Experimental Research

Experimental Research

Definition 

Experimental research attempts to establish a cause-and-effect relationship between two phenomena.



It is basically quantitative

Purpose 

The researcher hypothesizes that one variable, the independent variable, causes changes in another variable, the dependent variable. independent variable



affects

dependent variable

The purpose of the experimental design is to eliminate alternative hypotheses. If we can successfully eliminate all alternative hypotheses, we can argue-by a process of elimination- that the independent variable is the cause.

Example 

A researcher may wish to determine whether the explicit teaching of cultural background information to university ESL students will increase their comprehension of certain texts.

Dependent Variable: comprehension of certain texts Independent Variable: explicit teaching of cultural background information

Example 

Say I am testing whether a new form of psychotherapy is successful at improving mental health. I hypothesize that this psychotherapy is the cause of improved mental health in the research participants. I will use an experimental design to eliminate all (or as many as possible) alternative hypotheses. If I can eliminate alternative explanations, I will be able to make the case that the psychotherapy was the cause of the improvements in the research participants. Dependent Variable: mental health Independent Variable: a new form of psychotherapy

Research Question & Hypotheses 

The experimenter starts by making a series decisions that involve narrowing the question.



Then, he converts the very general question that guides study into a more specific question or statement. This specific formulation is a hypothesis.

Procedures involved in conducting an experimental study    



Decide on your hypothesis. Select subjects (participants/sample of the study) Divide subjects into groups if needed. Administer pretest (measurement before the experiment begins) Implement and monitor treatment -Experimental Treatment: The program you wish to assess its effect -Control Treatment: The existing program



Administer posttest

Causality & Control Experimental research attempts to establish causality, and to be well aware of its limitations. 1- The study of Planned Change: Unlike naturalistic

research in which phenomena are studied in their naturally occurring environments, an experiment, by definition involves manipulating the situation. For example, when the researchers compare the effects of variations in responses to student writing in EFL classes, they do not study existing classes with existing, naturally occurring variations in teacher feedback. Rather, they design differing response guidelines, ask the teachers to implement them, and examine their effects on student writing.

).Causality & Control )Cont 2- Random Assignment:

The purpose of the random assignment is to give each subject an equal chance of participating in any one of the experimental conditions. This is done to ensure that the groups are as similar to one another as possible. The larger the sample, of course, the more likely that the groups will be similar.

Validity of Experimental Design 



Internal Validity An experiment is designed to establish a causeand- effect relationship; that is, the researcher’s goal is to be able to conclude that observed differences between groups on the dependent variables are attributable to the treatment, not to other causes. External Validity (Generalizability of the study) To what other subjects in what other situations or settings would the results apply?

Methods of Experimental Control 

Physical Control Gives all subjects equal exposure to the independent variable. Controls non experimental variables that affect the dependent variable.



Selective Control -



Statistical Control -

Manipulate indirectly by selecting in or out variables that cannot be controlled. Variables not conducive to physical or selective manipulation may be controlled by statistical techniques (example: covariance).