/26

EXPERIMENTAL RESEARCH STRATEGYChapter 7

1

/26

GOAL

The purpose of the experimental research strategy is to establish the existence of a cause- and- effect relationship between two variables.

2

/26

HOW

To accomplish this goal, an experiment manipulates one variable while a second variable is measured and other variables are controlled.

3

/26

4 BASIC ELEMENTS,

1. Manipulation. Manipulate one variable by changing its value to create a set of two or more treatment conditions. (3 levels of lighting & plant grow)

2. Measurement. Obtain a set of scores in each treatment condition. (measure the length of the plant)

3. Comparison. The scores in one treatment condition are compared with the scores in another treatment condition. (compare growth under 3 conditions)

4. Control. All other variables are controlled to be sure that they do not influence the two variables being examined. (Control oxygen , fertilizer, soil, and temperature)

4

/26

TERMINOLOGY

In an experiment, a treatment condition (independent variables) is a situation or environment characterized by one specific value of the manipulated variable.

teaching methods, levels of lighting

The different values of the independent variable selected to create and define the treatment conditions are called the levels of the independent variable.

(Traditional, Constructivist) (high light, Med light, low light)

The dependent variable is the variable that is observed for changes to assess the effects of manipulating the independent variable.

Student score in math , size of plants

All variables in the study other than the independent and dependent variables are called extraneous variables.

IQ, Temperature, Fatigue, Age, noise,

oxygen, soil, fertilizer,..….

5

/26

THE PROBLEM WITH EXPERIMENTAL DESIGN

How can observations made in an artificial, carefully controlled experiment reveal any truth about nature?

Just because an experiment takes place in an unnatural environment does not necessarily imply that the results are unnatural.

Example, studying gravity in vacuum

feather , hammer

6

/26

CAUSATION & 3RD VARIABLE

Although it is relatively easy to demonstrate that one variable is related to another, it is much more difficult to establish the underlying cause of the relationship.

Number of smiles & life span

Eating fish & life span

7

/26

CAUSATION AND THE DIRECTIONALITY PROBLEM

TV & violence (correlation & t-test misleading)

We need manipulation

8

/26

Use manipulation if you can

In general, whenever there is a relationship between two variables, a researcher can use manipulation to determine which variable is the cause and which is the effect.

Temperature & Ice cream consumption (can we change the temperature to see if ice-cream consumption goes up?)

9

/26

SOMETIMES WE HAVE TO USE CORRELATION

Depression & Insomnia (can we manipulate depression to see if Insomnia decreases?)

10

/26

WHAT IS THE CONFOUNDING VARIABLE IN THIS RESEARCH?

Group A (using humorous words to memorize) Group B (using non-humorous words)

11

/26

CAN WE SEPARATE HUMOR AND SURPRISE?

12

≠≠

/26

LEVEL OF SURPRISE

The level of surprise varies systematically with the level of humor, and so it might be confounding variable.

13

/2614

≠=

/26

METHODS OF CONTROL (GENDER) Holding a variable constant (all boys) Matching values across treatment conditions (10 males

and 20 females could be assigned to each group) Control by randomization (random assignment)

15

/26

Which one is better to control gender?

16

/26

QUASI-EXPERIMENTAL DESIGN

A quasi-experimental design is one that looks a bit like an experimental design but lacks the key ingredient -- random assignment.

17

/26

EX POST FACTO

1. Studies pre-existing groups

2. No treatment

3. This type of study often is called ex post facto research because it looks at differences “ after the fact;” that is, at differences that already exist between groups.

Difference between Engineering and Education (PE , non-PE) students in their reading speed.

18

/26

2 TYPES OF CONTROL GROUPS

a no- treatment control group is a condition in which the participants do not receive the treatment being evaluated.

Place’bo Control Groups (can the researcher be sure that the observed effect is really caused by the treatment, or is part ( or all) of the effect simply a placebo effect?)

They think they are getting a medicine

19

/26

MANIPULATION CHECK

A manipulation check is an additional measure to assess if the participants are aware of, perceived and interpreted the manipulation and/ or to assess the direct effect of the manipulation.

The effects of posting podcasts on students achievement in Math

20

/26

SIMULATION AND FIELD STUDIES researchers often attempt to maximize the realism of the

experimental environment to increase the external validity of the results.

Two standard techniques are used to accomplish this: simulation and field studies.

21

/26

SIMULATION

• Simulation is the creation of conditions within an experiment that simulate or closely duplicate the natural environment being examined.

• Example, the intent of the research was to study the development of interpersonal dynamics and relationships between guards and inmates in a prison. An actual prison, consisting of three barred cells, a solitary confinement facility, guards’ quarters, and an interview room was built in the basement of the psychology building.

22

/26

FIELD STUDIES

Research studies conducted in a real- world environment are called field studies,

In these studies, the researchers create an emergency situation, then manipulate

variables within the emergency and observe bystander responses.

Candid Camera

23

/26

CH6- DISCUSSION

24

/26

CH7- DISCUSSION

Explain the difference between a no-treatment control group and a placebo control group.

Describe the directionality problem and explain how researchers attempt to avoid this problem in an experiment.

25

/26

CH7- DISCUSSION

You have been assigned to do a research to determine if teachers’ dress (casual, formal) is a significant factor in students’ evaluation of teachers’ professional qualifications.

Briefly explain the steps you need to take to do an experimental research to find the answer to your research question.

26