We always say that statistics is just dealing with data. But we also know that informatics is also getting knowledge from data analysis. For example, bioinformatics people can totally go without biostatistics. I want to know what is the essential difference between statistics and informatics.

  • 7
    $\begingroup$ Nah, this is just because the word "informatics" has completely lost definitive meaning. "Bioinformatics" was coined just for "biology made on computer", there is nothing deep in this. $\endgroup$
    – user88
    Jun 2, 2012 at 22:16
  • 1
    $\begingroup$ @mbq Agreed. "Informatics" and "Bioinformatics" have lost any meaningful definition. $\endgroup$
    – Fomite
    Jun 5, 2012 at 2:20
  • $\begingroup$ in clear way bioinformatics ( apply your findings to observe your results in biological way ) $\endgroup$ Mar 10, 2019 at 5:47

3 Answers 3


Excellent question!!

I heard several times that bioinformaticians can go without biostatistics, or even without statistics. That's perfectly true until it becomes false. In my opinion, general lack of statistical knowledge has disastrous effect in the field, as shown by Keith Baggerly. I could also observe that lack of basic knowledge in statistics (and linear algebra) is the cause of stagnation of bioinformaticians in the long run: without a deep knowledge of the theory, they tend to reinvent the wheel and resort to ad hoc solutions that solve nothing but their own problem. $ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $

But now, to answer your question, I agree that overall, statistics can't do without computers those days. Yet, one of the major aspects of statistics is inference, which has nothing to do with computers. Statistical inference is actually what makes statistics a science, because it tells you whether or not your conclusions hold up in other contexts.

In short, you can analyze the hell out of your data, you will still need statistics to know the validity of the predictions or decisions you will make based on your analyses.

  • $\begingroup$ Thanks. Could you explain more about what is the general principle behind bioinformatics to make it to be a discipline. For statistics, generally speaking, there are two main parts, one is pure data manipulation, the other is statistical inference, which is based on probability, one of the pure mathematics. Based on the statistical models (probability models), stat people can do science. What about bioinformatics? $\endgroup$ Jun 3, 2012 at 1:37
  • 4
    $\begingroup$ Bioinformatics is simply the use of computers to study biological questions. Disciplines are usually defined by the questions they ask, not by their methods, so bio-informatics should be part of biology in my opinion. It has a special name because biologists are very bad with computers, so people who can do it must have a special label. I am not sure that in 50 years, when biologists are better at IT and math, bio-informatics will still exist. $\endgroup$
    – gui11aume
    Jun 3, 2012 at 1:59
  • 2
    $\begingroup$ It is nice to see someone else appreciative of Keith's efforts. He certainly hasn't shied away from controversy or difficult and uncomfortable professional situations. $\endgroup$
    – cardinal
    Jun 3, 2012 at 14:44
  • $\begingroup$ @cardinal Saw Keith talk at an APHA conference a year or two ago. It was one of the best talks I've ever seen. $\endgroup$
    – Fomite
    Jun 5, 2012 at 2:23

My view is that while there is a fair amount of overlap between the fields there are also key differences. In general a statistics student (in the higher degrees) will take more theory classes (math and mathstat) than the informatics student, but the informatics student will learn more of the computing (especially the database part) side.

Developing a new statistical test would fall more to the statistician than the informaticist, but designing an interface for a user to enter data and produce tables and plots would fall more to the informaticist than the statistician.

To the statistician the computer is a tool to help with statistics. To the informaticist statistics are a tool to help collect and distribute information (via computer generally).

Edit below here -----

To exand, here is an example. I have worked on projects with informaticists (I am the statistician) where a medical doctor wants to have a system where information on patients is used to predict their risk of some condition (developing a blood clot for example) and wants to receive some form of alert to let them know about the risk. My role in the project (the statistician role) is to develop a model that will predict risk given the predictor variables (a logistic regression model is one such model). The informaticist role in the project is to develop the tools that collect the predictor variables, use my model on them, then send the results to the doctor. The data may be collected from an electronic medical record, or through a data entry screen for a nurse to fill in or others. The alert to the doctor may be a pop-up on the computer or a text message sent to their cell phone or others.

Now I (and many other statisticians) know enough of the programming that I could query a database to get the predictors and create some type of alert, but I am happy to leave that to the informaticists (and they are better at it anyways). There are informaticists that know enough statistics to fit the logistic regression model. So a simple version of this project could be done by only a statistician, or only an informaticist, but it is best when both work together. If you look at this project and think the modeling part is the fun part and the data collection, alert and other interfaces are just tools to move the information to and from the model then you are more of a statistician. If you see designing the interface, optimizing the data retrival, testing different types of alerts, etc. as the fun part and the statistical model as just a tool to convert one part of your data into the other part, then you are more of an informaticist.

$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $$ $

  • $\begingroup$ (+1) I like the balance of this answer. I'm not sure I quite understand what was intended by the very last sentence. $\endgroup$
    – cardinal
    Jun 3, 2012 at 14:46
  • 1
    $\begingroup$ I think your example is very nice and gives a good portrait of the basic lay of the land. I wish I could upvote it again for just that part. Cheers. $\endgroup$
    – cardinal
    Jun 4, 2012 at 17:10
  • $\begingroup$ Your example is really cool. Thanks a lot. Now I am just wondering one question. For statistician, whether all of the statistical model should have inference part, such as confidence interval or hypothesis testing, and hence based on probability models? Otherwise, they are only manipulate the data set by plotting and summarizing. $\endgroup$ Jun 5, 2012 at 15:05

Statistics infers from data; Informatics operates on data. Of course they overlap, but the question of which has the larger scope has no answer.

  • $\begingroup$ "Statistics inferes from data; Informatics operates on data." This is really what I want to confirm. For the inference, always based on the probability distribution, it should include confidence interval or hypothesis testing. Otherwise, you are just operating on data. $\endgroup$ Jun 5, 2012 at 15:11

Not the answer you're looking for? Browse other questions tagged or ask your own question.