Basic Statistical Steps

Basic Statistical Steps

In statistics we are interested in four steps:
•Collecting data or information.
•Organizing data or information.
•Analyzing data or information.
•Drawing conclusions from data or information
1.1 Introduction
Statistics is concerned with the scienti c method by
which information is collected, organized , analyzed
and interpreted for the purpose of description and
decision making.
Examples using statistics are: Hang Seng Index, Life
or car insurance rate, Unemployment rate, Consumer
Price Index, etc.
 What is Statistics?
Statistics: Statistics is the science of
collecting, organizing, analyzing,
drawing conclusions from data. and
ere are
statistical two
[Link]
(a) of
Descriptive
Statistics
presentation- It deals
of with the
numerical facts, or
data,
form, in either
and with tables
the or graphs
methodology of
analyzing the data.
(b) Inferential Statistics - It
involves techniques for
making inferences about
the whole population on
the basis of obse ations
obtained from samples.
 ORGANIZATION AND DESCRIPTION OF
DATA
Introduction to Basic Terms
Population: a population is a set of similar items or
events which is of interest for some question or
experiment.
Two kinds of populations: nite or in nite.
Sample: A subset of the population is chosen to
represent the population in a statistical analysis.
Variable: A characteristic about each individual element of
a population or sample. Variables can fu her be classi ed
into two types: qualitative and quantitative .
Data : e value of the variable associated with one
element of a population or sample. is value may be a
number, a word, or a symbol..
Experiment: An experiment is a procedure carried out to
suppo , refute, or validate hypothesis
Parameter: A descriptive measure of a population.
Statistic: A descriptive measure of a sample.
.
A variable differing in quality is called a qualitative variable .For
example gender (male – female), hair color (black, golden,
red), eyes color (black, brown, blue, green) are qualitative
variables. Qualitative variables
Note: Arithmetic operations, such as addition and averaging,
are not meaningful for data resulting from a qualitative
variable.
Quantitative variables are numerical and can be ordered or
ranked. For example, age, heights, weights and temperature
are quantitative variables. Quantitative variables can fur ther
be classif ied into discrete (which can assume values that are
countable) or continuous (which can assume all values in a
real inter val). Number of children in a family, number of
students in a class and number of missed calls received by a
mobile phone are examples of discrete variables, whereas
Qualitative and quantitative variables may be fu her
subdivided:
Nominal
Qualitative
Ordinal
Variable
Discrete
Quantitative
Continuous
Types of Data
We can classify data into two main types:
Quantitative Data
In this type of data, we represent each ent
of the data by a number; for example the
payrolls of employees in a company, the
heights of students in a ce ain class in
centimeters
Qualitative Data
and their weights in kilograms .

In this type of data, we represent some proper ties of

the sample under consideration; for example the sex
(male, female), hair colour (black, red, brown, …), eye
color (black, brown, blue, …)
HOW TO MAKE A DECISION
WITH STATISTICS
e scienti c method is
composed of thefollowing steps:
Step 1 Formulate a theo .
Step 2 Collect data to test the
theo .
Step 3 Summarize the results.
Step 4 Interpret the results and
make a decision.
Data

Collection
First problem a statistician faces: how to obtain the
data.
 It is impo ant to obtain good, or representative,
data.
 Inferences are made based on statistics obtained
from the data.
 Inferences can only be as good as the data.
Organization of Data
T he organization of data involves the presentation of the
collected measurements or Obser vation in a form suitable
for determining logical conclusions. Usually, tables or
graphs are used to represent the collected data.
Analysis of Data
T he analysis of data is the process of extracting, from
given measurements or Obser vation, related and relevant
information from which a brief numerical description can
be formulated. In this process we use concepts known as
the mean, median, range, variance, and standard deviation.
Interpretation of Data
By interpretation of data we mean the art of
drawing conclusions from the analysis of the
data. This involves the formulation of
predictions concerning populations based on
the information available from samples of
that population.
‫ﻣﻦ ﺧﻼﻝ ﺗﻔﺴﻴﺮ ﺍﻟﺒﻴﺎﻧﺎﺕ ﻧﻌﻨﻲ ﻓﻦ ﺍﺳﺘﺨﻼﺹ ﺍﻟﻨﺘﺎﺋﺞ ﻣﻦ‬
.
‫ﺗﺤﻠﻴﻞ ﺍﻟﺒﻴﺎﻧﺎﺕ ﻭﻫﺬﺍ ﻳﻨﻄﻮﻱ ﻋﻠﻰ ﺻﻴﺎﻏﺔ ﺗﻨﺒﺆﺍﺕ ﺗﺘﻌﻠﻖ‬
‫ﺍﻟﻤﺠﺘﻤﻊ ﺍﺳﺘﻨﺎﺩﺍ ﺇﻟﻰ ﺍﻟﻤﻌﻠﻮﻣﺎﺕ ﺍﻟﻤﺘﺎﺣﺔ ﻣﻦ ﻋﻴﻨﺎﺕ ﻣﻦ‬
.‫ﺫﻟﻚ ﺍﻟﻤﺠﺘﻤﻊ‬
Methods of Presentation of Data

 After collecting the data by dif ferent methods, we
need to organize it so that it can be easily read and
making use of it. T his step is essential especially if
the data is enormous. T he most two common
methods of data presentation are:
o Tabulation
o Graphical Presentation
 Organize Qualitative Data in Tables

© 2010 Pearson Prentice Hall. All rights rese ed 2-15

A frequency distribution lists each
catego of data and the number of
occurrences for each catego of data.

© 2010 Pearson Prentice Hall. All rights rese ed 2-16

EXAMPLE Frequency Distribution
Organizing Qualitative Data into a
Construct a frequency table for the
sample estimates of fo y students was
given as follows:
D B E C D B D C E A
B E C D B D D A E C
C D A C E D C C D B
D E D D A D D C D C
 e relative frequency is the propo ion (or
percent) of obse ations within a catego and is
found using the formula:
relative frequency  frequency
sum of all frequencies
A relative frequency distribution lists the relative
frequency of each catego of data.

© 2010 Pearson Prentice Hall. All rights rese ed 2-18

EXAMPLE Relative Frequency Distribution
Organizing Qualitative Data into a
following frequency distribution to
construct a relative frequency distribution
Use the

© 2010 Pearson Prentice Hall. All rights rese ed 2-19

 Frequency table

© 2010 Pearson Prentice Hall. All rights rese ed 2-20

 Relative Frequency
12  0.2667
45
0.2222
0.2
0.1333
0.0667
0.1111

© 2010 Pearson Prentice Hall. All rights rese ed 2-21

 e following data represent the size of twenty
families according to the number of their
members
5 5 4 3 4 5 6 3 4 6
7 2 8 6 2 5 4 4 5
7
Construct a frequency table and relative
frequency distribution
Organization of Data
Often studies result in data represented by a large collection of numbers. If
the data are to be interpreted, they must be organized. One way to organize
data is by using a frequency table.
Example 1
e following table lists the weights of a random sample of 71 children
selected from a group of 10,000. List a frequency table if the length of
inte al equal 10 .
69 71 71 55 50 55 58 58 58 62 67 94
82 94 95 89 89 104 93 93 58 62 67 62
94 85 92 75 75 79 75 82 94 105 115 104
10 109 94 92 89 85 85 89 95 92 105 71
5
72 72 79 79 85 72 79 119 89 72 72 69
79 79 69 93 85 93 79 85 85 69 79
In this table (50 –59) indicates the inte50 al x  60
A lower class limit 50 and an upper class limit of 59;
A lower class bounda 50-0.5=49.5 and an upper
class bounda 59+0.5=59.5.
.
e midpoint of a class inte al is de ned as:
Midpoint = ½ (Upper class bounda + Lower class
bounda )
e class width is the di erence between
consecutive lower class boundaries.
Notice that once raw data are conve ed lo grouped
data. it is impossible to retrieve or recover the original
data.
e best we can do is to choose the midpoint of
each class inte al as a representative for each class.
Class Inte al f
50 -59 7
60 -69 9
70 -79 19
80 -89 14
90 -99 14
100 -109 6
110 -119 2
 Cumulative Frequency Table
Sometimes it is useful to learn how many cases fall
below (or above) a ce ain value. For the data of the
above table, we do this as follows:
Start at the lowest class interval (50 -59) and note
how many scores are in this interval. The number is 7.
So we write 7 in the column labeled cf (cumulative
frequency) in the row for (50 -59).
Next we list how many scores fall in the next class
interval (60 -69), 9, and place the cumulative total 7 +
9 = 16 in the cf column. The process is continued.
The bottom entry of the last column should equal the
total number of scores in the sample. The numbers in
the column cf are called the cumulative (less than)
frequencies.
Class Inte al f Cumulative cf
Inte al
50 -59 7 Less than 60 7
60 -69 9 Less than 70 16
70 -79 19 Less than 80 35
80 -89 14 Less than 90 49
90 -99 14 Less than 100 63
100 -109 6 Less than 110 69
110 -119 2 Less than 120 71
 We can also form a cumulative (greater than or equal to)
frequency table as follows:
Class Inte al F Cumulative Inte al cf
  7 Greater than or equal to 50 71
  9 Greater than or equal to 60 64
  19 Greater than or equal to 70 55
  14 Greater than or equal to 80 36
  14 Greater than or equal to 90 22
6 Greater than or equal to 8
 
100
  2 Greater than or equal to 2
Example 1
A tra c inspector has counted the number of automobiles
passing a ce ain point in 100 successive 20-minute time
periods. e obse ations are listed below.
23 20 16 18 30 22 26 15 5 18 14 17 11 37 21 6 10 20 22 25
19 19 19 20 12 23 24 17 18 16 27 16 28 26 15 29 19 35 20 17
12 30 21 22 20 15 18 16 23 24 15 24 28 19 24 22 17 19 8 18
17 18 23 21 25 19 20 22 21 21 16 20 19 11 23 17 23 13 17 26
26 14 15 16 27 18 21 24 33 20 21 27 18 22 17 20 14 21 22 19
. List a frequency table with class width of 5 for each class.

Graphical
package
2-Histograms

We can build a histogram of the data grouped as follows:

Construct a set of adjoining rectangles having as base the size of the class inte al
and as height the frequency of occurrence of data in that pa icular inte al. e
center of the base is the midpoint of each class inte al.
 Frequency Curve-3–
Frequency Polygon
If we connect all the midpoints of the tops of the rectangles in Histograms
we obtain a line graph called a frequency polygon.
Draw a cumulative frequency Cu e