5 Experimental Research and its Ethical Issues

T. Amutha

epgp books

 

 

 

 

Introduction

 

Experimental researches are used to investigate the casual (cause/effect) relationship between one variable and the other. It is used to study the relationship between one variable and another variable. Experimental research is quantitative in nature. It is the most traditional type of research. Researchers use the experimental research for comparison. They compare two or more groups on one or more measures. In this type of research one variable is manipulated to see whether it has an effect on the other variable. Experimental research is used in this way to answer the hypothesis. Hypothesis is a testable statement or assumptions that are formulated by the researcher to address a specific question. The researcher designs an experimental study and check whether the hypothesis is supported or disproved in his research. For Example The researcher can set an assumption that there is a significant relationship between rainfall and yield of the paddy crops. With this assumption the researcher can set the hypothesis as if there is increase in rainfall then there is increase in the yield of paddy crops. In this study the researcher can check whether the hypothesis is supported or disproved in his research. Here rainfall is the independent variable (cause) and yield of paddy is the dependent variable (effect).

 

2. Basic Terms Used in Experimental Research

 

It is important to know the basic terms used in experimental research. They are

 

2.1 Independent Variable: Independent variable is the variable that will be manipulated, the “cause” or treatment variable. Independent variable can be the activity or characteristic that the researcher believes will make a difference. Eg: Rainfall

 

2.2 Dependent Variable: Dependent variable is the “effect” or outcome of manipulating the independent variable. The only constraint is that the outcome must be measurable. Eg:Yield of Paddy cultivation.

 

2.3 Experimental Group: It is the group that receives the treatment being investigated.

 

2.4 Control Group: It is the group that remains the same in order to have something to compare the experimental group against.

 

3. Criteria for Experimental research

 

Experimental research must meet these three criteria for the results to be meaningful. It includes:

 

3.1 Random Assignment: Test subjects must be randomly assign to the treatment groups to control for formation of groups that may systematically differ in another way that impact the result of the treatment.

 

3.2 Experimental Control: All aspects of the treatment are the same except for the independent variable. If all other factors are controlled and kept constant, then if quantifiable differences are found in the outcomes, the researcher can be confident that the difference is due the independent variable (treatment).

 

3.3 Appropriate Measures: The measure or outcomes must be proper for testing the hypothesis. The outcome measured must correspond to the idea being tested in the hypothesis in order for the results to be valid. Lets say that a researcher wanted to investigate the effects of productivity by changing the intensity of light. For this we can consider the Human relations – Hawthorne Experiment. The initial experiment was known as the Illumination Study, which aimed at investigating the relationship between workplace lighting and employees‟ productivity.

 

The researchers selected two groups of workers. In the first group known as the experimental group, the level of lighting was varied. The second one was the control group that had no alteration in light. During the study, the researchers found that the output of workers increased in both groups. Additionally, the productivity of the experimental group made researchers even more surprised because whether the lighting level was high or low as ordinary moonlight, the output generally increased. One of the employees who were in the experiment was asked to inform about the study. He said that the environment “wasn‟t that bad”. It got a little darker but he could still see what he was doing. The experiment concluded that there is no relationship existing between workers‟ output and illumination.

 

From the above example the change in the intensity of light is the independent variable. The productivity is the dependent variable. The experimental group is the group where the level of lighting was varied and the control group is the group that had no alteration in light. This is a classical example of the use of experimental research design.

 

4. Steps in Experimental Research

 

Researcher should follow the following steps for experimental research.

 

I. Select a topic:

 

The first and foremost step is to select a topic which involves simply identifying the area of interest or general subject. The researcher as the first step has to think of the three important key aspects such as Novelty, inventive step and Application.

 

II.Identify the research problem:

 

After a topic or subject is selected the researcher must identify the specific problems or questions related to the subject. Suppose if the researcher is familiar with the subject and may already know the problem they want to search then the researcher can move to the next step. If the researcher is new to the topic then the researcher must examine the literature and previous studies related to the subject. Also the researcher can discuss with the other researchers to get clarity about the subject. The problem selected should be important to the field and be of significance to others in the discipline.

 

III. Conduct literature search:

 

After identifying the research problem the next step we have to conduct literature search before proceeding to design the experiment. Literature search helps the researcher to know what studies have been performed, the designs, the instruments used, the procedures and findings.

 

IV.Construct a hypothesis:

 

In this step the researcher has to formulate the research questions and set the hypothesis. It is a most critical step.

 

V. Determine the design of the research:

 

The researcher should review the hypothesis, then the researcher should verify whether the experimental design is the appropriate research design needed to answer the questions.

 

VI.Determine the research methods:

 

In this step the researcher will identify and plan the details necessary to conduct the research. This includes identifying the test subjects, materials data collection instruments and methods and the procedures for the conduct of experiment.

 

VII. Conduct the research and test the hypothesis:

 

The actual experimental procedures will be carried out in this phase.

 

VIII.  Analyse the data:

 

The experimental research data lends itself to variety of potential statistical analyses. The appropriate analysis is determined by the research questions and the type of data.

 

IX. Formulate conclusions:

 

As the final step the researchers has to review the data and determine if it confirms or disproves the hypothesis.

 

All this are the basic outline of the steps involved in conducting experimental research.

 

5. Types of Experimental research

 

There are three types of experimental research designs. They are True experimental designs, Quasi experimental designs, and pre experimental designs.

 

Experimental research designs are most scientifically developed research methods. It clear states the observation under controlled conditions. Experimental research design is guarded with test of effect of independent variable on the dependent variable and is manipulated through treatment or interventions and the effect of those interventions is observed on the dependent variable.

 

5.1 True Experimental design:

 

True experimental research design are those where the researchers have complete control over the extraneous variables and can predict confidently that the observed effect on the dependent variable is only due to the manipulation of the independent variable. A true experimental research design includes the Manipulation, Control and Randomization.

 

5.1.1 Manipulation

 

Manipulations means conscious control of the independent variable by the researcher through treatment or intervention to observe its effect on the dependent variable.

 

5.1.2 Control

 

Control is another essential element of true experimental design, control means the use of control group and controlling the effects of extraneous variables on the dependent variable in which researcher is interested. The subject in the control and experimental group are alike in number and characteristic, but the subject in the control group receive no experimental treatment or any interventions at all. The experimental group receives the planned treatment or intervention and a comparison is made with the control group to observe the effect of this treatment or intervention.

 

5.1.3 Randomization

 

Randomization states that every subject has an equal possibility of being assigned to experimental or of study subjects on a random basis. With the help of random task of subject under experimental or control group, probability of bias is eliminated. In true experimental research design randomization is used to minimize the threat of internal validity of the study and to eliminate the effect of extraneous variables on dependent variables.

 

5.2 Quasi- experimental research

 

Quasi-experimental research design involves the manipulation of independent variable to observe to effect on dependent variable, but it lacks at least one of the two characteristics of the true experimental design; randomization or a control group. Quasi-experimental designs are usually used to establish the causality in situations where researchers are not able to erratically assign the subjects to groups or for a variety of reasons and no control group are available for an experimental study.

 

Types of Quasi-Experimental Design:

 

There are two types of Quasi-experimental design. They are Non randomized control group design and Time-Series design

 

5.2.1 Non randomized control group design

 

Non randomized control group design also known as the non equivalent control group design. This design is identical to the pre test – post test control group design, except there is no random assignment of subjects in experimental and control groups. In this design, experimental and control groups are selected without randomization, and dependent variables are observed in experimental as well as control groups before the intervention. Later, the experimental group receives treatment and after that post-test observation of dependent variables is carried out for both the groups to assess the effect of treatment on experimental group.

 

5.2.2 Time-Series Design

 

This design is useful to measure the effects of a treatment over a long period of time when the experimenter wants to measure. The experimenter would keep on to direct the treatment and measure the effects a number of times during the course of the experiment. usually it is a single subject research, in which the researcher carries out an experiment on an individual or on a small number of individuals, by alternating between administering and then withdrawing the treatment to determine the effectiveness of the intervention.

 

5.3 Pre-Experimental Research Design

 

This research design is considered very weak, because the researcher has very little control over the experiment.

 

Types of Pre-Experimental Research Design

  •  One-shot case design
  • One-group pretest-posttest design

   5.3.1 One-shot case design

 

In one-shot case design, a single experimental group is exposed to a treatment and observations are made after the implementation of that treatment. There is no random assignment of subjects to the experimental group and no control group at all.

 

5.3.2 One-group pretest-posttest design

 

It is the simplest type of pre-experimental design, where only the experimental group is selected as the study subjects. A pre-test observation of the dependent variable is made before implementation of the treatment to the selected group, the treatment is administered, and finally a post-test observation of dependent variables is carried out to assess the effect of treatment on the group. Some researcher also argues this design as sub type of quasi-experimental research design, though in absence of both randomization and control group. This design ethically cannot be placed under the classification of quasi-experimental research design.

 

6. Validity in Experimental Research

 

There are two types of validity. They are internal validity and external validity.

 

6.1 Internal validity:

 

Internal validity refers to the validity of the findings within the research study. It is primarily concerned with controlling the extraneous variables and outside influences that may impact the outcome.

 

6.2 External validity:

 

External validity refers to the extent to which the results of study can be generalized or applied to other members of the larger population being studied. For this reason, the random selection of participants and random assignment of the study participants into groups is critical so that the members of the study are truly representative of the larger population. External validity is concerned with real life applications that have relevance beyond the confines of the experiment. Random selection is really the key ensuring that results are generalizable.

 

7. Benefits and Limitations of Experimental Research

 

There are many benefits and limitations to experimental research. Let me brief the benefits and limitations of experimental research.

 

7.1 Benefits

  • Experimental research is the most appropriate way for drawing causal conclusions, regarding interventions or treatments and establishing whether or not one or more factors causes a change in an outcome. This is largely due to the emphasis in controlling extraneous variables. If other variables are controlled, the researcher can say with confidence that manipulation independent variable caused a changed in the dependent variable.
  •  It is a basic, straightforward, efficient type of research that can be applied across a variety of disciplines.
  • Experimental research designs are repeatable and therefore, results can be checked and verified.
  • Due to the controlled environment of experimental research, better results are often achieved.
  • In the case of laboratory research, circumstances not found in a natural setting can be created in an experimental setting that allows for greater control of extraneous variables. Conditions that may take longer to occur in a natural environment may occur more quickly in an experimental setting.
  • There are many variations of experimental research and the researcher can tailor the experiment while still maintaining the validity of the design.

7.2 Limitations:

  • Experimental research can create artificial situations that do not always represent real-life situations. This is largely due to fact that all other variables are tightly controlled which may not create a fully realistic situation.
  • Because the situations are very controlled and do not often represent real life, the reactions of the test subjects may not be true indicators of their behaviors in a non-experimental environment.
  • Human error also plays a key role in the validity of the project.
  • It may not be really possible to control all extraneous variables.
  • The research must adhere to ethical standards in order to be valid.
  • Experimental research designs help to ensure internal validity but sometimes at the expense of external validity. When this happens, the results may not be generalizable to the larger population.
  • If an experimental study is conducted in its natural environment, such as a hospital or community, it may not be possible to control the extraneous variables.
  • Experimental research is a powerful tool for determining or verifying causation, but it typically cannot specify “why” the outcome occurred.

   8.  Ethics in Experimental Research

 

Ethical considerations in research are critical in experimental research, just as they are in other types of research. Ethics are the norms or standards for conduct that distinguish between right and wrong. They help to determine the difference between acceptable and unacceptable behaviors on the part of the researcher.

 

8.1 Why are ethical considerations so important in research?

 

The integrity, reliability and validity of the research findings rely heavily on adherence to ethical principles. The readers and the public want to be assured that researchers followed the appropriate guidelines for issues such as human rights, animal welfare, compliance with the law, conflicts of interest, safety, health standards and so on. The handling of these ethical issues greatly impact the integrity of the research project and can affect whether or not the project receives funding.

 

Ethical issues are important in all types of research. Regardless of the type of research, the researcher should take into consideration both general research principles and those that are more specific to the type of research. In experimental research, ethical standards prevent against such things as the fabrication or falsifying of data and therefore, promote the pursuit of knowledge and truth which is the primary goal of research. It is also important to protect research participants and follow the guiding foundation of “do no harm” if human subjects are utilized in the study.

 

9.Conclusion

 

Ethics is a requirement for human life. It is our means of deciding a course of action. Without it, our actions would be random and aimless. Even with an ethical standard, we may be unable to pursue our research with the possibility of success. To the degree which a rational ethical standard is taken, we are able to correctly organize our research and accomplish the results which may be most useful to the society with most important values. Any flaw in our ethics will reduce our ability to be successful in our endeavours.

you can view video on Experimental Research and its Ethical Issues

Web links