Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Tenacity
In this method the logic of no change is followed. The users of the method of
tenacity are holding their point of view persistently without accepting any change in
it. The basic idea is that nothing changes; what was good, bad or successful before
will continue to be so in the future. An example is the store owner who says, I do
not advertise because my parents did not believe in advertising.
Authority
The method of authority seeks to promote a belief in something because a trusted
source such as doctor, teacher ,religious scholar ,etc say it is true. Here the
emphasis is on the source.
Definition
Research is the processes of looking for a specific answer to a specific question in
an organized, objective, reliable way (payton, 1979)
Scientific research is a systematic, controlled, empirical and critical investigation of
hypothetical propositions about the presumed relations among natural phenomena
(kerlinger, 1986).
Purpose of research
As a method of knowledge research in whatever field of inquiry has at least three
major purposes:
1. Describing phenomena,
2. Explaining phenomena,
3. Predicting phenomena,
Science is objective
Science tries to rule out personal like and dislike. In research there is no room for
subjectivity. When a study is under taken explicit rules and procedures are
constructed and the researcher is bound to follow them. Reliability of the
measurement tool.
Science is Empirical
Researchers deal with a world that is knowable and potentially measurable.
Empiricism derives from a Greek word for experience. Researcher must be able to
classify what they study and to reject metaphysical and irrational explanations of
events. For example, a newspaper publisher claims that declining subscriptions
rates are Gods will would be rejected by scientists. Such statements cannot be
measured and classified. scientists give operational definition to abstract ideas
/notion (concepts).
Science is predictive
Science is concerned with relating to the present to the future. (Hypothesis, theory)
Research Process
problem,
Hypothesis(es)
Research design
Measurement
Data collection,
data analysis
Empirical generalization
Operationalization
Operationalization is the process of observing and measuring the research problem.
Research journals
Everyday situations: Every day we are exposed to various types of
communication via radio, TV, newspapers, etc. These exposures can be an
excellent source of research topics for researchers who want to analyze these
situations.
Research summaries (Meta research): examples are, The Communication
Yearbook, A Research Bibliography, etc.
Archive data: Gallup Pakistan, Federal Bureau of Statistics, Libraries, etc.
feasibility. Research studies must be designed in such a way that they can be
completed in the amount of time.
Researchers must carefully analyze whether the project may cause physical
or psychological harm to the subjects under evaluation? For example, will
respondent be frightened in any way? Will they require answering
embarrassing questions?
Literature Review
Researchers who conduct studies under the guideline of scientific research never
begin a research project without first consulting available literature. The
review provides information about what was done, how it was done, and what result
was generated. Experienced researchers consider the literature review as one of the
important step in the research process. It not only allows them to learn from
previous research but also saves time, effort and money. A literature review
discusses published as well as unpublished information in a particular subject area.
The review of literature involves the systematic identification, location, and analysis
of documents containing information related to the research problem. These
documents may include research journals, books, and other research reports.
Variable
Measurement
S.S. Steven defines measurement as the assignment of numerals to objects or
events according to some rules.
Key terms:
Objects/events
Numerals
Assignment
rules
Objects/events are the variables. Numerals are symbols such as 1,2,3,or i, ii,iii or a,
b, c, etc. numerals have no quantitative meaning but may be used simply as
qualitative labeling devices. Numerals that are given quantitative meaning
represent numbers, which can be added, subtracted, divided or multiplied.
Assignment is the designation of numerals or numbers to certain objects/ events.
The rules are guidelines. They specify the way that numerals or numbers are to be
assigned.
Reality Isomorphism
Isomorphism means similarity or identity of form or structure. Reality isomorphism
implies that ones measurement schemes should be similar in structure to the
structure of reality.
Levels of measurement
Scientists have distinguished four different ways to measure things. They are called
levels of measurement which are as under
1) nominal,
2) ordinal,
3) Interval,
4) Ratio,
Researchers are supposed to choose measurement levels on the basis of their
isomorphism (structural similarity) with the variables being measured. Because
statistical operations (data analysis) depend on the level of measurement
10
Nominal
Nominal level is the weakest measurement level. In nominal measurement numerals
are used to classify persons, objects, etc. Example, classification of media users on
the basis of the medium (radio, TV, newspaper) they use for news. 1. Radio, (2) TV,
(3) newspaper
Note that the numerals are simply labels that stand for the respective categories
they have no mathematical significance.
Ordinal Level
Objects measured on ordinal level are ranked in a meaningful way, from smaller to
greater. Example, categories of socio-economic status may be like (1) lower, (2)
lower middle (3) middle, (4) upper middle, (5) upper. Here in the example a rank of
1 is assigned to lower, 2 to lower middle, 3 to middle, 4 to upper middle, and 5 to
upper. Here the assignment of numerals has some mathematical meaning. 1 is
lower than 2, 3, 4 and 5. Similarly 2 is greater than 1 but smaller than 3, 4 and 5.
However, ordinal level does not show the distance between two categories.
It is therefore, compared with a horse race without a stopwatch.
Interval level
When a scale has all the properties of an ordinal scale and the intervals between
adjacent points on the scale are of equal value, the scale is at interval level. In
addition to the intervals between two adjacent categories the interval scale
contains properties of nominal and ordinal measurement levels.
With interval measurement we not only know that some category A is greater than
category B and that B is greater than C, but we also know that the intervals
between A and B and B and C are the same.
We know the magnitude of the distance between the categories.
Interval scales lack a true zero point or condition of nothingness.
Example: communication competence
Categories: 5= high competence, 4= moderate competence, 3= average,
2= below average, 1= minimal, 0= poor
The interval between categories is 1.
11
However, the zero point on the scale is not a true zero rather it has been
arbitrarily chosen. The 0, does not represent the absolute absence of
communication competence rather it represents the smallest measureable
quantity of a variable as we used a zero to designate poor comm.
Competence.
For example, it is difficult to conceive of a person having zero intelligence.
Lacking a true zero point means that a researcher cannot make
statements of a proportional nature: a person who scores 30 on a test of
aggression is not three times as aggressive as a person who scores 10.
Ratio Level
Scale that possessing all the properties of interval scale plus one more: the
existence of true zero point. Properties that have natural zero points such as weight,
length, area, etc can be measured on the ratio level of measurement. For example;
since time and distance are ratio measures, one can say that a car traveling at 50
miles per hour is going twice as fast as a car traveling at 25.
Solution
1. An appropriate time period between the first and 2 nd administration should be
set.
2. Researchers recommend at least one full day but not more than a month
between the two administrations.
12
Limitations:
It is difficult to construct truly parallel versions of the same instrument.
Validity
A measuring instrument is said to be valid if it fully and accurately measures the
variable that it supposed to measure.
As in social sciences measurement is usually indirect therefore, researchers are
never completely certain that they are measuring the precise property they intend
to measure. Hence it is necessary to gather some sort of evidence which provides
confidence that a measuring device in fact measures what it appears to measure.
Types of validity
Three basic kinds of validity: I) Content validity (face validity), ii) predictive validity
iii) concurrent validity, each one has a corresponding technique for evaluating the
measuring instrument.
Content validity:
This type of validity deals with whether the instrument contains a representative
sample of a constructs empirical indicators. It is examined on the face.
Example, when students complain that the paper was out of course, they are
questioning content validity of the test (paper). Similarly, if a measuring instrument
is supposed to measure communication competence of the subjects, and by
communication competence the researcher means both writing and speaking skills
but the measure which is being used for measuring this construct contains items
(questions) only about writing skills, the instrument will lacks content validity.
13
Concurrent validity
It is related with the predictive validity however in this case the instrument is being
checked against some present criterion.
Example: A test of proof-reading being administered to two different groups and it
discriminates between the two groups.
SAMPLING
Population: It is a comprehensive and well defined group (a universal set) of the
elements pertinent to a given research question or hypothesis.
A Survey Population
It is an aggregation of all the elements from which a researchers sample will
actually be taken. It is the realistic group of elements available to a researcher after
practical constraints has been taken into account.
Major Types:
1) Probability sampling and 2) Non-probability
sampling
1) Probability Sampling:
Probability sampling is a sampling technique wherein the samples are gathered in a
process that gives all the individuals in the population, equal chances of being
14
selected.
2) Non-Probability Sampling:
We use non-probability sampling techniques, where participants are selected
deliberately by convenience or haphazardly.
Commonly used in studies where the trait or behavior being investigated occurs so
rarely in the general population that it becomes impractical to use a random
selection process.
The disadvantage is that you will not be able to make broad generalizations
about the entire population of people with the condition.
5. Time Constraints:
6. In many cases researchers colleting preliminary information operate under
the time constraints imposed by sponsoring agencies. Since probability
sample is often time costing while a Non-probability Sample may provide
temporary relief.
15
If a subject or unit is drawn from the population and removed from subsequent
selections, the procedure is known as Random Sampling Without Replacement.
(most widely used).
Returning the subject or unit into the population so that it has a chance of been
chosen another time is called Random Sampling with Replacement. (Often used
in most complicated research studies as nationwide survey) .
4.
Non-Probability Sampling
It does not involve random selection as the probability sampling does. Nonprobability samples cannot depend upon the rationale of probability theory. At least
with a probabilistic sample, we know the odds or probability that we have
represented the population well. We are able to estimate confidence intervals for
the statistic. With non-probability samples, we may or may not represent the
population well.
Types of non-probability:
1. Accidental, Haphazard, Easily Available or Convenience Sampling
16
2. Purposive Sampling
3. Quota Sampling
4. Snowball Sampling
Accidental, Haphazard, Easily Available or Convenience Sampling
One of the most common methods of sampling in this category is the traditional
"man on the street" (person on the street) interviews conducted frequently by
television news programs to get a quick (although non-representative) reading of
public opinion. It is collection of readily accessible subjects for study. The typical use
of college students in much research is primarily a matter of convenience. In clinical
practice, we might use clients who are available to us as our sample. In many
research contexts, we sample simply by asking for volunteers. Clearly, the problem
with all of these types of samples is that we have no evidence that they are
representative of the populations we're interested in generalizing to -- and in many
cases we would clearly suspect that they are not.
Advantages:
1. Easily available 2. Low cost 3.Quick results 4. Useful in pretesting questionnaire
5. Beneficial in Pilot Studies 6. Helpful in eliminating potential problems in research
procedures, testing and methodology before the final research study is attempted
Disadvantages:
1. Contains un-known quantities of error. 2. Available samples do not represent
the population
3. Have no external validity. 4. Biased results. 5. Results
cannot be generalized
Purposive Sampling
Purposive Sampling includes the subjects selected on the basis of specific
characteristics and eliminates those who fail to meet these criteria. It often used in
advertising studies. In it, we sample with a purpose in mind. We usually would have
one or more specific predefined groups we are seeking.
For instance, have you ever run into people in a mall or on the street who are
carrying a clipboard and who are stopping various people and asking if they could
interview them?
Most likely they are conducting a purposive sample (and most likely they are
engaged in market research). It is must to verify that the respondent does meet the
criteria for being in the sample.
All of the methods that follow can be considered subcategories of purposive
sampling. We might sample for specific groups or types of people as in modal
instance, expert, or quota sampling. We might sample for diversity as in
heterogeneity sampling. In all of these methods we know what we want -- we are
sampling with a purpose.
17
For instance, if we know the population has 40% women and 60% men, and that we
want a total sample size of 100, we will continue sampling until get those
percentages and then we will stop. So, if we've already got 40 women for our
sample, but not the 60 men, we will continue to sample men but even if legitimate
women respondents come along, we will not sample them. The problem here (as in
much purposive sampling) is that we have to decide the specific features as gender,
age, education race, religion, etc. on which we will base the quota.
2. Non-proportional quota sampling is a bit less restrictive. We specify the
minimum number of sampled units we want in each category. Here, we're not
concerned with having numbers that match the proportions in the population.
Instead, we simply want to have enough to assure that we will be able to talk about
even small groups in the population. This method is the non-probabilistic analogue
of stratified random sampling in that it is typically used to assure that smaller
groups are adequately represented in sample.
4. Snowball Sampling
The term snowball sampling is used most often in academic research. In private
sector research, this approach is known as referrals. In this method a researcher
randomly contacts a few qualified respondents and then asks these people for the
names of friends, relatives, or acquaintances they know who may also qualify for
the research study. These referrals are then contacted to determine if they qualify
for the research.
18
2.
3.
Sampling frame
Sampling frame is the list that includes all the members of the survey population.
This list identifies each member, and hence makes access to that member of the
population easier if selected as respondent for the study.
The list may exist already or can be made for the purpose of the study. It depends
on the nature of the study. Examples: voters list, telephone directory, attendance
sheet, etc.
Sampling error
In all research studies that involve sampling there are chances of sampling error.
Sampling error is the chance of difference between the characteristics of the sample
(statistics) and that of the population from which the sample is drawn.
The sampling error is also called the standard error.
According to Kerlinger, Standard error is the standard deviation of the
sampling distribution of any given measure (for example the mean).
If there was no chances of error then there would have no need for statistical
tests of significance. The word significance would be meaningless. Any
difference at all would be real difference. But such is never the case.
Non-probability does not need to be computed for sampling error.
The greater the sampling error the greater the chances of misrepresentation
of the population.
Computing standard error is a process of determining with a certain amount
of confidence the difference between a sample and the population.
Sampling error involves two concepts:
Confidence level
Confidence interval