its own view points and its own right of existence, independent of the others. Of cause, statistics without real data can be quite boring, but using synthetic data is quite usual.
Nevertheless, only the combination of the three fields (and all its subfields) can lead to the results, which solve the scientific questions of the future. We definitely need observations, because without it we are just operating in a unjustified thought-experiment. Nice to have, but does not necessary have something to do with the “truth”. We definitely need models, as we want to explain the observations, know more of their causes and want to see the simple structures in an otherwise complex world. And yes, we need statistics, to evaluate how sure or unsure we are on the results, to find out which assumptions in the two other fields are necessary to get to them and to make an educated guess on the developments during the past and in the future.