Scribd
Upload
36 views23 pages

A-Inferental Data Correlation.

The document discusses inferential data analysis and provides examples of correlation analysis. It defines descriptive and inferential statistics, with the latter helping to make inferences about populations based on samples. Correlation analysis examines relationships between two numeric variables and can be positive, negative, or zero. The intensity of a correlation is classified as perfect, high, moderate, low, or none based on the correlation coefficient value. Examples are provided to illustrate positive, negative, and no correlations. [/SUMMARY]

Uploaded by

y64pnh9x8b
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
36 views23 pages

A-Inferental Data Correlation.

The document discusses inferential data analysis and provides examples of correlation analysis. It defines descriptive and inferential statistics, with the latter helping to make inferences about populations based on samples. Correlation analysis examines relationships between two numeric variables and can be positive, negative, or zero. The intensity of a correlation is classified as perfect, high, moderate, low, or none based on the correlation coefficient value. Examples are provided to illustrate positive, negative, and no correlations. [/SUMMARY]

Uploaded by

y64pnh9x8b
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 23

INFERENTIAL DATA

ANALYSIS
DATA ANALYSIS

In the research process, DATA ANALYSIS


comes after data collection and before the
final stage, i.e., study report.
The results of the data analysis are
traditionally called ‘Research findings’.
These findings answer the Research
Question(s).
INFERENTIAL DATA ANALYSIS

There are two major types of data analysis procedures used in


research:
1. Descriptive Statistics
2. Inferential Statistics
Descriptive statistics simplify and organize data collected.
Inferential statistics assist in making inferences about the
population of data-points represented and the relationship
between data-point populations. In other words, it helps us
understand what the data means in our context.
INFERENTIAL DATA ANALYSIS TOOLS

There are many inferential data analysis


instruments (Correlation, T-Test, Multiple
Regression, ANOVA, MANOVA, ANCOVA, etc.).

The ‘choice’ of the appropriate data analysis


tool depends on the research question and the
nature and number of the variables studied .
EXAMPLE OF FIRST STEP

 RQ:
 What is the influence of anxiety on students ’ oral
performance?

 What are Variables?


 V1: Anxiety
 V2: oral performance
DATA ANALYSIS TOOLS

For the purpose of this course (PSYC4138) we


shall focus on two statistical analyses, namely
CORRELATION and T-TEST.
CORRELATION

Correlation is inferential. Findings can be


generalised.
Used to examine relationships between
variables which appear to respond to each
other without a clear IV-DV association(ONE
group, two or more measurements).
Pearson’s Correlation Moment ‘r’ is used to
measure the potential correlation between
two NUMERIC variables (e.g. age and weight).
CORRELATION- USES

Pearson Correlation Moment ‘r’ is for research


on relationship between two numeric
variables.
Answers research questions such as:
1. Is there any relationship between students’
family size (number) and academic
achievement (score)?
2. Is there any relationship between students’
achievement in IELTS (score) and their CGPA
(score)?
EXAMPLE OF CALCULATING
CORRELATION
 RQ:
 What is the influence of anxiety on students ’ oral
performance?

 What are Variables?


 V1: Anxiety
 V2: oral performance

 Are these two variables are NUMERIC?


 Yes
 Therefore, We can use Pearson correlation
 Strongly agree =100
 A gree=75
 Not sure=50
 Disagree=25
 Strongly disagree=0

 1- How much do you like English speaking?


 A=5
 B=4
 C=3
 D=2
 E=1

 What is your favorite social media?


 YouTube
 Twitter
 WhatsApp
 A=1
 B=2
 C=3
MEASURING THE VARIABLES

 Each Variable should be converted to Numbers (NUMERIC).


 V1: Anxiety measured by Anxiety questionnaire,
 Mark each questionnaire to find the total mark of each
student in Anxiety

 V2: Oral performance measured by students ’ mark in


Speaking Test.
 Calculate the total mark of Each student in speaking test

 Input them into SPSS to analyse them


CORRELATION

 Correlation “indicates the extent to which two variables are


related or associated
▪ The extent to which the direction and size of deviations from the
mean in one variable are related to the direction and size of
deviations from the mean in another variable”

12
CORRELATION-INTERPRETATION

Two aspects need to be reported in a


correlation study:
A- DIRECTION: Correlation score comes in the
form of a fraction (coefficient) between -1 and
+1. (NEGATIVE or POSITIVE)
B-INTENSITY: The degree of relationship
between the two variables (Perfect-High-
Moderate-Low-None).
CORRELATION-INTERPRETATION

 DIRECTION:

SCORE READING MEANING

POSITIVE POSITIVE When the value of one variable goes UP or


CORRELATION DOWN, the value of the other variable goes UP,
DOWN (Example 1). Up-Up, Down-Down

NEGATIVE NEGATIVE When the value of one variable goes UP, the
CORRELATION value of the other variable goes DOWN (Example
2). Up-Down, Down-Up

ZERO NO The two variables are independent from each


CORRELATION other and move up and down randomly (Example
3).
EXAMPLE OF CORRELATIONS

15
EXAMPLE 1: POSITIVE CORRELATION

WEIGHT
12

10

6
WEIGHT

0
0 2 4 6 8 10 12 14
EXAMPLE 2: NEGATIVE CORRELATION

SLEEP
25

20

15

SLEEP

10

0
0 0.5 1 1.5 2 2.5 3 3.5 4 4.5
EXAMPLE 3

laughing
12

10

6
laughing

0
0 1 2 3 4 5 6 7 8
CORRLEATION-INTENSIT Y

If the absolute value of ‘r’ value is 1, the


correlation is PERFECT.
If ‘r’ is between .61 and .99, it is HIGH.
If ‘r’ is between .3 and .6, it is MODERATE.
If ‘r’ is below .3, it is LOW
If ‘r’ is 0, there is NO CORRELATION.
CORRELATION-INTERPRETATION

1 PERFECT POSITIVE CORRELATION


.61 ------ .99 HIGH POSITIVE CORRELATION
.31 ----- .6 MODERATE POSITIVE CORRELATION
.1 ----- .3 LOW POSITIVE CORRELATION

0 NO CORRELATION

-.1 ---- -.3 LOW NEGATIVE CORRELATION


-.31 ---- -.6 MODERATE NEGATIVE CORRELATION
-.61 ------ -.99 HIGH NEGATIVE CORRELATION
-1 PERFECT NEGATIVE CORRELATION
REPORT WRITING FOR C0RRELATION

 A Pearson correlation analysis was conducted on a


sample of n=… to examine the potential relationship
between ….. and ….
 The study found a negative/positive
strong/high/moderate/low correlation between the
two variables (+/- r= -.696). This correlation is
statistically significant< 0.05 (p=.004)/ or is not
significant (p> 0.05). The study suggests that the
more ….. the more/less …., however it is/is not
generalizable to the society (is not only if p is not
significant>0.05)
EXAMPLES-3

▪ Examine the following scenarios and give a two -sentence


report of their findings

RQ N Alpha p
Effect of method of study on academic performance 50 .05 .02

Effect of new textbook on grammar skills development 40 .05 .10

Relationship between students’ learning history and 60 .05 .21


their motivation
EXAMPLE OF CORRELATION

 Do some exercise calculating correlation

 LOOK at this example

 SPSS/JASP output

 HOW to Interpret and write Report about Correlation

You might also like