Gathering data or collecting data is the filling of the database that a scientist uses for analysing the data to answer the research question.
What is a database?
A definition of research is answering questions for which first new data have to be gathered and analysed. The information that is gathered has to be stored somewhere. The place where the information is stored is called the database.
A database can be any form of storage and what the scientist puts into it can really be anything. It can be photos, movies, text, objects, a note on a page of a newspaper and so on and so on. This is the raw data set and it must be stored somewhere safe, so that anyone who wants to go back to the basics of the research can start with the raw data again.
A scientist who wants to analyse the data, cannot work with this raw data. Therefore he is reordering the information in a more suitable way. Besides that he is reducing the information he needs for answering the research question. Normally that ends up in a database with only text or numbers or a mix of it. This is the database that is used for analysing the data, and this should be stored somewhere save too.
There are five ways to fill the database
Observing is the collection of information in which only one's own senses are used. He (or she) might hear, see or feel things and write them down. It can be noted on a clean sheet of paper or stored on a digital information carrier.
The problem with this kind of information is that it is directly observed from reality (the empery), so the scientist has to interpret what he observes. He could make mistakes when doing this. Can anybody trust his senses? Don’t we all make mistakes while observing the world that surrounds us? This is a severe attack on getting trustworthy information and the conclusions we want draw out from this information. There are several ways to reduce faults in observations. We explore this issue more in detail on our site page observation.
When conducting interviews, the senses of the scientists are not used, but the senses of other people. This is useful because scientists cannot be everywhere to collect the data themselves.
In this situation, scientists do not observe the real world itself, but record what other people have seen, heard, felt or think about what they have experienced. Again, anyone can question the quality of the information collected. Has the person who gives the information got it right? But this time we worry less about it. Normally it is not about the exact facts, but about the opinion of the person. Yet it is difficult to get the person's real opinion and the information he gives may be wrong. A scientist must therefore have techniques to obtain valid and reliable data.
The different ways to use interviews to collect data and how you can be more certain that this information is valid and reliable are discussed on our page: Interviews.
Instrumentation is a way of getting information without using anyone’s senses. All information is gathered by instruments. Some instruments are very common like a ruler, a hydrometer, an instrument for measuring blood pressure. A questionnaire is an instrument as well. Sometimes a person is needed to write the measured information in the database, but nowadays most instruments themselves can write all the information in the database.
When a scientist uses instruments he has to know if these instruments give valid and reliable information. Read more about this on our page: Instrumentation.
Copying and transferring data is another way to fill the database. The information in other documents can easily be copied to your own database. This may seem simple, but there are some aspects that can make it difficult and provide unreliable information. You can read more about this on our page: Transferring data.
Generating is a way of filling a database which some scientists do not consider a scientific way of gathering data. However, a database is a document that is used for the analysis, and the document can be filled with generated data. It is used in simulation. In a simulation a scientist makes a model that creates data, and these data are analysed.
Simulation can be used for all kinds of research. We will discuss this more in detail on our page: Simulation.
Related topics to gathering data
- Transferring data
- Generating data