Data collection is fundamental to the study of statistics because it is an integral step in the process of carrying out a research study. There are different types of methods which can be implemented to go about collecting data. In statistical studies some of the most common techniques for data collection include population censuses, sample surveys and conducting experiments.
Before a researcher can begin collecting data, a planned research design with a focused study objective needs to be drawn out. Data collection has an influence on many factors in a statistical study such as on the study design, the survey methodology and later on, the conclusions which can be formulated. In order for a study to formulate valuable conclusions, the method of data collection needs to be organized in a way which meets the needs of the study, most importantly the question(s) being asked and units being collected.
For example, pretend you are a bird researcher and you are studying red-winged blackbird populations in all of the marshes located near busy, urban roads in your local city. Although you plan on collecting current data, you are also fortunate enough to have past collected data on red-wing blackbird populations residing in the marshes you are studying, from 20 years ago. The purpose of this current study is to analyze whether an increase in urban activity over 20 years has caused a change in population size.
From the above scenario, it is clear that the units being measured are red-wing black birds, which are being counted, and the question of interest is whether urban activity influences population size. Now when deciding how to design the experimental study, considering how exactly to go about collecting the data is critical. Some things to consider may include: how large of a sample size should be collected at each marsh or what time of day to collect the data. Clearly this example illustrates how the process of data collection is an important step in designing a successful statistical study.