Mathematics as a Tool: Data Management

Introduction

1.1 Statistics

The term statistics has several meaning. Sometimes it is used to refer to any recorded data such as the
number of enrollees, the common size of classes, the number of patients, and the average score of nurses from a
board examination. It is also used to denote some characteristics of a group or set of objects such as mean, median,
standard deviation and coefficient of correlation. Another meaning of statistics refers to the method or procedure of
analysis of data. And universally, it is being defined as:

Statistics – a science that deals with collection,

presentation, analysis, and interpretation of data.

Statistics is fundamentally concerned with the understanding of structures of data. Methods range from
simple to a more systematic procedures in describing and summarizing data. These methods enable us to develop
a way of thinking. This helps us:

 describe or characterized person, objects, situation and phenomena with some reliability,
 make statement and comparison in an objective manner
 make evidence-based decisions.

1.2 Steps in Statistical Investigation

1. Identification of the problem.

2. Collection of Data - refers to the different methods and techniques of gathering the data.
3. Presentation of Data - refers to the tabulation and organization of data in tables, graphs & chart
4. Analysis of Data - the process of deriving relevant information from the gathered data through the different
statistical tools.
5. Interpretation of Data - refers to the task of drawing conclusions or inferences from the analyzed data.

1.3 Population and Sample

In statistics, the terms population and sample are commonly used. These terms are at the very core of
statistics.

Universe – is the set of all entities under study.

Population – is the set of complete collection or totality of all possible values of the variables.
Examples:
1. Total number of enrollees from a certain university,
2. Collection of all books in the library,
3. The whole number of registered nurses.

Sample – a subset or sub collection of elements drawn from a population.

- Refers to the small portion or sub-group of a population.

Examples:
1. A television survey uses a sample of 1,500 newly graduates nurse,
2. A doctor conducts an interview to 10 dengue victims from a local barangay with 100 dengue cases,
3. To analyze the mortality rate of infants in the Philippines for five years, researchers considered the last two
years’ mortality rates

1
 Note:
Sometimes it is difficult to determine if a
given group or set of object is a population or a
sample, particularly if it does not contain any
numerical values. Hence, we have to analyze if
this group or set refers to a larger group or set, if
it is, then the said group or set is a sample
otherwise it is a population.

1.4 Divisions of Statistics

In analyzing set of data, it is important to determine whether this set of data refers to population or to a sample;
that determination will affect the methodology of analyzing the data and at the same time the conclusions that will
be drawn.

Descriptive Statistics
This division of statistics summarizes or
describes the important characteristics of a given
set of data.

Examples:
1. The average body temperature of 100 people is 36.78 0C.
2. The deviation of scores of all examinees from the recent board examination for nurses is 5.
3. The average monthly income of a nurse in the Phil. is P15,000.00.

Note:
Descriptive Statistics is being applied
once the set of data refers to a population or to a
sample.

Inferential Statistics
This division of statistics aims to give
information about the population by studying the
characteristics of the sample drawn from it.

Examples:
1. From the above example, treating those 100 people as a sample drawn from a larger population, we might
conclude that the average body temperature of all people is 36.78 0C.
2. To determine if 1000 units of cell phone is of good quality, the quality control department considered 100 units
of it. If this particular number of cell phones has good quality then the entire 1000 units are also of good
quality.

2
1.4 The Nature of Data

Data – refers to any information concerning to a population or sample.

Types of Data According to Source

1. Primary Data – refer to information which is gathered directly from the original source.

Example: Information that is gathered by an interviewer from an interviewee, data that is written by an
applicant to his bio data, and news that is reported by a field reporter.

2. Secondary Data – refer to information which is taken from a secondary source.

Example: Information or data that is taken from newspaper, published or unpublished book, thesis or
dissertation etc.

Types of Data According to

Functional Relationship

1. Independent Data- refer to any controlling data. Data which are not affected by any other data.

Example: Blood type, age, gender of 10 freshmen, and time.

2. Dependent Data- any data that is affected by the controlling data.

Example: Blood pressure, score in a test, monthly phone bills, and monthly income.

Variable
– refers to the different characteristics of the population or of the sample.
Variable also refers to those characteristics of the population or sample that continuously varies.

Example: age, scores in the test, daily incomes, kilowatt-hour used, and weight of 10 students.

Parameter
– refers to specific characteristic of the population subject of interest or subject of investigation that is
measurable.

Example: IQ, talents, vital statistics and weights of all the contestants in a beauty pageant.

Statistic
- refers to specific characteristic of the sample subject of interest or subject of investigation that is measurable.

Example: IQ, talents, vital statistics and weights of some contestants in a beauty pageant.

Categories of Data

1. Qualitative Data – uses categories or attributes that are distinguished by some non-
numeric characteristics.

Examples: Sex, religion, race, responses such as “Yes” or “No” and color of the skin.

3
 2. Quantitative Data- consist of numbers representing counts or measurements.

Examples: weights, heights, temperature, scores, number of enrollees, and length of the table.

Types of Quantitative Data

1. Discrete Data – quantitative data which can assume a finite or countable number of values. Cannot be
represented by fractions or decimal numbers but by any whole number only

Examples: scores, no. of enrollees, number of table, number of body temperatures recorded, and number of
schools.

2. Continuous Data- quantitative data which can assume infinity of many possible values corresponding to the
points on a line interval.

Examples: temperature, heights, weights, length of the tables, size of a classroom, and blood pressure.

Note:
Qualitative and quantitative data are commonly
represented by numerical values. But for
qualitative data, numerical values are being used
to represent the different categories, names, labels
etc.

DATA

Variable

According According to
to Source Function

Primary Secondary Independent Dependent

Qualitative Quantitative

Discrete Continuous

Figure 1. Classification of Data

4
1.1 Measurements of Data

There are four levels of measurements used in preparing data for analysis.

Nominal
– data that consists of names, labels, or categories only commonly used number to categorize data.

Examples:

1. Gender: M - Male F - Female

2. Religion: 0 – Catholic 1 – INC
2 – Islam 3 – Protestant
3. Responses: 0 – Yes 1 - No

Ordinal
– measurements which deal with order or rank, provides information about relative comparison but the
degrees of difference are not available.

Examples:
1. In a sample of 15 computers, 7 were rated as “good” 5 were rated as “ better” and 3 were rated as “best”.
2. From an IT company, three programmers were ranked as 2 nd, 3rd and 4th.
3. A grading system:
A-Excellent B-Very Good C-Good D-Fair E-Poor

Interval
– similar with ordinal but this level of measurement does not only show likeness or differences between data,
likewise it gives meaningful amounts of differences between data. It does not have a “true-zero” starting point, instead
it is arbitrarily assigned.

Examples:

1. Consider the following temperatures: 300 250 400 Here we can say that 300 > 250 or 250 < 400.
2. Age Bracket: 18 – 24 yrs old
3. Passing score in a test.

Ratio
– a modified interval level to include the starting point “zero”. The quality of ratio or proportion is meaningful.

Examples:
Time, rate of change in production, height, weight, volume, area, density, velocity etc.

5
 MATM 111 – Mathematics in the Modern World
Math as a Tool: Data Management

Describing Data
MEASURES OF CENTRAL TENDENCY

In descriptive measures, an average is considered the most representative value in data set. An average is the
general term for the measure of central tendency, since this lie centrally in an array of values. There are three
commonly used averages: the mean, median and mode.

1. MEAN x (sample mean)

µ (population mean)

The mean arithmetic mean or mean in the

distribution is the sum of the data value
divided by the number of data values.

The mean is the most widely used central measure of the distribution. It is also represents the “the center
of gravity”. That is, if the value in a list were to be placed on a dot scale, the mean acts as the balancing point where
smaller data will ‘balance” the larger data.

Characteristics of the Mean:

 The most reliable measure of central tendency
 may not be an actual observation in the data set
 can be applied in at least interval level
 every observation contributes to the value of the mean
 sub group mean can be combined to come up with a group mean
 easy to compute but easily affected by extreme values

Mean of Ungrouped Data:

Formula:

 xi
x = n

where : x = any empirical data

n = the number of the data set,

Example 1. A researcher wants to determine the average age of working students. A random sample of 10 students
working in one of the popular fast foods was asked about their ages. The following ages were gathered: 18,20, 21,
18, 20, 18, 22, 24, 27, 25.
Solution:

6
 x = ( 18 + 20 + 21 + 18 + 20 + 18 + 22 + 24 + 27 + 25 )
10

x = 213 / 10 = 21.3

Analysis: The average age of working students is 21.3 years old.

Example 2 : The following are the numbers of hours spent in a computer shop of 8 students in one week. What is
the average number of hours spent of the students in the computer shop?
Hrs: 20 , 13 , 10 , 8 , 7 , 5 , 5 , 9
Solution:

x=  xi =
20+13+10+8+7+5+5+9
=
77
= 9.625
n 8 8

Analysis: The average number of hours spent by the students in computer shop is approximately 10 hours..

Weighted Mean(WM)
The weighted mean of the set of data represented by x 1 , x2 ,x3 …xn can be expressed as the sum of the
data multiplied by their corresponding frequency or weight.
The formula is:
n n

WM=  wixi / w
i 1
or x =  fixi / f
i 1

where : wi or fi = the weight of frequency

xi = the given data
w or f = sum of weights or frequencies

Example 3: Find the weighted mean of three 25’s , five 30’s and two 40’s
Solution:
305
WM = 3( 25 ) + 5(30 ) +2 ( 40) = 10
= 30.5

3+5+2

7
Example 4: Determine the general weighted average grade (GWAG) of a student whose grades are:

Subject Units Grade Subject Units (w) Grade (x) wx

Fil 2a 3 1.25 Fil 2a 3 1.25 3(1.25) = 3.75

Soc 4 3 1.50 Soc 4 3 1.50 3(1.50) = 4.50

Eng 3 3 1.75 Eng 3 3 1.75 3(1.75) = 5.25

Phys 103 5 1.0 Phys 103 5 1.0 5(1.0) = 5

Ncm 101 7 1.0 Ncm 101 7 1.0 7(1) =7

Mat 3 3 3.0 Mat 3 3 3.0 3 (3) =9

Sum 24 Sum 24 34.50

Solution:

 wixi / w
34.50
WM = = = 1.44
24
i 1

Analysis: Therefore the GWAG of the student is 1.44.

2. MEDIAN ( Md )

The median is the middle value when the data / observations is arrange in an array
(increasing or decreasing order).

Characteristics of the median:

 the most stable measure among measures of central tendency
 the value that refers to the 50th percent of the distribution
 may not be an actual observation in the data set
 can be applied in at least ordinal level
 a positional measure; not affected by extreme values

8
Median of Ungrouped Data
Case 1: if the number of data (n) is odd number, the median is exactly the middle value.

Md  X ( n 1) / 2

Example 1: Data set A: 24, 20, 18, 21, 27, 24, 30, 19, 25
Solution: Arrange the data first in ascending order (increasing)
18, 19, 20, 21, 24, 24, 25, 27, 30 ; n = 9
Md = x (9+1)/ 2 = x 5 = 24

Case 2: if the number of data (n) is even number, the median is the average of the two middle most scores

X n / 2  X ( n / 2) 1
Md=
2

Example 2:
Data set B : 21 , 20 , 18 , 22 , 24, 21, 27 , 30 , 19 , 25

Solution: arrange the data in ascending order

18 , 19, 20 , 21 , 22 , 24 , 24 , 25 , 27 , 30 ;n= 10

X5  X6
Md = = (22 + 24) / 2 = 23
2
2. MODE ( Mo )

The value in the distribution that occurs most

frequently.

 It is sometimes referred to as nominal average. In a given distribution both for grouped or ungrouped data the
mode can easily be picked out by ocular inspection.
 Uni-modal if the distribution has only one mode.
 Bimodal if the distribution has two values for the mode.
 Trimodal if the distribution has three values for the mode
 Multimodal if there are more than two values for the mode
 It is possible for the data set to have no mode, no mode ( not zero ).

9
Mode for Ungrouped Data
Example 1.
Data set A : 400,450,430,415,438,426  has no mode
Data set B: 1, 2, 3, 5, 6, 6, 7, 8, 9,10  unimodal , mode is 6
Data set C: 25,20,18,21,15,20,21,30,19  bimodal ( 20 & 21)
Data set D: 26, 27, 25, 30,21, 22, 22,21,30  multimodal (21, 22 & 30 )

Comparison between the three measures of central tendency

The choice of a measure of central tendency is mainly based on the purpose for which the measure is being
used and scale of measurement. The mean is the best measure of central tendency if we want every value to
contribute to the average. In using sample as a basis for inferring something about the population, the sample mean
will be the most reliable estimate of the center. If the concerned is the effects of extreme value, the median will give
a more accurate average. However, if the objective is to get the most frequently occurring data in the distribution
mode is the measure to use.

How to Interpret
Example 1. To determine the performance of CAS 2Y2-1 in Mat 3-Statistics PE, a 75-item test was
administered to them and has the following results:

Scores:

17 39 45 53
24 40 47 53
25 41 47 55
30 42 47 55
32 43 49 57
34 43 49 57
37 43 52 58
37 44 53 62
38 44 53 63
38 45 53 63

10
Using the standard set below, perform the necessary interpretation of the above results.

Table 4.1. Range Interpretation for the Computed

Measure of Central Tendency.

Range Score Interpretation

65-75 Excellent
55-64 Very Satisfactory
45-54 Satisfactory
<45 Poor

Solution:
It is important to note that any standard or any form to be used to interpret data must be clearly stated first
before the computation of any appropriate statistical tool to be used in the study or research. The table above (Table
4.1), is only an example, the researcher may utilize or come up with his own standard or adopt any known standard
to interpret data.

Analysis Interpretations

1. The computed mean score of CAS 2Y2-1 in MAT3 Therefore, the average or mean performance of
P.E.is approximately 46 points. CAS 2Y2-1 IN MAT3 P.E is SATISFACTORY.

2. The median score of CAS 2Y2-1 in MAT3 P.E. is

Therefore, the performance of the upper half or
45 points, which means that the 1st 20 group of of the upper 20 students of CAS 2Y2-1 in MAT3-
students had scored BELOW 45 points while the PE is POOR while the 2nd 20 group of students is
other half had scored ABOVE 45 points. ABOVE POOR.

3. The modal score of 40 students in MAT3 P.E. is Therefore, most of the students of CAS 2Y2-1
53 , most of the students scored 53 points. had perform In SATISFACTORY level in MAT 3
P.E.

11
 Example 2. A survey was conducted to determine the perception of the students in the effectiveness
of having music while they are solving problems in Statistics. Using the scale below, 150 students were
asked.

Scale Interpretation
4 Highly Effective
3 Moderately Effective
2 Sometime Effective
1 Not Effective

Data: Responses
4 3 2 1
Students 35 53 43 19

Solution:
Using the weighted mean,
Wm = 4(35) + 3(53) + 2(43) + 1(19) = 2.693
150
Analysis:
The average or the mean response of the students is 2.693.

For the Interpretation, we have to establish the range interpretation of the computed weighted mean.

Table 4.2. Range Interpretation for the Computed Weighted Mean Response.

Scale Range Interpretation

4 3.25 – 4.00 Highly Effective
3 2.50 – 3.24 Moderately Effective
2 1.75 – 2.49 Sometime Effective
1 1.00 – 1.74 Not Effective

Interpretation:
The average or the weighted mean response of the students is 2.693 which mean that it is moderately
effective for them to have music while performing problem solving in Statistics.

12