The two main methods of inquiry in research are quantitative and qualitative studies (Creswell, 2013). Quantitative studies are empirical and data is collected in numerical form and is quantified through statistical analysis. The two broad categories of quantitative research methods are experimental and non-experimental. With this in mind, the purpose of this paper is to discuss the major categories of non-experimental research designs and discuss how the similarities and differences among these categories.
Non-experimental designs, unlike experimental designs, involve the use of variables that the researcher does not manipulate but rather they are studied as they naturally exists (Creswell, 2013). Non-experimental designs are appropriate because sometimes variables cannot be manipulated, especially in the social sciences. These types of variables cannot be manipulated because they are attribute variables, for example, gender, race, or a personality trait. In this way, a research is not able to randomly assign individuals into a control group or experimental group because these variables are naturally occurring attributes (Creswell, 2013). Non-experimental designs are also appropriate when it would be considered unethical to randomly assign research participants to different treatment or intervention groups. As an example, it would not be ethical for a researcher to examine the effects of smoking by randomly assigning participants to either a smoking group or a non-smoking group to compare the differences. Also, in this scenario, other variables would have to be taken into account, i.e. how long the individual smoked, their age, etc.
Correlational, descriptive and historical research studies are classified under the category of non-experimental research, each with their similarities and differences (Creswell, 2013). As these are classified as non-experimental designs, as previously noted, the researcher does not manipulate variables or the environment. Another similarity between these designs is that they are all considered non-obtrusive research in that the researcher attempts to be inconspicuous and avoids influencing the participants.
Correlational designs are used when a researcher wants to examine the relationship between two or more existing variables (Creswell, 2013). This type of design is useful when the researcher wants to gain a better understanding of the present conditions and to make predictions. Correlational designs however do not show a cause and effect relationship. The study by Bakker, Van Der Zee, Lewig and Dollard (2006) is an example of a quantitative methodology incorporating a correlational design. In this study the researchers examined the relationship between the Big Five Personality Factors and levels of burnout. In this study the researchers collected data from the participants using surveys. In this way the research was non-obtrusive and no variables were manipulated.
Whereas correlational studies explore the relationship between variables, descriptive research involves examining data and observing participants. The descriptive design is used to provide a snapshot of what is going on at that particular time. Also, descriptive research allows for further questioning. There are three types of descriptive research. These include a case study in which one or more individual’s experiences and behaviors are recorded; surveys in which participants provide information of their behaviors experiences through questionnaires; and naturalistic observation, in which the researcher observes participants in their everyday events.
Historical research uses a systematic method to search for information and facts in order to interpret, analyze or describe what has happened in the past (Creswell, 2013). Historical research is of value as it provides researchers with prospective information that can be useful in making decisions about current issues. Current problems may be understood better if there is an understanding from a historical perspective. A source of data for historical research is often found in past records.
In non-experimental designs the variables are not manipulated. The three main categories of non-experimental designs are correlational, descriptive and historical. Correlational designs examine the relationship between existing variables. Descriptive designs are used to provide a snapshot of what is going on at that particular time and are either done through surveys, naturalistic observation or case studies. Historical research is a method used to search for information and facts in order to interpret, analyze or describe what has happened in the past.
- Bakker, A.B., Van Der Zee, K.I., Lewig, K.A., & Dollard, M.F. (2006). The relationship between the Big Five Personality factors and burnout: A Study among volunteer counselors. The Journal of Social Psychology, 146(1), 31-50. doi: 10.3200/ SOCP.146.1.31-50
- Creswell, J.W. (2013). Research design: Qualitative, quantitative and mixed method approaches. (4th ed.). Thousand Oaks, CA: Sage Publications.