lecture notesnota_8_eksperimental design (1)

8/10/2019 Lecture NotesNota_8_Eksperimental Design (1)

1/41

Rekabentuk Kajian Eksperimental

Norlena Salamuddin

Selamat Datang ke GGGB6013

Kaedah Penyelidikan I


2/41

Rekabentuk Kajian Eksperimental

Penyelidik mempunyai kawalan ke atas

kajian dari aspek pemilihan sampel,

rawatan yang diberikan, persekitaran,

dsb


3/41

Research

True Experimental

Quasi-Experimental

Ex Post Facto (Causal-Comparative)

Jenis-jenis.


4/41

Ciri-ciri Kajian

Eksperimental Benar Terdapat kumpulan kawalan atau perbandingan

Subjek diagih secara rawak

Rawatan diberi secara rawak kepada kumpulan

Sering digunakan dalam psikologi, perubatan,

pendidikan, dsb


5/41

Ciri-ciri Kajian Kuasi

Eksperimental

Terdapat kumpulan kawalan atau perbandingan

Kumpulan sedia ada digunakan Rawatan diberi secara rawak kepada kumpulan

Dilaukan dalam persekitaran natural

Sering digunakan dalam ekonomi, sosiologi,pentadbiran awam, perancangan bandar dan

wilayah, sains politik, dsb


6/41

Ciri-ciri KajianEx Post Facto

Terdapat kumpulan kawalan atau perbandingan

Kumpulan sedia ada digunakan

Kawalan tidak dimanipulasi, tetapi telah berlaku


7/41


8/41

Lakaran Kajian

Untuk ilustrasi rekabentuk kajian, beberapa

simbol digunakan:X1= Rawatan

X2= Kumpulan kawalan

O = Pemerhatian/Cerapan (pra- atau pos-ujian)R = Pemilihan/Agihan rawak


9/41

Sampel Rekabentuk Kajian

Single-Group Pretest-Treatment-

Posttest Design

R O X1O Ini bermaksud, subjekdipilih secara rawak kepada

kumpulan, diberi pra-ujian,kemudian diberi rawatan,

kemudian diberi pos-ujian.


10/41

R O X1O

This is not really an experimental designbecause there is no control group

It is often referred to as a preexperimental design

Novice researchers often use this researchdesign

There are some major problems with thisdesigndid the treatment really make the

difference or was something else happening.


11/41

R O X1O

What are the threats to the Internal

Validity of this type of research (Did

the treatment really cause a

difference?)


12/41

Internal Validity Threats

History

Another event occurs during the time of theexperiment that might cause the difference

An experiment to heighten racial awareness wasconducted by a researcher during February. This isBlack History month; so the results might be affected

by events that occur during Black History month andnot the treatment.

R O X1O


13/41


Maturation

People naturally change and evolve over time.This may cause the difference.

A college develops a new housing plan to promotemore open-mindness and acceptance of others. Thestudents are tested when they enter college and when

they graduate. The results show they are now moreopen-minded and tolerant of others. Did the housingplan work or do students just mature and grow as aresult of the college experience.

R O X1O


14/41


Mortality

Some people drop out during an experiment. Thismay affect the outcome.

I am teaching a new experimental seminar on studyskills. About half of the class stopped coming to theseminar before the semester was over. The students

who remained improved their study skills. So mycourse was effective!

Probably not. The half that stopped coming might nothave gained anything; that is why they stoppedattending.

R O X1O


15/41


Testing

Whenever you give a pretest, the students mayremember the test questions, and get them correcton the posttest.

I gave a test to my study skills group on Monday,presented some unique concepts on Tuesday, then gave

them the posttest on Wednesday. The grades weresignificantly higher on the posttest.

It is possible the grades were higher because the studentsstill remembered the questions from the pretest.

R O X1O


16/41


Instrumentation

To overcome the testing threat to internalvalidity, a researcher develops a different form ofthe test instrument, but it is not really equivalent.

I gave a test to my study skills group on Monday,presented some unique concepts on Tuesday, then gave

them an alternative form of the pretest on Wednesday.The grades were significantly higher on the posttest.

It is possible the grades were higher because the secondtest was easier than the first.

R O X1O


17/41


Regression

When subjects are selected because of extremescores on some type of instrument, there istendency for their scores to move more towardthe average on subsequent tests.

An experimenter selected students for a reading

program based on their low test scores. At the end ofthe treatment, the test scores had improved.

Extreme scores naturally move toward the mean onsubsequent tests.

RO X1O


18/41

How to Handle Internal

Validity Threats

Have a control group and use

randomization.This design is the Two-Group Pretest-Treatment-Posttest

Design.

R O X1O

R O X2O

The Control Group would experience the same

history and maturation. Mortality should be the

same because of random assignment. Random

assignment eliminates the selection threat.

However testing and instrumentation could still

be a threat.


19/41

Other Research Designs

Two-Group Treatment-Posttest-Only

Design

R X1 O

R X2 O

There is no pretest so this

eliminates the testing and

instrumentation threat to

internal validly but youdont know about their

knowledge or attitude

coming into the study.


20/41

Other Research Designs

Solomon 4-Group Design

R O X1 O

R X1 O

R O OR O

Note: A blankindicates the

control group,

same as X2


21/41

Quasi-Experimental Designs

Posttest Only Nonequivalent Group

Design

X1 O

X2 O

The absence of R indicates

there is no random

assignment. Sometimes you

will see a dotted line

between the two groups.

This indicates the two

groups may not be

equivalent.


22/41

Quasi-Experimental Designs

Pretest-Posttest Nonequivalent Group

Design

O X1 O

O X2 O


23/41

Time Series Designs

O O O X1 O O O


24/41

External Validity

Can the research be generalized to

other settings?

Population Validity

Personological Variables

Ecological Validity


25/41

Population Validity

Is the sample population similar to the

population the researchers wishes to

generalize to


26/41

Personological Variables

Different people have different

personalities, learning styles, etc., so

the results may not be generalizable to

people who are substantially different

on these personological variables.


27/41

Ecological Validity

The setting or situation in which the

experiment occurred may be differentthan other settings.


28/41

Social Interaction ValidityThreats

Diffusion or Imitation of Treatment

This occurs when a comparison group learnsabout the program either directly or indirectly

from program group participants.

This group may try to imitate or emulate what the

treatment group is getting.


29/41


Compensatory Rivalry

The comparison group knows what

the program group is getting and

develops a competitive attitude with

them.


30/41


Resentful Demoralization

This is almost the opposite of compensatoryrivalry. Here, students in the comparison

group know what the program group is

getting. But here, instead of developing a

rivalry, they get discouraged or angry andthey give up.


31/41


Compensatory Equalization of

Treatment

The researcher is under pressure to

enrich the experiences of the control

group. This pressure may come fromparents, school administrators, etc.


32/41

Ex Post Facto (Causal-Comparative) Research

Explores possible causes and effects

The independent variable is not manipulated,it has already been applied

Focuses first on the effect, then attempts to

determine what caused the observed effect.


33/41

Statistical Analysis

If we are comparing the scores of two

groupsa t-test is normally used. Thevalue of t means nothing by itself

(unlike the value of R). We have to

determine if t is statistically significant

Tea for two


34/41


If we are comparing the scores of three

(or more) groupsAnalysis ofVariance (ANOVA) is used. This testgives us a f value which means nothingby itself. We have to determine if it isstatistically significant.


35/41


If we want to statistically equate two or more

groups (because one group had a high pretestscore) we use Analysis of Covariance

(ANCOVA). This test gives us a f value

which means nothing by itself. We have to

determine if it is statistically significant.


36/41

Changes to look for.

CONVERGENCE-DIVERGENCE

Positive change in the treatment

group without change in the control

group Treatment

Control

Treatment


37/41

Divergence

Positive increments at a different rate

Treatment

Control


38/41

Convergence

The treatment group catches up with the

control group

Control

Treatment


39/41

Cross pattern

The treatment group overpass the control

group Treatment

Control


40/41

TIMEX

No effect

Change in the rate or slope

Change in the intercept


41/41

Questions?

lecture notesnota_8_eksperimental design (1)

Documents