What is Research?
Everywhere
knowledge is incomplete and problems are waiting to be solved. We address the
void in our knowledge and those unresolved problems by asking relevant
questions and seeking answer to them. The role of research is to provide a
method for obtaining those answers by inquiringly studying the evidence within
the parameters of the scientific method.
Research is the systematic investigation into
existing or new knowledge. It is used to establish or confirm facts,
reaffirm the results of previous work, solve new or existing problems, support theorems, or
develop new theories.
Research is not mere information gathering and not mere the transportation of
facts from one location to another location. It is not also the rummaging for
information and is not a catch word used to get attention.
Research is getting to know a subject by
reading up on it, reflecting, playing with the ideas, choosing the areas that
interest we and following up on them. Research is the way we educate ourselves.
Some definitions of research are;
1. Shuttleworth, M. (2008), "In the
broadest sense of the word, the definition of research includes any gathering
of data, information and facts for the advancement of knowledge."
2. Creswell, J. W. (2008), "Research is
a process of steps used to collect and analyze information to increase our
understanding of a topic or issue". It consists of three steps: Pose a
question, collect data to answer the question, and present an answer to the
question.
Additionally, research articulates the
genuine and research problem, adopts the scientific process and contributes the
body of research. There are several forms of research: scientific, humanities,
artistic, economic, social, business, etc
1. Scientific
research relies on the
application of the scientific method, a harnessing of curiosity.
This research provides scientific information and theories for the explanation of
the nature and
the properties of the world. Scientific research is a widely used criterion for
judging the standing of an academic institution, such as business schools, but
some argue that such is an inaccurate assessment of the institution.
2. Research in the
humanities involves different
methods such as for example hermeneutics and semiotics,
and a different, more relativist epistemology.
An example of research in the humanities is historical research, which is
embodied in historical method.
3.
Artistic research, also seen as 'practice-based research', can take
form when creative works are considered both the research and the object of
research itself.
Purpose of Research
Purpose of the
research can be discussed in five categories follows,
1. Basic Research: collection and analysis of data to develop or
enhance theory. Some examples of learning theories are; constructivism, mastery
learning etc.
2. Applied Research: Collection and analysis of data to examine the
usefulness of theory in solving the practical educational problems. For
example; examining the effectiveness of a computer based algebra program
developed around a mastery learning approach.
3. Evaluation Research: The collection and analysis of data to make
decisions related to the merit or worth of a specific program. A critical appraisal or assessment; a judgment of the
value, worth, character, or effectiveness of something; measurement of
progress. There are two types of evaluation research. a) Formative
evaluation is designed to inform and improve a program while it is being
developed or implemented. b) Summative evaluation, is designed to make
decisions regarding the overall quality of the program being evaluated
4. Research and Development: Research and development is often scientific or towards developing
particular technologies and is frequently carried out as corporate or
governmental activity.The development of effective
products for the use in schools. For example, the development of smart board to
enhance a teacher’s use of technology in the classroom.
5. Action Research: The collection and analysis of data to provide a
solution to the practical, valued program of educators within own school or
organization. For example, how can the disciplinary policies are enforced
consistently on our schools.
Major Steps of Conducting Research
Research is often conducted using the
hourglass model structure of research (Trochim, W.M.K, 2006). The major steps in conducting research are:
1.
Identification of research problem
2.
Literature review
3.
Specifying the purpose of research
4.
Determine specific research questions
or hypotheses
5.
Data collection
6.
Analyzing and interpreting the data
7.
Reporting and evaluating research
Generally, research is understood to follow a
certain structural process Though step order may vary depending on the subject
matter and researcher, the following steps are usually part of most formal
research, both basic and applied:
What is not Research?
Different ideas
regarding the understanding ‘what is not research’ can be elaborated as,
Research is not mere information gathering and not
mere the transportation of facts from one location to another location. It is
not also the rummaging for information and is not a catch word used to get
attention.
Elements of Research
1. Research originates with a question or problem like; why, what is
cause of that, what does it mean. For instant; what might be the cause of
securing lower marks in mathematics by girls of 10 class students?
2. Research requires a clear articulation of a goal like; what we
intended to do is a goal of the research. For example; to identify the
underlying causes of getting lower marks in math might be the goal of research.
3. Research follows the scientific procedure or plan like; the
logically designing and planning of the research is a must crucial effort of
any research. Like, as per our research problem, where are the data of marks in
math of girls we can get? Do these data address the research problem? How we
can access the data? What procedure we adopt to collect the data? etc.
4. Research always divides the principal problem in to more manageable
sub-problems. For example; what is the class room attendance percentage of
girls in math class? How many hours of everyday class is being conducted for
math subject in class 10?, these might be the some sub problems of the
research.
5. Research is guided by the scientific research problem, question or
hypothesis. For example; there is less scores in math by the girls of 10 class
students of a school as mentioned above. We begin to construct a series of
reasonable guesses (i.e. hypothesis) for the cause of the failure (getting
lower number in math) in mathematics. Like; are all girls attending the class regularly?
Is the mathematics teacher regular in teaching the students?
6. Research requires the collection and interpretation of data in
attempting to resolve the problem that initiated the research. Thus, research
is cyclical or, more exactly, helical.
Data, Information and Knowledge
The terms data, information
and knowledge
are frequently used for overlapping concepts. The main difference is in the
level of abstraction
being considered. Data is the lowest level of abstraction, information is the
next level, and finally, knowledge is the highest level among all three (Mitra, A., 2011). Data on its own carries no meaning. For
data to become information, it must be interpreted and take on a meaning. For
example, the height of Mt. Everest is generally considered as "data",
a book on Mt. Everest geological characteristics may be considered as
"information", and a report containing practical information on the
best way to reach Mt. Everest's peak may be considered as "knowledge".
Data is raw. It simply exists and has no
significance beyond its existence (in and of itself). It can exist in any form,
usable or not. It does not have meaning of itself. In computer parlance, a
spreadsheet generally starts out by holding data.
Information is data that has been given
meaning by way of relational connection. This "meaning" can be
useful, but does not have to be. In computer parlance, a relational database
makes information from the data stored within it.
Knowledge is the appropriate collection
of information, such that its intent is to be useful. Knowledge is a
deterministic process. In computer parlance, most of the applications we use
(modeling, simulation, etc.) exercise some type of stored knowledge.
Understanding is an interpolative and
probabilistic process. It is cognitive and analytical. It is the process by
which we can take knowledge and synthesize new knowledge from the previously
held knowledge.
Wisdom is an extrapolative and
non-deterministic, non-probabilistic process. It calls upon all the previous
levels of consciousness, and specifically upon special types of human
programming (moral, ethical codes, etc.). Wisdom is, the process by which we
also discern, or judge, between right and wrong, good and bad.
Knowledge is dichotomous:
It always brings the contrast meaning like; yes or no, right or wrong, good or
bad.
The Ways of Knowing
In this context, arguments about “ways of knowing” are really arguments
about “ways of defending knowledge claims.” If the best findings of science
suggest the Earth is over four billion years old, while the Bible strongly
implies that it is less than ten thousand years, then among educated people it
is the Bible that must yield. When dealing with empirical claims about nature,
science is a far more reliable way of knowing than is reading the Bible.
We will be
discussing about the different ways of knowing something as follows,
- Personal experience: It means relying on one’s knowledge of prior experience
- Tradition: It means the way of doing things they have always been done
- Expert or Authorities: It means relying on the expertise or authority of others
- Deductive reasoning: It means reasoning based on the rules or laws
- Inductive reasoning: It means reasoning based on the observation or experience
Deductive and Inductive Reasoning
Inductive and
deductive reasoning are two methods of logic use to arrive at a conclusion
based on the information assumed to be true. Both are used in research to
establish hypothesis. Arguments based on experience or observation is best
expressed inductively, while arguments based on laws or rules are best
expressed deductively.
Deductive approach
begins with a general idea such as theory, laws and principles. An inductive
approach begins with specific things, observation of individual cases. A
deductive argument is an argument whose premises make its conclusion certain. Inductive
argument is an argument whose premises make its conclusion likely.
Research
Paradigms
There are two major research designs: qualitative
research and quantitative research. Researchers choose one of these two tracks
according to the nature of the research problem they want to observe and the
research questions they aim to answer:
1.
Qualitative
research: Understanding of human behavior and the reasons that govern such
behavior. Asking a broad question and collecting word-type data that is
analyzed searching for themes. This type of research looks to describe a
population without attempting to quantifiably measure variables or look to
potential relationships between variables. It is viewed as more restrictive in
testing hypotheses because it can be expensive and time consuming, and
typically limited to a single set of research subjects. Qualitative research is
often used as a method of exploratory research as a basis for later quantitative
research hypotheses.
2.
Quantitative
research: Systematic empirical investigation of quantitative properties and
phenomena and their relationships. Asking a narrow question and collecting
numerical data to analyze utilizing statistical methods. The
quantitative research designs are experimental, correlational, and survey or
descriptive (Creswell, J. W., 2008).
Statistics derived from quantitative research can be used to establish the
existence of associative or causal relationships between variables.
3.
Mix
Method: It uses both the qualitative and quantitative methods. Pragmatism worldwide philosophy followed this paradigm. Researcher
need to establish a purpose for their mixing; rationalize for the reason why
both qualitative and quantitative data need to be mixed in the first place.
Mixed method study can apply elsewhere like; socio-cultural, historical,
economic, political thus it is theoretical lens that reflective of social
justice and political aim.
THE BASIC TERMINOLOGIES
Data: The terms data, information and knowledge are
frequently used for overlapping concepts. The main difference is in the level
of abstraction
being considered. Data is the lowest level of abstraction, information is the
next level, and finally, knowledge is the highest level among all three (Mitra, A., 2011). Discrete data are set in
nominal, ordinal scale for example age of students is16, 17, 19, 20, 21, 22
years. Continuous data are set in
certain categories like interval scale e.g. age from 10-19, 20-29, 30-39 etc.
Measurement
Scale
A scale is a tool which is used to distinguish the individual on the
basis of variables interest in our study. Therefore, we use different scales to
measure different variables on the basis of their degree of precision. They are
explained as
1)
Nominal scale
A nominal scale classifies objects into different categories based
on some defined characteristics and then the number of objects in each category
is counted. In other words, it is a
classification system that places people, object, or other entities into
different categories and counting their frequency of occurrence. Thus, the categories must be non-over lapping
or mutually exclusive. For instance, a respondent’s race classified as black
cannot be classified as white.
Therefore, nominal data are not graded, ranked or scaled for qualities
such as worse or better, more or less,
more or less and high or low but they are always grouped into separate
categories to indicate the sameness or
difference with respect to the given quality or characteristics. It only tells
us to which group a subject belongs, but they do not provide any quantitative
information about the subject. For instance, the gender variable may tell us that subjects are males while others
are females. But it doesn’t tell us that some subjects posses more of a
specific characteristic relative to others.
.Gender, ethnicity, hair color are some of the example of variables
measured on a nominal scale. The important point is that there is no logical
ordering of the categories in a nominal measurement but shows only the
difference.
Properties:
·
Data categories are mutually
exclusive: that is, an object can belong to only one category.
·
Data categories have no logical
ordering
2)
Ordinal scale
An ordinal scale not only shows classification of objects or
characteristics but also shows logical order of categorised objects. In other
word, ordinal measurement provides information about the ordering of
categories, but doesn’t indicate the magnitude difference between numbers. The
objects can be out into order on the basis of some characteristics but they
cannot be given values that represent the degree of differences on that
attribute. Thus, the values of ordinal
scale represent a hierarchy or order of levels with respect to the construct of
effectiveness i.e. the agent ranked “1” is perceived as being more effective
that the agent ranked “2”, and agent ranked “2” is more effective that one
ranked “3” and so forth.
For example, in a letter grading system (as
A, B, C, D and F) A has higher level of achievement than B. But still, we
cannot infer that the difference between an A and a B is the same as between a
B and a C. The properties
of ordinal data are:
·
Data categories are mutually
exclusive
·
Data categories have some
logical order
·
Data categories are selected
according to the particular characteristics they possess.
3) Interval Scale
Interval scale not only tells us about the ordering of categories,
but also shows the exact distance between them i.e. position and distance.
Therefore, it reflects equal differences in the characteristics measured, that
is equal unit is established in the scale. Hence, it not only groups
individuals according to certain categories but it also measure the magnitude
differences n the performances among the individuals. The important point is that in all interval scale 0 is just another point
on the scale, that is, 0 is not necessarily the starting point of the
scale, e.g., temperature. The properties of the interval data are:
§ Data categories are mutually exclusive
§ Data categories have some logical order
§ Data categories are selected according to the particular
characteristics they possess
§ Equal differences in the characteristic are represented by equal
differences in the numbers assigned to the categories
§ The point 0 is just another point on the scale
4. Ratio Scale:
It represents an absolute true zero point that
reflects an absence of the characteristics. It not only measures the equality
of the differences between any two points or variables on the scale but also
measures the proportional amounts of the attributes which the two objects
possess. The properties of ratio data are:
§ Data categories are mutually exclusive
§ Data categories have some logical order
§ Data categories are selected according to the particular
characteristics they possess
§ Equal differences in the characteristic are represented by equal
differences in the numbers assigned to the categories
§ The point 0 reflects an absence of the characteristics.
In nutshell, Nominal scale only
classifies the variables without ordering them whereas ordinal scale not only
shows the classification but also the orders of the objects. In the same way,
interval scale categorizes, orders and established an equal unit in the scale
but on the other hand ratio scale also categorizes,
orders, establishes an equal but contains a true zero point. Therefore we have
to be clear of how variables are measured in the study.
Types of data
There are
different types of variables as Discrete, Continuous and Binomial. Discrete
variables generally take integer value. That is to say it takes only certain
values of objects as whole numbers, for example, 1, 2, 3, 4, 5 or the number of
children, or family size. That is why discrete variables are always measured
across a set of fixed values, such as age in years. On the other hand,
Continuous data can take any value. It means a variable that is not restricted
to particular values, for instance, height or weight, 60-61, 60.1, 60.2, and 60.3. That is why continues variables are measured
along a continuous scale which can be expressed or divided into fractions or in
decimals. While Binomial can take only two value, for example 1 or 0, yes/no
Parametric and Non-parametric Statistics
Parametric statistics are more powerful and more flexible than
nonparametric used with interval and ratio variables and normality of
population. We can use to describe the data with some commonly used parameters,
particularly the mean and standard deviation.
Non-parametric statics
are not based on the estimation of population parameters. It means it often
uses ordinal or nominal variables meaning is it doesn’t depend upon numerical
but it depends on a ranking or order of things, for instance, consumers
demanding ranges from like to dislike i.e. ordinal data.
Variable
A variable refers to some specific
characteristic of a subject that assumes one or more different values. It is
characteristic of person, thing, groups or objects. Thus variable is a symbol
to which numerals or values are assigned. In other words, a variable is any
entity that can take on different values. Therefore, an attributes is a
specific value on a variable. For example, the variable sex or gender has two
attributes or values as male and female, productivity and job satisfaction both
are variables which have different values. A variable thus is defined as
anything that can take on differing or varying values.
There are different types of
variables as
a.
Dependent variable:
A variable is called dependent
variable if its values depend upon the other variables. It means the value of
the dependent variable always depends upon another variable i.e. on the
independent variable. Therefore, the dependent variables are affected by the
independent variables.
For instance,
education (training) income
(productivity)
Independent variable Dependent
variable
Thus, dependent variable is used to
describe or measure the problem under study. It is always explained.
b.
Independent variable:
A variable is called independent
variable if it is not influenced by another variable under study. But it
influences the dependent variable. So, the independent variable is what you or
nature manipulates. Any changes in the
dependent either positive or negative are due to change in the independent
variable. So, the independent variables
are used to as the basis of predication whereas the dependent variable is being
predicted. Independent variables are used to describe or measure the factors
which are thought to cause or at least to influence the problem. It is always explanatory.
- Intervening variable
It is third construct
variable that influences the nature and degree of relationship between
independent and dependent variables i.e. if agriculture output is increased by
irrigation facility then fertilizer, improved seed, can be other intervening
variables to help increase thee agriculture output.
Descriptive Statistics
Statistics
consists with collecting and describing a set of data to yield meaningful
information. Some of the descriptive statistics are bar diagram, pie chart and
graph or curve. Each of them are discussed below
- Bar diagrams: They represent the data by means of bars of rectangles of equal width. The length of the bars represents the given figures and the width may be of any size. So they are also called one dimensional diagram. We will consider four types of bar diagrams.
(i)
Simple bar diagrams.
(ii)
Multiple bar diagrams.
(iii)
Sub-divided bar diagrams.
(iv)
Percentage bar diagrams.
They represent the data by means of bars of rectangles of equal
width.
The length of the bars represents the given figures and the width may
be of any size. So
they are also called one dimensional diagram.
We will consider four types of bar diagrams.
(i)
Simple bar diagrams
(ii)
Multiple bar diagrams
(iii)
Sub-divided bar diagrams
(iv)
Percentage bar diagrams
|
- Pie chart: Take a circle and divide it into several parts or
sectors to represent the total magnitude and the various parts into which
it is broken up. Draw a circle to represent the whole and divide it into
sectors to represent each of its components. Such a diagram is called a
pie diagram.
Sex ratio of the respondents.
- Graphs: Graphs are pictorial forms to represent the collection of data. They can be categorized into different types on the basis of different criteria. In the graphs one variable is presented on the X-axis and another variable on the Y-axis.
1.
Measures of Central Tendency:
Any measure
indicating the centre of a set of data, arranged in increasing or decreasing
order of magnitude is called a measure of central tendency. It is also called
measure of central location. Mean median and mode are measures of central
tendency. Their main purpose is to get the single value that describes the
characteristics of entire group and to facilitate comparison.
Different Measurements of Central tendencies
N
|
Range
|
Minimum
|
Maximum
|
Mean
|
Std. Deviation
|
Variance
|
||
Statistic
|
Statistic
|
Statistic
|
Statistic
|
Statistic
|
Std. Error
|
Statistic
|
Statistic
|
|
Reading Score
|
200
|
48.00
|
28.00
|
76.00
|
52.2300
|
.72499
|
10.25294
|
105.123
|
Writing Score
|
200
|
36.00
|
31.00
|
67.00
|
52.7750
|
.67024
|
9.47859
|
89.844
|
Valid N
|
200
|
|||||||
- Mean:
Arithmetic mean is
very powerful measures of central tendency. It is defined as the sum of all
items divided by the number of items.
The common formula
of arithmetic mean:
x¯ is symbol of
mean.
X is
number(value).
N isnumber(total).
∑ is summation of numbers.
X=x1+ X2..............Xn/n
Descriptive
Statistics
|
||||
N
|
Mean
|
Std. Deviation
|
Variance
|
|
Reading Score
|
200
|
52.2300
|
10.25294
|
105.123
|
Valid N
|
200
|
|||
- Median:
The middle item is
known as the median. Median is the value which divides the distribution into
two equal parts when the data are arranged in increasing or decreasing order.
For example, in the series 10, 15, 20, 25, 30 the value arranged in ascending
order and 20 is the middle most item. So 20 is the median. For calculation of
median in individual series,
Median = N+1/2
Where N is the
number of item
- Mode:
Mode of a set of
observations is that value which occurs with a greatest frequency. The mode may
not exist, and even if it does exist, it may not be unique. When observation
occurs with the same frequency, mode does not exist.
- Range:
It is defined as
the difference between the largest (maximum) and the smallest (minimum) items
in the distribution. Thus, it is defined by following formula.
Range = L-S,
Where, L= Largest
item
S = Smallest item
Range
N
|
Range
|
Minimum
|
Maximum
|
|
Reading Score
|
200
|
48.00
|
28.00
|
76.00
|
Valid N
|
200
|
- Coefficient of
Variation:
The relative
measure of dispersion based on standard deviation is called coefficient of
standard deviation. Thus,
Coefficient of standard deviation
= σ / Х
100 times coefficient of standard deviation is
called coefficient of variation. It is denoted by C.V. Thus, C.V. = σ / Х x100 %
- Standard Deviation:
It is the positive
square root of the arithmetic mean of the squares of the deviations of the
given values from their arithmetic mean. It gives greater weight to extremes
values. Therefore, it is regarded as the best and the most powerful measure of
dispersion.
- Measures of
Dispersion:
The degree to
which numerical data tend to spread about an average value is called measures
of dispersion. They are called measures of variation. Range, variance and
standard deviation are measures of dispersion.
Statistics: It is a science of collecting, summarizing, presenting, and interpreting
data and of using them to test hypothesis. Statistics
can roughly subdivide into two areas, which are given below.
Descriptive statistics
includes the collection, presentation and description of numerical data. Inferential statistics means technique
of interpreting the values resulting from descriptive techniques and then using
them to make decision and in order to generalize them. It describes the nature
of data according to sample population. Normal curve is the foundation base of inferential
statistics.
Distribution
Distribution of
data is always observed in data analysis process. It is used to analysis in
inferential statistics. Normal distribution (symmetrical distribution) and
skeweness (left skewed distribution) and right skewed distribution pattern
always happen in distribution.
Normal distribution
Normal
distribution of data can study under bell shape, Norma curve. In this curve,
fifty percent of the score fall above the mean and fifty percent fall below the
mean, mean/
median/mode are the same value, so most participant scores falls
nearer the mean. Basic parameter of normal curve are ± 1sd = 68%, ±2sd = 95.5%,
± 3sd =99.7%. Every numeric variable has approximately normally distributed.
Main importance of normal distribution is checking the normality of data
whether they are normally distributed or not. In inferential statistics, it can
help to interpretation of data according to given parameters.
median/mode are the same value, so most participant scores falls
nearer the mean. Basic parameter of normal curve are ± 1sd = 68%, ±2sd = 95.5%,
± 3sd =99.7%. Every numeric variable has approximately normally distributed.
Main importance of normal distribution is checking the normality of data
whether they are normally distributed or not. In inferential statistics, it can
help to interpretation of data according to given parameters.
Skewness distribution
means lack of symmetry or unsymmetrical distribution of data’s. Skewness is
present if the value of mean, median and mode do not coincide, i.e. mean ≠
median ≠ mode, frequencies are not equally distributed at points of equal
deviation from the mode etc. Data is not always distributed in normal curve
symmetrically thus skeweness refer to distributing data not symmetrically or
either distributed in positive skewedness (Mo> Md > M) or in negative
skewedness (M> Md>Mo).
Kurtosis distribution
observes height, pickness and flatness of the distribution. There are always
three types of pickness. Pickness with normal curve (mesokurtic), High peakness
(Lapto kurtic) and low peak (platykurtic). Skeweness and kurtosis are both for
measurement for shape under inferential statistics because they can help to
analysis data under given parameters and shapes.
Population and sample: Sampling is the
process of selecting units (e.g., people, organizations) from a population of
interest so that by studying the sample we may fairly generalize our results back
to the population from which they were chosen. The group you wish to generalize
to is often called the population in your study. This is the
group you would like to sample from because this is the group you are
interested in generalizing to. The listing of the accessible population from
which you'll draw your sample is called the sampling frame.
The sample is the group of people who you select to be in your
study. The distribution of an infinite number of samples of the same size as
the sample in your study is known as the sampling distribution.
