Experimental research
1-Experimental research involves a variable that can be manipulated. With this type of experiment, participants can be randomly assigned to either the control group or treatment group. It often demonstrate a cause-and-effect relationship.
On the contrary, nonexperimental research involves a variable that cannot be manipulated or change. The variable is controlled and has to remain constant. Participants will not be randomly assigned to either the control or treatment group. This type of experiment does not demonstrate a true cause-and-effect relationship but instead, relies on observation and correlation.
For instance, in 2013, New England Journal of Medicine released an article on what was believed to have been an experimental study. The article suggested that Mediterranean diet lowers the chance of heart attack, stroke, and other cardiovascular diseases by 30%. Mediterranean diet has been recommended since for general prevention. However, it was retracted in 2018 after it was reported that 14% of the participants were not randomly assigned to either a control or treatment group. Married couples were put into the same group and even participants from an entire village was placed into a single group. All this was never reported in the paper.
References:
Yu, C. (2018). Experiment and Non-experiment. Retrieved from http://www.creative-wisdom.com/teaching/WBI/doe.shtml
Bonds-Raacke, J.M., & Raacke, J.D. (2014). Nonexperimental Research Methods from Research Methods: Are You Equipped?.Retrieved from https://he.kendallhunt.com/sites/default/files/uploadedFiles/Kendall_Hunt/Content/Higher_Education/Uploads/Bonds_Raacke_Research_2e_Ch4.pdf
2-Experimental research is when the researcher manipulates or controls the independent variable. Experimental research normally is used when the researcher has a specific question or hypothesis (Price et al, 2017). This is done to identify a cause and effect relationship, normally conducted with an experimental group and placebo or non-manipulated group. An example of this is to determine effects of certain medications such as pain relievers. Half of the group will receive a pain pill to manage their pain symptoms while the other half will receive a placebo pill. The expected results should be that the half who received the placebo pills did not experience pain relief.
Non-experimental research is when the research lacks manipulation or control of the independent variable (Price et al, 2017). Variables are usually measured as they naturally occur and the researcher relies on observation and interactions through case studies, surveys, or correlations. It is also used when the conditions of the experimental research is not met. An example of this is to study if there is a correlation between crime rates and poverty levels. A researcher would not manipulate or control any variables of this research but rather would observe and take data as it naturally occurs.
Grove, & Burns. (2011). Understanding nursing research. Retrieved from https://evolve.elsevier.com/cs/product/9781455770601
Price, P. C., Jhangiani, R. S., Chiang, I. A., Leighton, D. C., & Cuttler, C. (2017, August 21). What is Non-Experimental Research. Retrieved from https://opentext.wsu.edu/carriecuttler/chapter/overview-of-non-experimental-research/
3-Experimental research designs: This type of research is controlled in order to find an answer. This type of research can deliver evidence and prove a cause and its effect. Statistics Solutions states, “..they typically involve the manipulation of variables and random assignment of participants to conditions. A traditional experiment may involve the comparison of a control group to an experimental group who receives a treatment (i.e., a variable is manipulated). When done correctly, experimental designs can provide evidence for cause and effect. Because of their ability to determine causation, experimental designs are the gold-standard for research in medicine, biology, and so on” (Statistics Solutions, 2018).
Experimental research is tightly controlled and i may contain groups who are taking a placebo for instance, and the other group actually taking a medicine. An example would be testing if a medication causes birth defects. One group will take the medication while pregnant, and other group will be given a sugar pill and having them believe it is an actual medication. This can prove what happens to the actual group taking the medication and also the group not taking the medication and come to a conclusion based on results.
Nonexperimental research designs: This type of research is not controlled. This type of research is typically observational. This information is grasped after the fact and known as “retrospect” because it is studying things that have already occured and sometimes more prone to bias. A journal on research study designs gives the following example: “..an investigator may be interested in the average age, sex, most common diagnoses, and other characteristics of pediatric patients being transported by air. They may be interested in the prevalence of a clinical presentation pattern or a specific symptom for a given disease. In such studies, the research question would be focused on prevalence rates, or such, rather than causality. They may propose some associations but cannot effectively prove them” (Air Medical Journal, 2007).
Some examples of nonexperimental research designs are:
- cross sectional study
- case control study
- historical controls
- surveys/ questionaires
- case series
- case report
Reference:
Air Medical Journal. 2007. Research Study Designs: Non-Experimental. Retrieved from
Statistics Solutions. 2018. Research Designs: Non-experimental vs. Experimental. Retrieved from https://www.statisticssolutions.com/research-designs-non-experimental-vs-experimental/