Descriptive Statistics

SPSS Version 27

Laiba Ali

Department of Psychology, University of Karachi

532: Introduction to Statistics

Dr. Rabia Riaz

October 28, 2025

 This work is submitted in the partial fulfillment of Course: 532 Introduction to Statistics

Date: 1st Oct 2025

QUESTION: Generate the descriptive statistics for all variables used in the hypothesis we

formed in the class?

Table 1

Demographic Characteristics of the Sample (N = 30)

Variable f % Mean SD
Socioeconomic Status
Lower middle class 3 10
Middle class 16 53
Upper middle class 11 37

Gender
Male 3 10
Female 27 90

Age (18-25 Years) 20.9 2.63

Faculty
Social Sciences 24 80
Pure Sciences 6 20

Academic Year
1st Year 4 13
2nd Year 19 63
3rd Year 3 10
4th Year 4 13

Birth Order
First born 16 53
Middle born 3 10
Youngest born 11 37
Note. (f =Frequency, %=Percentage, M=Mean, SD=Standard deviation).

Table 01 shows that most students belonged to middle socioeconomic families (53%).

Most participants were female (90%), while males accounted for a smaller proportion (10%).

Students’ ages ranged from 18 to 25 years, with a mean age of 20.9 years (SD = 2.63). Most

students were enrolled in Social Sciences (80%), and over half were in their second year of study

(63%). Regarding birth order, most were firstborn (53%), followed by youngest-born (37%), and

middle-born (10%).
Date: 4th Oct 2025
QUESTION :01 Give reason why we enter variables in numeric and string form?

String variables are used for words or text, like names, or categories such as “Male” and

“Female.” They cannot do mathematical calculation like mean, standard deviation, or run

statistical tests like the numeric variables can do. That’s why the variables like gender,

socioeconomic status, academic year, faculty and birth order are taken as string. Numeric

variables contain only numbers. They can do mathematical calculation. They can find the mean,

standard deviation, or run statistical tests. Therefore, we take age as numeric variable.

QUESTION:02 Define standard deviation and explain how it relates to mean?

SD tell us how much the number or value are far or close from the mean value. Small SD

value indicates that number or value are closer to the mean whereas large SD value indicates that

number or value are far from the mean. The mean age of students is 20 years (M =20.9), with a

standard deviation of 2.6 (SD =2.63), which means that most student’s ages are two years above

or below the mean, showing only a small amount of difference.

QUESTION :03 Define different scale of measurement with example?

Nominal Scale: In Nominal scale we put data into categories by name only. The

categories do not have any order, and we cannot do math with them. Example: Blood type.

Ordinal Scale: In Ordinal scale data is divided into categories that can be ranked in order, but

the gaps between them are not equal or known. Example: Customer satisfaction → Dissatisfied,

Neutral, Satisfied.
Interval Scale: An interval scale is a type of measurement where: The numbers are in order, the

distance between numbers is always equal, But the zero does not mean nothing – it’s just a point

on the scale. Example: Temperature.

Ratio Scale: A ratio scale is the highest level of measurement because it has all the features:

You can categorize (put into groups), you can order/rank the values, the intervals between

numbers are equal, and most importantly, it has a true zero, which means zero = none of that

thing exists. Example: Age

QUESTION :04 Explain which variables are taken as nominal and ordinal in your data

and why?

In my table, faculty, gender, socioeconomic status are nominal variables, used only for

labeling without any ranking. Academic year, and birth order are ordinal variables since they

have a natural order but unequal intervals for example, categories like firstborn, middle born, and

youngest born indicate ranking without measurable gaps between them. The age is a ratio

variable because it has equal intervals between values, meaning the differences and proportions

between ages can be precisely measured.

 Date: 14th oct 2025

QUESTION: Calculate the correlation between birth order and self-esteem, and state the

corresponding hypothesis?

Table 2

The Relationship Between Birth Order and Self Esteem (N=30)

Self-Esteem Total
Spearman’s rho Birth Order Correlation Coefficient -.090
Sig. (2 tailed) .636
N 30
Note. The results showed a weak, negative, and non-significant correlation between the

two variables (rₛ (28) = –.090, p = .636), indicating that birth order had little to no association

with self-esteem.

Hypothesis:

There is no significant correlation between birth order and self-esteem.

 Date: 28th Oct 2025

QUESTION: Make the Bar Graph and Scatter Plot of variables and answer the following

question?

QUESTION: Why are Scatter plots are used to show correlation and not for any other

types of graphs?

Scatter plots are used to show correlation because they display the values of two variables

together. One variable is on the X-axis and the other on the Y-axis, so we can clearly see how

they move, if one increases when the other increases or decreases. This helps us check the

direction, strength, and pattern of the relationship between both variables. Other graphs like bar

charts, line graphs, or pie charts cannot show this, because they don’t display both variable’s

points together. They only show totals or single-variable information.

QUESTION: Which type of variables are displayed in Bar Graphs and Histograms?

Bar graphs are used to display categorical variables such as faculty, gender, and

socioeconomic status (SES), while histograms are used to display continuous variables, which in

our case is the age of participants.

Bar Graphs

Figure 01

Distribution of the Participants by Gender (N=30)

 Note. This bar graph shows that most of participants were female (n=27), while only a

few were male (n=3).

Figure 02

Distribution of Participants by Faculty (N=30)

 Note. The bar graph shows that most of the participants were from social sciences (n=

(n=24), while fewer were from science (n=6).

Figure 03

Distribution of Academic Year of the Participants (N=30)

 Note. The bar graph shows that most of the participants were from 2nd year (n=19), while

fewer were from 1st (n=4), 3rd (n=3), and 4th year (n=4).

Figure 04

Distribution of the Participants by Socioeconomic Status (N=30)

 Note. The bar graph shows that most participants belonged to the middle class (n=16),

followed by the upper middle class (n=11), while fewer were from the lower middle class (n=3).

Figure 05

Distribution of the Participants by Birth Order (N=30)

 Note. The bar graph shows that most participants were first-born (n=16), followed by

youngest-born (n=11), while fewer were middle-born (n=3).

Histogram

Figure 06

Age Distribution of the Participants (N=30)

 Note. The histogram shows that most participants are around 18 years old, and only a few

are older, between 22 and 25 years and the mean age of the participants were 20 years (M=20.9).

Scatter Plot

Figure 07

Scatter Plot showing relationship between Self Esteem and Birth Order (N=30)
 Note. This graph explores the relationship between birth order and self-esteem. The x-

axis displays self-esteem scores, while the y-axis categorizes individuals by their birth order

(oldest, middle, youngest). The data points suggest a weak correlation, indicating that self-

esteem varies across different birth order positions.