AYESHA AYUB

20211-29883

INTRODUCTION TO BEHAVIOURAL STATS-STA410

SUBMITTED TO DR SHAHID IQBAL

DATED 20TH, October, 2021

ASSIGNMENT #01
Statistics

Statistic is the science of collecting, organizing, summarizing and interpreting large amount of

data for decision making. It is used to manipulate and analyze large amount of data available

(raw data) or data that has already been collected by primary sources (secondary data) for

information-decision making process.

There are two types of statistic:

1. Description Statistics

2. Inferential Statistic

Descriptive Stats: Descriptive statistics are used to meaningfully and effectively describe or

summarize data.

Inferential Stats: You can use inferential statistics to construct predictions (inferences) based on

the data. Inferential statistics are used to generate generalizations about a population using data

from samples.

Example

You could, for example, stand in a mall and ask a random sample of 100 people if they enjoy

shopping at Dolmen. You could produce a bar chart with yes/no responses (descriptive

statistics), or you could utilize your study (inferential statistics) to conclude that about 75-80

percent of the population enjoy shopping at Dolmen.

Type of Data in Statistics

There are two main type of data in statistics:

 1. Quantitative data: Data available in form of numbers is known as quantitative data. It

can be further divided into two groups: (i) Discrete data is the data that can be described

as data available in whole numbers that can’t be further divided e.g. Number of female

participants in the study and, (ii) Continuous data is the data that can be further divided

into parts e.g. Height or Weight of male students in the class.

2. Qualitative data: this type of data is data that is available on the basis on quality of

things e.g. eye color of female cats or Hair color, Origin country, Gender etc.

Discrete data
QUANTITATIVE
DATA
Continuous
TYPE OF DATA
data
QUALITATIVE
DATA

There are four level of data in Statistics:

1. Nominal data

2. Ordinal data

3. Interval data

4. Ratio data
 Interval data
QUANTITATIVE
DATA
Ratio data
LEVEL OF DATA
Nominal data
QUALITATIVE
DATA
Ordinal Data

Nominal data: This type of data is categorized on the basis of classifications i.e. how many

participants and grouping.

Example: Gender (male/female), Nationality (Pakistani/American/British), Music Genre

(Pop/Rock/Disco pop/R&B) etc.

Ordinal Data: this type of data is categorized on the basis of order.

Example: Opinion (Strongly Agree/Agree/Neutral/ Disagree/Strongly Disagree), Education

Level (Ph.D./Masters/Undergrad/Intermediate/Matriculation), Socioeconomic status (Lower

class/Lower middle class/Middle Class/Upper Middle Class,/Lower Upper Class/Middle Upper

Class/Upper class)

Interval Data: It is a data type that is measured along a scale with each point put at the same

distance from the others.

Example: Temperature, Time Interval etc.

Ratio Data: this type of data has a non-arbitrary zero point. With an equal and definitive ratio

between each data and absolute "zero" being taken as a point of origin, it has the same qualities

as interval data.

Example: Boiling Point of water, Distance, Time

Sampling: In statistical analysis, sampling is the process of selecting a specific number of

observations from a larger population.

Population and Sample:

A sample is a subset of the population, whereas a population is a complete group of people with

a specialized set of characteristics.

Example: People living in Karachi (Population)

People living in Karachi who are currently residing in Defense Housing Authority DHA

(Sample)

Type of Sampling Techniques: There are two type of sampling techniques: (i) Probability

sampling and (ii) Non-Probability Sampling.

Probability Sampling: Probability sampling is the process of selecting a sample from a

population using the principle of randomization, often known as random selection or chance i.e.

each participant has equal chance of being selected as a participant. It can be further divided into

three types:

S.no. Definition Example

1 Simple Random: A simple random sample is a Out of total number of 200

subset of a statistical population in which each students studying in A-Level, 50

 subset member has the same chance of being students are selected by chit-in-hat

chosen. A simple random sample is intended to technique

represent a group in an unbiased manner (Chit-in-

hat technique, Fish Bowl technique).

2 Stratified Sampling: Stratified random sampling 1. 25 number of males whom

is a sampling method in which a population is belong to any non-muslim

divided into smaller sub-groups called strata minority group

depending on shared features or characteristics

among individuals, such as income or educational 2. males who belong to any

attainment. It is further divided into two types: non-muslim minority

1.Proportionate- In proportional sampling, each group

stratum has the same sample fraction (fixed

number)

2. Disproportionate- In disproportional

sampling, each stratum has a different sampling

fraction.

3 Cluster/Area Sampling: Cluster sampling is the A company wants to do survey on

type of sampling in which researcher divides the which city has highest number of

population into different clusters. android user in Pakistan. They can

divide the country’s population

into cities (cluster) and then filter

out those using android cluster

 wise.

Non-Probability Sampling: In this type of sampling, there is no equal chance of being selected

rather researcher make subjective judgement to choose sample.

s.no Definition Example

1 Quota Sampling: a non-probability sampling A company wants to conduct a

technique in which the probability of occurrence research university student (100%)

is not taken into account. The researcher chooses and their self-esteem sample of

the sample method based on a quota in this students 30% are enrolled in

process. Quota sampling ensures that the final Engineering, 50% are enrolled in

sample meets the researcher's quota standards. BBA and 20% are enrolled in

Psychology
2 Accidental/Convenience sampling involves A company wants to conduct a

taking a sample that is close to hand or easier to survey for their brand so they

reach. For pilot testing stage of hypothesis this approach customers coming at

type of non-probability sampling is the most their shop or people randomly

useful. passing-by their stall.

3 Purposive/Judgmental is the type of non- As a researcher you want to

probability sampling that involves researchers conduct research on high-school

own subjective opinion. This type of sampling is students so you purposely go to

done on the basis of researcher’s judgement high-schools to select your sample

4 Snowball Sampling is the type of non- To find a sample of people who

probability sampling in which you find sample are homeless you might approach

with reference to reference. This type of sampling one person and ask him to refer

is used to find characteristic that are rare to find. you to another and thus chain goes
 on
5 Systematic Nth Technique is the type of Every 2nd and 5th candidate will be

sampling in which you decide a nth number on selected as a part of sample

basis on which you select your sample.

6 Saturation Technique is the type of non- You want to conduct a research on

probability sampling in which you select you hospital employees with a FCPS

sample on the basis of characteristic and narrow it degree with specialization in

down into further characteristic cardiology.

7 Dense Technique is the type of non-probability You want to conduct a research on

sampling which is similar to saturation technique female hospital employees with a

except you narrow down your data even further FCPS degree with specialization in

on the basis of required characteristic for your cardiology between the ages of 30-

study 45 years with a work experience of

2-3 years.
8 Double Sampling Technique is the type of non- After deriving a sample of 2000

probability in which you take second set of employee with a bachelor degree

sample from already derived sample. you shortlist 750 out of them to

represent the entire population

Grouped and Ungrouped data: Data (or information) presented in the form of class intervals

such as 0-20, 20-40, and so on is referred to as grouped data. Individual points (i.e. values or

numbers) such as 15, 63, 34, 20, 25, and so on are considered ungrouped data.

Central Tendency: A single number that seeks to represent a set of data by identifying the

center position within that set of data is referred to as a measure of central tendency. Mean,

Median and Mode all are valid measures of central tendency.

Deviation: The standard deviation is a statistic that measures the amount of variation or

dispersion in a set of numbers. A low standard deviation implies that the values are close to the

set's mean (also known as the expected value), whereas a high standard deviation shows that the

values are spread out over a larger range.

Correlation: Correlation is a measure of how closely two variables are linked. As a result, when

one variable increases while the other declines (positive correlation) e.g. Height and Weight,

whereas one variable increases while other decreases (negative correlation) e.g. Daily Exercise

and Weight.

0-0.20 – Very week correlation

0.21-0.40 Week correlation

0.41-0.60 Intermediate/moderate correlation

0.61-0.80 Strong correlation

0.80-1.00 Very strong correlation

Probability: Probability in stats refers to how much likely an event would occur. For example,

Flipping a coin and getting heads or tails has a 50% chance of happening.