This document discusses correlational research methods. It explains that correlational research involves observing relationships between variables without manipulating them. There are two types: retrospective, which looks at cause and effect after an event, and prospective, which looks at cause and effect as an event unfolds. Key aspects of correlational research include having a dependent variable and two or more naturally occurring groups, being unable to manipulate organismic variables, and using statistical controls and multiple studies to strengthen hypotheses about causality.
Food processing presentation for bsc agriculture hons
Causal Comparative Research Methods
1.
2.
3.
4. Variable cannot be manipulated for ethical & practical
reasons.
Individuals are not randomly assigned to group.
Allow researcher to determine what variable causes
another variable.
2 types of CCR:
• A researcher starting with effect & investigate cause.
• Common in educational research.
Retrospective CCR
• Starting with cause & investigate effect.
Prospective CCR
5. 1 DEPENDENT VARIABLE & 2 OR MORE GROUPS OF
PARTICIPANTS.
RESEARCHER PREFER THE TERM “GROUPING VARIABLES”
RATHER THAN INDEPENDENT VARIABLE.
RESEARCHER CANNOT CONTROL AN ORGANISMIC VARIABLE.
ORGANISMIC VARIABLE: IS A CHARACTERISTICS OF A
SUBJECT / ORGANISM.
ETHICAL CONSIDERATIONS OFTEN PREVENT MANIPULATION
OF A VARIABLE THAT COULD BE MANIPULATED BUT SHOULD
NOT BE, PARTICULARY WHEN THE MANIPULATION MAY
CAUSE PHYSICAL / MENTAL HARM TO PARTICIPANTS.
6. GROUPING VARIABLE
CANNOT BE
MANIPULATED
• SOSIOECONOMIC
STATUS
SHOULD NOT
BE
MANIPULATED
• NO OF
CIGARETTES
SMOKED PER DAY
SIMPLYARE
NOT
MANIPULATED
BUT COULD BE
• METHOD OF
READING
INSTRUCTIONS
9. BASED ON EXPERINCES
OR SITUATIONS THAT
HAVE OCCURRED IN THE
REAL WORLD.
KNOWLEDGE ON THE
EVENT MIGHT IMPACT
RESEARCHER’S FUTURE
BEHAVIOURS.
10. REVIEWING PUBLISHED
LITERATURE ON SPECIFIC TOPIC.
IDENTIFY AN INDEPENDENT
& DEPENDENT VARIABLES.
• THE CHARACTERISTICS / EXPERIENCE THAT DIFFERS
BETWEEN THE GROUPS STUDIES WHERE CANNOT BE
MANIPULATED.
INDEPENDENT
VARIABLE
• THE VARIABLE THAT IS IMPACTED IN SOME
WAY BE THE INDEPENDENT VARIABLE.
DEPENDENT
VARIABLE
11. RESEARCHER MUST CONSIDER OTHER
EXPLANATIONS SUCH AS REVERSE CAUSATION.
RESEARCHER ASSUMED ERRONEOUS THAT ANY
RELATED EVENT THAT HAS OCCURRED PRIOR TO
THE DEPENDENT IS THE CAUSE.
SHOULD DESCRIBE THE EXPECTED IMPACT OF THE
INDEPENDENT VARIABLE ON THE DEPENDENT
VARIABLE.
12. STATISTICAL TESTS IS USED TO ACCOUNT FOR EXTRANEOUS
VARIABLE.
CCR CAN EMPLOY A VARIETY OF METHODS TO CONTROL FOR
EXTRANEOUS VARIABLES.
MUST BE DETERMINED THAT THE GROUP ONLY DIFFER BASED ON
THE INDEPENDENT VARIABLE.
GROUPS DEFINED AS COMPARISON GROUP.
ALREADY ORGANIZED IN GROUPS.
13. SELECT INSTRUMENTS
THAT ARE RELIABLE &
ALLOW RESEARCHER TO
DRAW VALID
CONCLUSIONS.
RESEARCHER DO NOT
REQUIRED TO IMPLEMENT
A TREATMENT -
TREATMENT HAS ALREADY
OCCURRED.
14. HYPOTHESIS REGARDING CAUSALITY CAN BE STRENGTHENED WHEN
MULTI CCR HAVE BEEN CONDUCTED BY A VARIETY OF RESEARCHERS.
IT IS BECAUSE RESEARCHER CANNOT DETERMINE THAT ONE
VARIABLE HAS CAUSED SOMETHING OCCUR.
MUST CAREFUL WHEN STATING THAT THE INDEPENDENT VARIABLE
HAS CAUSED A SPECIFIC EFFECT TO OCCUR.
INFERENTIAL STATISTICS ARE USED FOR THE GROUPS ARE
SIGNIFICANTLY DIFFERENT FROM EACH OTHER.
DATA IS REPORTED AS A MEAN/FREQUENCY FOR EACH GROUP.
19. GROUP MAY
DIFFERENT IN 2
WAYS :
EITHER 1 GROUP
POSSESSES A
CHARACTERISTIC THAT
THE OTHER DOES NOT
BOTH GROUPS HAVE
THE CHARACTERISTIC
BUT TO DIFFERING
DEGREES / AMOUNT
20. THE VARIABLE DIFFERENTIATING THE GROUP MUST
BE CLEARLY AND OPERATIONALLY DEFINED.
BECAUSE EACH GROUP REPRESENTS A DIFFERENT
POPULATION AND THE WAY IN WHICH THE GROUPS
ARE DEFINED AFFECTS THE GENERALIZABILITY OF
THE RESULT.
SAMPLE MUST BE REPRESENTATIVE OF THEIR
RESPECTIVE POPULATIONS AND SIMILAR WITH
RESPECT TO CRITICAL VARIABLES OTHER THAN THE
GROUPING VARIABLE.
23. Technique for equating groups on one or more variables.
Pair-wise grouping
The researcher finds a participant in the other group
with the same or very similar score on control variable
for each participant in one group.
If participant in either group does not have a suitable
match, the participant is eliminated from the study
24. Comparing Homogeneous
Control for extraneous variables that are homogeneous
with respect to the extraneous variables.
Lowers the no of participants in the study & limits the
generalizability of the findings.
Comparing subgroup
Each group represent all levels of the control variable.
Researcher can determine whether the target grouping variable
affects the dependent variable differently at control group.
Build the control variable into the research design & analyze the result
with FANOVA.
25. Statistical technique used to adjust scores on a
dependent variable for initial differences on
some other variable related to performance on
the dependent variable.
28. Indicates the average performance of a group on
a measure of some variables.
Involves mean, median and mode.
Indicates the spread of a set of scores around the mean.
That is whether the scores are relatively close together
and clustered around mean or widely spread out around
them.
29. Used to determine whether the scores of 2
groups are significant different from one
another.
Used to test for significant differences among
the scores for 3 or more groups.
30. Used to compare group frequencies – to see if
an event occurs more frequently in one group
than another group.
31. Used when analysis the result of comparing
homogeneous subgroup (about interest)
Researcher can determine the effects on the
grouping variable (CCR) or independent
variable (Experimental Design) & the
control variable both separately & in
combination.