ESM 641�RESEARCH METHODS IN EDUCATION

Chapter 5 & 6

Video C

​

​

Dr Kim Teng Siang

kskim2007@gmail.com

h/p: 0124661131

5. Experimental Method (2)

WHAT IS A RESEARCH DESIGN?

• research design refers to the outline, plan, or strategy specifying the procedure to be used in seeking an answer to the research question

SYMBOLS USED IN EXPERIMENTAL RESEARCH DESIGNS

• O = Observation or Measurement , O

​

O1, O2, O3 ………… On

​

• R = Random assignment

​

• X = Treatment or intervention , teaching methods

Weak Designs

• NO Control group

​

a. One-Shot Design,

b. One-Group Pretest-Posttest Design

​

c. Non-Equivalent Posttest-Only

​

​

​

Strong Designs

• Have Control group, Random assignment to groups, Equivalent groups

​

a. After-Only Research Design

b. Factorial Research Design

(After-only but involved 2 IV)

​

c. Before-After Research Design

​

​

​

2 x 2 design, 2 x 3 design etc

Quasi-Experimental Design

• Have Control group

But No Random assignment to groups or Equivalent groups

​

a. Non-Equivalent Control-Group Design

​

b. Interrupted Time Series Design

​

​

​

Factorial Research Design

• Is an after-design experimental research
• Involved study of two or more independent variables simultaneously and
• their interactive effects on the dependent variable.
• Denote by 2 x 2, 2 x 3, 3 x 3 … the numbers show the levels of each IV

Example ( 2 x 2 design) �(pg 7-12)

IV1

Academic ability

• High
• Low

DV

History Test Achievement

IV2

Instruction Methods

- Inductive

- Deductive

1. There is no significant difference between the inductive method and deductive method

on performance in history (MAIN EFFECT – Method)

2. There is no significant difference between high and low ability students on performance

in history (MAIN EFFECT – Ability)

3) There is no significant interaction between method and ability (INTERACTION EFFECT)

​

1

2

3

Interactive Effect (2 x 2 factorial design)

Low

High

Academic Ability

Histotry score

Deductive

Inductive

No interaction, Academic ability has a positive effect

for each method, Inductive higher than deductive

Low

High

Academic Ability

Deductive

Inductive

Has interaction, Academic ability has a positive effect

for deductive but not Inductive, inductive more effective for low acad. than deductive and vice versal

6. Survey Method

INTRODUCTION

• Do you want to know what people are thinking, feeling or doing?

​

• How to find out quickly and economically?

WHAT IS A SURVEY?

• a method of obtaining information about a population from a sample of individuals.
• Surveys can provide a quick, inexpensive and accurate means of obtaining information from a large group of people

TYPES OF SURVEYS

• Figure 6.1 , pg 4
• Cross-sectional – immediate
• Sample from a cross section of the population

​

• Longitudinal – same sample - longer time - see the changes at different points of time
• Trend study
• Cohort Study – same group with the same

characteristic – different samples

• Panel Study – same participants

SAMPLING

• Census -- 100% of the population studied

(Panji)

​

• Survey ---Sample or part of the population

Sample represent the population?

• How can it be?

​

• Yes by taking random sample

​

• i.e. every one in the population has the same chance to be selected

SAMPLING TECHNIQUES

• Probability sampling – selection by chance alone
• Simple random
• Systematic
• Stratified
• Cluster
• Non-probability sampling – not by chance
• Quota
• Purposive
• convenience

A) Probability sampling� i) Simple Random Sampling

• If sample and population is small
• Can use draw lot or random number table

​

• Is sample & population is big like whole Malaysia
• See Fig 6.3 , pg 7
• Must have whole list of the accessible population
• Then use random number table or SPSS

ii) Systematic sampling

• an N^th name selection technique.
• E.g.
• You want to select a sample of 100 students from a population of 1000 students.
• You divide the population by the sample needed (1000 / 100) = 10
• You select at random a number smaller than 10
• You start with that number (e.g. 8) and select every eighth name out of the next 10 from the list of the population.

​

1 2 3 4 5 6 7 8 9 10

Random draw one number, let’s say 8

18

28

1000

988

998

iii) Stratified sampling

• ensure that individuals with certain characteristics or groups are included in the sample to be studied.
• See Table 6.2
• the proportion of students randomly selected to fill each of the groups is the same as the population

45%

Malay

25%

India

30%

Chinese

45%

Malay

25%

India

30%

Chinese

25%

India

30%

Chinese

45%

Malay

Population, N=1,000,000

Sample, n=1000

iv) Cluster sampling

• the unit of sampling is not the individual but rather a group of individuals or class
• saves time and money
• But less accurate compared to other techniques

​

• LEARNING ACTIVITY, pg 10

 �B) Non-Probability Sampling� i) Quota sampling��

• unable to ensure that subjects are randomly assigned to the subgroups
• Select the proportions of subgroups based on the actual proportions to the population
• Selection is based on convenience not chance

​

​

ii) Purposive sampling

• select cases to answer certain research questions
• sample may have characteristics which differ from population characteristics.

iii) Convenience sampling (like TV)

• the freedom to choose whomever they find
• sample people who are easy to survey
• least reliable because of its high incidence of biasness.

5.5 SAMPLE SIZE

• general rule is to use the largest sample possible.
• If involving comparisons of many smaller groups (male & female), a larger sample is advisable
• attrition is expected, especially in longitudinal studies, bigger sample
• population is highly heterogeneous on the variables, larger sample

THE PROCESS OF CONDUCTING A SURVEY (7 steps)

1. Defining the Objectives of the Study

2. Writing & Constructing the Items in the Questionnaire

3. Method of Conducting the Survey

4. Pilot-Testing of the Questionnaire

5. Administering the Questionnaire

6. Data Entry and Analysis

7. Writing the Report

​

DATA COLLECTION METHODS USING SURVEYS

• a) Mail Surveys
• b) Web Survey
• c) Telephone Interviews
• d) Face-to-face Interview
• e) Group-Administered Questionnaire

​

• Fig.6.3 , pg 18

​

ETHICS IN SURVEYS

Confidentiality and integrity in surveys

• use only number codes
• names and addresses of survey respondents should not be made available to anyone outside those involved
• Omitting the names and addresses of survey respondents from computer files used for analysis
• Presenting statistical tabulations using broad enough categories so that individual respondents cannot be singled out.
• Respondents should be informed about the purpose of the survey and have the option not to participate or not to divulge information that he or she feels not comfortable

​

SAMPLE OF SURVEY

Module 10.3

2002 Survey of Voters and Non-voter

- Methodology Report

​