CAUSAL-COMPARATIVE RESEARCH LIYANA BT AHMAD AFIP 2010439958 1.

CAUSAL-COMPARATIVE RESEARCHLIYANA BT AHMAD AFIP2010439958

1

OVERVIEW

Description Characteristics Procedure Sample Data Analysis Example of topics Example of research utilizing the

methodology

2

DESCRIPTION

It is a quantitative research To determine the cause or consequences

of the differences that already exist between or among group of individuals- ‘ex post facto’

One variable is considered as the causal (independent variable) and one variable is considered the effect (dependent variable)

3

CHARACTERISTICS

There are three types of causal-comparative research: Exploration of effects Exploration of causes Exploration of the consequences

It is an alternative to experimental research

Disadvantage: lack of control over threats to internal validity Lack of randomization Inability to manipulate independent variable

4

CHARACTERISTICS

CAUSAL –COMPARATIVE VS CORRELATIONAL RESEARCH

CAUSAL COMPARATIVE VS EXPERIMENTAL RESEARCH

SIMILARITIES:Both explore relationship among variables, and after the relationship is identified, it will then studied by using experimental research

DIFFERENCES:Causal- compare two or more groups of subjects; correlation- require each variable for each subjectCausal- involve at least one group membership; correlation- two and more variablesCausal- compare average /crossbreak table; correlation-scatterplot

SIMILARITIES:Both require at least one categorical variable (group membership) and compare the performance t determine relationship

DIFFERENCES:Causal- no manipulation takes place; experimental-independent variable is manipulatedCausal- weaker evidence for causation than experimental studiesCausal- locate already formed group; experimental- can create treatment groups

5

PROCEDURE

Problem formulation Identify and define particular phenomena of

interest and then to consider possible causes for, or consequences of these phenomena

Sample Define carefully the characteristic to be studied

and select group that differ in this characteristic Instrumentation

No limitation Design

Involve selecting groups that differ on particular variable of interest, compare and remember no manipulation!

6

DATA ANALYSIS

Construct frequency polygons Calculate means and standard

deviations T-test to show differences between

means The result do not prove cause and effect,

but only identifying the relationship

7

EXAMPLE OF TOPICS

The effect of gender on a visual alertness measure for 6th grade public school pupils

Classroom behavior of good and poor readers

A comparative study of the pre-service teachers’ self-efficacy based on field experience

8

EXAMPLE OF RESEARCH

Author: Talebi, S.H., & Maghsuodi, M.(2008) Title: Monolingual and Bilingual English

Learners in one Classroom: ‘Who is at a Disadvantage?’

Source: Asian EFL Journal, Volume 10. Issue 3, Article 10.

Purpose: To investigate how monolingual and bilingual ESL learners perform on reading comprehension tests in mixed mono/bilinguality classrooms

9

EXAMPLE OF RESEARCH (cont.) Hypotheses:

1. Bilingual and monolingual students differ significantly in reading comprehension scores

2. There will be significant interaction between linguality and proficiency in reading comprehension scores

3. Male and female students differ significantly in their reading comprehension scores

4. There will be significant interaction between linguality and gender in reading comprehension scores

10

EXAMPLE OF RESEARCH (cont.) Sample: male and female 1st year pre-

university students (157 students, group A- 47 M, 30 F, Mono; group B, 53 M, 27 F, Bili)

Instrumentations: Language Proficiency test (NELSON, series 400 B), Test of reading comprehension in English, Self evaluation proficiency scale and background questionnaire

Procedure: 3 Phases, refer to handouts

11

EXAMPLE OF RESEARCH (cont.) Results

1. Bilingual students had significantly higher score than monolingual students

2. There was a significant interaction effect between linguality and proficiency, where students with high proficiency and bilingualism had highest scores

3. The third and forth hypotheses were rejected as there were no significant differences between gender as well as for interaction between linguality and gender.

12