You are on page 1of 5

2/23/2017

Introductory Statistics What is Statistics?


STAT-302
• “Statistics is a way to get information from data”
Statistics
Data Information
Some Key Definitions &
Information:
Graphs of Qualitative and Discrete dataset Data: Facts,
especially numerical
Communicated
concerning some
facts, collected
particular facts.
together for
reference or
information.

Why study statistics? Brief history?

1. Data are everywhere • The word statistics is derived from the Latin word status (meaning
“state”). Early uses of statistics involved compilations of data and
2. Statistical techniques are used to make many decisions that affect graphs describing various aspects of a state or country. In 1662, John
our lives Graunt published statistical information about births and deaths.
3. No matter what your career, you will make professional decisions Graunt’s work was followed by studies of mortality and disease rates,
that involve data. An understanding of statistical methods will help population sizes, incomes, and unemployment rates.
you make these decisions efectively • Households, governments, and businesses rely heavily on statistical
data for guidance. For example, unemployment rates, inflation rates,
consumer indexes, and birth and death rates are carefully compiled
on a regular basis, and the resulting data are used by business leaders
to make decisions affecting future hiring, production levels, and
expansion into new markets.

Definitions Population vs Sample


Statistical
• Statistics is a collection of methods for planning experiments, Inference
obtaining data, and then processing, summarizing, presenting,
analyzing, interpreting, and drawing scientific conclusions based on Population
the data under uncertain conditions. Sample
(have Parameters)
• Statistics is the subject which deals with the variability. No two (have Statistic)
objects in a universe are exactly alike. If they were, there would have Statistic: 𝑿, S, r
been no statistical problem. Parameters: µ, σ, ρ
• It also deals with uncertainty as every process of getting observations
whether controlled or uncontrolled, involves deficiencies or chance
variation. That is why we have to talk in terms of probability since the Population: A Population Sample: A representative
inferences which are made about the population on the basis of is a group of all part/subset of the
sample evidence cannot be absolutely certain. object/elements/items population.
under investigation.

1
2/23/2017

Why Sampling? Branches of Statistics

• A process of drawing a sample from population is called Statistics


sampling.
• Reduced cost
• Greater speed Descriptive Inferential
• Greater accuracy
• Some times it is the only option (testing the life of bulbs/bulets)
Involves in Organization,
Using sample information
Summarization, and Display of
such as 𝑿, S, r, p to draw
Data into Tables, Graphs and
Inference about the
Summary Numbers such as
Population.
𝑿, S, r, p

Variable Any Characteristics that varies from Object to Object, Place to Place Measurement
or Over time is known as Variable. e.g., marks, age, height, sex,
temperature, sales, revenue, time etc.

Variable • The process of assigning numbers or labels to objects, persons, states


or, events in accordance with specific logically accepted rules for
Qualitative Quantitative representing quantities or qualities of attributes or characteristics.
• There are actually four levels of measurement: nominal, ordinal,
Characteristic which interval, and ratio [psychologist researcher named Stanley Stevens
varies in quality (not Discrete Continuous
1951].
numerically) e.g.,
Eye colour, Height
No. of students
Education level, Weight
No. of chairs
Behaviour, Marks
No. of deaths
Quality, Time
No. of births in a hospital
Design, Distance
No. of accidents
Performance Temperature

Nominal Ordinal
• With ordinal scales, it is the order of the values is what’s important
• Nominal scales are used for labeling variables, without any and significant, but the differences between each one is not really
quantitative value. known.
• “Nominal” scales could simply be called “labels.” Poor  Fair  Good  Very Good  Excellent
• Nominal scales are mutually exclusive (no overlap) categories where • Order is important because Very Good is better than Good and
order of the categories is not important. Excellent is better than Very Good etc.
• But, Is the difference between “Very Good” and “Excellent” the same
Example: Sex, Religion, Marital status, Political affiliation, Eye colour as the difference between “Good” and “Very Good?” We can’t say.
• Therefore, it is the logical ordering for example, cricket teams
standings in ICC ranking, students’ grades, etc.

2
2/23/2017

Interval Ratio

• Interval scales are numeric scales in which we know not only the • Ratio scales tell us about the order, they tell us the exact value
order, but also the exact differences between the values. between units, AND they also have a “true zero” point
• Constant interval size
• No “true zero” i.e., there is no such thing as no temperature Example: height and weight
• With interval data, we can add and subtract, but cannot multiply or
divide.

Example: Temperature, IQ scores, Shoe size

Qualitative data Solution


Example 1: Consider the data about Sex of 10 students Example 1 Sex f Relative % freq Example 2 Sex Sec A Sec B Total
freq
Male 7 0.7 70 Male 3 4 7
Sex M F M M F M F M M M
Female 3 0.3 30 Female 2 1 3

• Make a frequency distribution, relative frequency and % frequency of the Total 10 1.0 100 Total 5 5 10
above data and interpret your results? Make an appropriate graph?
Bar Chart Multiple Bar chart
Example 2: Suppose we have also collected data of Sections of these 10 8 7 5
students as 7
4

Frequency
Frequency

6
Sec A
Sex M F M M F M F M M M 5 3
4 3
A A A B B B A B A B Sec B
Section 3
2
2
• Construct the Cross tabulation of the above data and interpret your results?
1
1
0
Also make an appropriate graph? 0
Male Female Male Female
Sex Sex

Simple Bar Chart Multiple Bar Chart


• A bar chart is a type of chart which shows the values of different
categories of data as rectangular bars with different lengths. Population Multiple Bar Chart showing Population of
Cities (000) Male Female
Example: Draw a Simple Bar Chart to represent the Population of 5 Males and Females
Lahore 10,355 5385 4,970 6000
cities of the province Punjab. 5385
Bar diagram showing Population of 5 cities 4,970
Rawalpindi 4,765 2478 2,287 5000 Males Females
of Punjab
Cities Population (000)
12,000 Faisalabad 3,675 1911 1,764 4000
POPULATION

10,355
Lahore 10,355 10,000
Sargodha 1,550 806 744 3000
Population in ‘000’

2478
Rawalpindi 4,765 8,000 2,287
1911
1,764
2000
Faisalabad 3,675 6,000 4,765
3,675 806 744
4,000 3,100 1000
Sargodha 1,550 1,550
2,000
Multan 3,100 0
0
Lahore Rawalpindi Faisalabad Sargodha
Lahore Rawalpindi Faisalabad Sargodha Multan
Cities CITIES

3
2/23/2017

Component Bar Chart Discrete data – Frequency Distribution

Component Bar Chart showing population of Example:


both Males and Females and Total
Cities Pop (000) Male Female • Following data represents the number of infected plants from a
12000
Lahore 10,355 5385 4,970 sample of twenty experimental plots. Your task is to present it in
10000 Males tabular form.
Rawalpindi 4,765 2478 2,287
8000 Females
4,970
Population

Faisalabad 3,675 1911 1,764


6000
1 2 4 3 0 1 2 3 1 1 0
Sargodha 1,550 806 744 4000 2 1 0 2 3 0 0 1 3
2,287
5385 1,764
2000
2478 1911 744
0 806
Lahore Rawalpindi Faisalabad Sargodha
Cities

Discrete Frequency Distribution Graphical Representation of Discrete Data


No. of infected Tally Frequency Relative Bar Chart representing the infected items
items 7
f frequency
X 6
6
0 |||| 5 5/20 = 0.25 5
5
6 0.30
Frequency

1 |||| | 4
4 4
2 |||| 4 0.20 3

3 |||| 4 0.20 2

4 | 1 0.05 1
1
Total 20 1.00 0
0 1 2 3 4
No. of infected items

Pie Chart Pie Chart


• A pie chart is a type of graph in which a circle is divided into sectors Blood No. of Relative Percent Angle
that each represent a proportion of the whole. Groups Students frequency frequency rf x 360
Example: The blood group of 70 students were tested and the following (f)
results were obtained. A 8 8/70 = 0.11 0.11*100 = 11 39.6

Blood Groups of Students B 30 0.43 43 154.8


Blood No. of
Groups Students (f) Divide the total
O 20 0.29 29 104.4
11%
angle of the Circle
17%
A 8 0.17 17 61.2 360 into four
A AB 12
B 30 29% 43%
B segments as
O
Total 70 1.00 100 360 calculated
O 20 AB

AB 12

4
2/23/2017

Simple Bar Chart

• Consider the Same example of the blood group of 70 students

Blood Groups
Blood No. of 35
Groups Students (f) 30
30
A 8 25
20
B 30 20
15 12
O 20
10 8
AB 12
5
0
A B O AB

You might also like