Plan the study. The research starts with identification of a research problem and research questions or hypotheses. It is also necessary to plan the research design before you select the data collection instrument(s) and begin to collect data. Most research methods books discuss this part of the research process extensively (e.g., see Gliner, Morgan, & Leech, 2009).
Select or develop the instrument(s). If there is an appropriate, available instrument that provides reliable and valid data and it has been used with a population similar to yours, it is usually desirable to use it. However, sometimes it is necessary to modify an existing instrument or develop your own. For this chapter, we have developed a short questionnaire to be given to students at the end of a course. Remember that questionnaires or surveys are only one way to collect quantitative data. You could also use structured interviews, observations, tests, standardized inventories, or some other type of data collection method. Research methods and measurement books have one or more chapters devoted to the selection and development of data collection instruments. A useful book on the development of questionnaires is Fink (2009).
Pilot test and refine instruments. It is always desirable to try out your instrument and directions with, at the very least, a few colleagues or friends. When possible, you also should conduct a pilot study with a sample similar to the one you plan to use later. This is especially important if you developed the instrument or if it is going to be used with a population different from the one(s) for which it was developed and on which it was previously used.
Pilot participants should be asked about the clarity of the items and whether they think any items should be added or deleted. Then, use the feedback to make modifications in the instrument before beginning the actual data collection. If the instrument is changed, the pilot data should not be added to the data collected for the study. Content validity can also be checked by asking experts to judge whether your items cover all aspects of the domain you intended to measure and whether they are in appropriate proportions relative to that domain.
Collect the data. The next step in the research process is to collect the data. There are several ways to collect questionnaire or survey data (such as telephone, mail, or e-mail). We do not discuss them here because that is not the purpose of this book. The Fink (2009) book, How to Conduct Surveys: A Step by Step Guide, provides information on the various methods for collecting survey data.
You should check your raw data after you collect it even before it is entered into the computer. Make sure that the participants marked their score sheets or questionnaires appropriately; check
to see if there are double answers to a question (when only one is expected) or answers that are marked between two rating points. If this happens, you need to have a rule (e.g., “use the average”) that you can apply consistently. Thus, you should “clean up” your data, making sure they are clear, consistent, and readable, before entering them into a data file.
Let’s assume that the completed questionnaires shown in Figs. 2.1 and 2.2 were given to a small class of 12 students and that they filled them out and turned them in at the end of the class. The researcher numbered the forms from 1 to 12, as shown opposite ID.
Fig. 2.1. Completed questionnaires for Participants 1 through 6.
Fig. 2.2. Completed questionnaires for Participants 7 through 12.
After the questionnaires were turned in and numbered (i.e., given an ID number in the top right corner), the researcher was ready to begin the coding process, which we describe in the next section.
Source: Morgan George A, Leech Nancy L., Gloeckner Gene W., Barrett Karen C. (2012), IBM SPSS for Introductory Statistics: Use and Interpretation, Routledge; 5th edition; download Datasets and Materials.
Yes! Finally sⲟmething about unitariаn.