Beruflich Dokumente
Kultur Dokumente
Sample Design
Method of selection
Sample structure
Sample designs can vary from simple to complex. They depend on the type of
information required and the way the sample is selected.
Sample design affects the size of the sample and the way in which analysis is
carried out; in simple terms the more precision the market researcher requires, the
more complex the design and larger the sample size will be.
The sample design may make use of the characteristics of the overall market
population, but it does not have to be proportionally representative. It may be
necessary to draw a larger sample than would be expected from some parts of the
population: for example, to select more from a minority grouping to ensure that
sufficient data is obtained for analysis on such groups.
Many sample designs are built around the concept of random selection. This
permits justifiable inference from the sample to the population, at quantified levels
of precision. Random selection also helps guard against sample bias in a way that
selecting by judgment or convenience cannot.
Often, the units in the population can be identified by existing information such as
pay-rolls, company lists, government registers etc.
A sampling frame could also be geographical. For example, postcodes have become
a well-used means of selecting a sample.
Sample Size
For any sample design, deciding upon the appropriate sample size will depend on
several key factors:
2. To lower the margin of error usually requires a larger sample size: the amount
of variability in the population, i.e. the range of values or opinions, will also
affect accuracy and therefore size of the sample
3. The confidence level is the likelihood that the results obtained from the
sample lie within a required precision: the higher the confidence level, the
more certain you wish to be that the results are not atypical. Statisticians
often use a 95% confidence level to provide strong conclusions
4. Population size does not normally affect sample size: in fact the larger the
population size, the lower the proportion of that population needs to be
sampled to be representative. It's only when the proposed sample size is
more than 5% of the population that the population size becomes part of the
formulae to calculate the sample size
Types of Sampling
There are many different types of sampling methods, here's a summary of the most
common:
Cluster sampling
Units in the population can often be found in certain geographic groups or "clusters"
for example, primary school children in Derbyshire.
A random sample of clusters is taken, and then all units within the cluster are
examined.
Advantages
Disadvantages
Convenience sampling
Uses those who are willing to volunteer and easiest to involve in the study.
Advantages
Disadvantages
Judgment sampling
Advantages
Quota sampling
Advantages
Disadvantages
This makes sure that every member of the population has an equal chance of
selection.
Advantages
Disadvantages
May not be practical if the sample requires lots of small visits over the
country
Systematic sampling
After randomly selecting a starting point from the population between 1 and *n,
every nth unit is selected.
Advantages
Disadvantages
Quantitative data deals with numbers and things you can measure objectively:
dimensions such as height, width, length, temperature, humidity, Price, Area and
volume.
Qualitative data deals with characteristics and descriptors that can't be easily
measured, but can be observed subjectivelysuch as smells, tastes, textures,
attractiveness, and color.
Qualitative Quantitative
Methodology
Data are analyzed
Data are analyzed by
through numerical
themes from descriptions
comparisons & statistical
by informants.
inferences.
Nominal: Categorical data and numbers that are simply used as identifiers or
names represent a nominal scale of measurement. Numbers on the back of a
baseball jersey and your social security number are examples of nominal data. If we
conduct a study and we are including gender as a variable, we may code Female as
1 and Male as 2 or vice versa when we enter our data into the computer. Thus, we
are using the numbers 1 and 2 to represent categories of data.
Interval: A scale that represents quantity and has equal units but for which zero
represents simply an additional point of measurement is an interval scale. The
Fahrenheit scale is a clear example of the interval scale of measurement. Thus, 60
degree Fahrenheit or -10 degrees Fahrenheit represent interval data. Measurement
of Sea Level is another example of an interval scale. With each of these scales there
are direct, measurable quantities with equality of units. In addition, zero does not
represent the absolute lowest value. Rather, it is point on the scale with numbers
both above and below it (for example, -10degrees Fahrenheit).
Ratio: The ratio scale of measurement is similar to the interval scale in that it also
represents quantity and has equality of units. However, this scale also has an
absolute zero (no numbers exist below zero). Very often, physical measures will
represent ratio data (for example, height and weight). If one is measuring the length
of a piece of wood in centimeters, there is quantity, equal units, and that measure
cannot go below zero centimeters. A negative length is not possible.
Introduction
Data collection is one of the most important stages in conducting a research. You
can have the best research design in the world but if you cannot collect the required
data you will be not be able to complete your project. Data collection is a very
demanding job which needs thorough planning, hard work, patience, perseverance
and more to be able to complete the task successfully. Data collection starts with
determining what kind of data required followed by the selection of a sample from a
certain population. After that, you need to use a certain instrument to collect the
data from the selected sample.
Types of Data
Data can be divided into two types, namely quantitative and qualitative.
Quantitative data is numerical in nature and can be mathematically computed.
Quantitative data measure uses different scales, which can be classified as nominal
scale, ordinal scale, interval scale and ratio scale. Nominal scale is used to
categorize items into different group, for example male and female, different
examination grades, different races in a country, different types of companies,
different shoe sizes and so on. The statistics that is used to analyze this type of data
is mode. The second measure for quantitative data is the ordinal scale which other
than providing information as the nominal scale does also permit ranking of the
data. For example, shoe sizes can be ranked from big to small. A typical ordinal in
ranking a set of data is poor, satisfactory, good, very god, excellent. On the other
hand, an interval scale not only rank order of a set of data, it also measure the
order in units of equal intervals. However, the starting point for the measurement is
arbitrary rather than absolute. For example, Celsius in temperature measurement is
an interval scale because 0o C is an arbitrary value, it is not absolute zero, it does
not mean temperature is lacking at that point. For absolute quantities, we have to
use the ratio scale. For example, measuring temperature in Kelvin is a ratio scale as
it starts the measurement at absolute zero, which is about -273 o Celsius.
Sources of data
Generally we can collect data from two sources, primary sources and secondary
sources. Data collected from primary sources are known as primary data and data
collected from secondary sources are called secondary data.
Primary data are also known as raw data. Data are collected from the original
source in a controlled or an uncontrolled environment. Examples of a controlled
environment are experimental research where certain variables are being controlled
by the researcher. On the other hand, data collected through observation or
questionnaire survey in a natural setting are examples data obtained in an
uncontrolled environment. Secondary data are data obtained from secondary
sources such as reports, books, journals, documents, magazines, the web and more.
There are many methods to collect data, depending on our research design and the
methodologies employed. Some of the common methods are questionnaires,
interview and observation.
Questionnaires Survey
Questionnaires often use various measuring scales to obtain information from the
respondents. To obtain the bio data of the respondents, we use nominal scale as it
serves as label or identification such as gender and age, which often does not
involve calculations. To gather respondents' preferences, we use ordinal scale which
is used to arrange objects or alternatives according to their magnitude in an ordered
relationship. To obtain information related to attitude, we use rating scales. Rating
asks the respondents to estimate the magnitude of a characteristic or quality
regarding certain object or thing.
On the other hand, rating scale is always used to measure attitude or opinion of the
respondents in an analytical survey. In an analytical survey, it normally needs to
identify independent, dependent and extraneous variables based on a certain
conceptual framework. A researcher needs to conduct a thorough literature review
by paying attention to any existing research and theory relevant to the research
problem. Once the variables are determined, they are built into a questionnaire
using rating scale measures, the most popular one being the Likert scale. Likert
scale questions can consist of three items, four items, five item, six items, seven
items and more. The ratings obtained from the respondents are then summarized or
averaged up to reflect a certain variable, such as job satisfaction. They can be used
to analysed any causal relationship with other variables. Example of Likert-type
questions are shown below:
Strongly
Disagree Strongly Agree
Can the questions be understood; are they free from jargon, esoteric
terminology, unsuitable assumptions and ambiguity?
Observation
Researcher own values and ethics might affect his objectivity and give rise to
observer bias
i. Observation Method:
In this method, the respondent may give wrong and imaginary information. For
effective interview there should be a good rapport with respondents which is often
very difficult to develop. For a good result the interviewers approach should be
friendly, courteous, conversational and unbiased for which a proper training is
required.
(iii) Recall is easy and replies can be recorded without causing embarrassment to
respondents.
This method also has several weaknesses. For example, the surveys are restricted
to respondents who have telephonic facilities and little time is given to respondents
for considered answers. It is not suitable for intensive surveys where comprehensive
answers are required for various questions.
(i) There is low cost even when the universe is large and is widespread
geographically.
(ii) It is free from bias of interviewer as answers are respondents own words.
(iii) Respondents, who are not easily approachable, can also be reached
conveniently. Moreover, respondents are given enough time to give well thought
answers.
(ii) It can be used only when the respondents are educated and cooperative.
This method of data collection is very much like the collection of data through
questionnaires, with little difference that lies in the fact that schedules (proforma
containing a set of questions) are being filled in by the enumerators who are
specially appointed for this purpose. Enumerators explain the aims and objects of
the investigation and also remove the difficulties which any respondent may feel in
understanding the implications of a particular question.
This method is very useful in extensive enquiries and can lead to fairly reliable
results. It is, however, very expensive and is usually adopted in investigations
conducted by governmental agencies or by some organizations. Population census
all over the world is conducted through this method.
For the selection of an appropriate method, the objective, nature and scope of
study, the availability of time and funds, and the level of precision required are to
be taken into consideration.
By far the most widely used method for collecting data is through secondary data
collection, commonly called secondary research. This process involves collecting
data from either the originator or a distributor of primary research (see Primary
Research discussion below). In other words, accessing information already gathered.
In most cases this means finding information from third-party sources such as
marketing research reports, company websites, magazine articles, and other
sources. But in actuality any information previously gathered, whether from sources
external to the marketer or from internal sources, such as accessing material from
previous market research carried out by the marketers organization, old sales
reports, accounting records and many others, falls under the heading of secondary
research.
Published Data is the most basic secondary source of information for data
collection. Published data can be obtained from various sources like books,
magazines, newspapers, journals and periodicals etc. Published data is the most
reliable secondary source of information. The validity of published data is greater
than unpublished data.
The majority of published records can be obtained from libraries and archives.
Libraries carry a vast variety of books, journals and periodicals. You can use this
information as a reference in your thesis, dissertation or other research articles.
Periodicals and journals provide up to date information and they are also available
in libraries. In social sciences and humanities newspapers can also be used to get
references. Newspaper is an excellent source of data collection historical research.
Some record cannot be obtained from any other source except newspaper as it does
not exist in books and journals. Old newspapers record can be obtained from the
archives. In published data books are easier to use as data are arranged in order in
books while newspapers are difficult to use because in newspapers there is no list of
contents or bibliography.
Electronic Data like movies, documentaries and television programs can also be
sued for recording data in secondary research. In the social sciences and humanities
it can be a good source of information.
Government Records are available in the form of government surveys, tax
records, census data and other statistical reports. They are easily available and
widely used in research studies.
Public Sector Records are available in NGOs as well as some other public sector
organization keeps records. These records can be published or unpublished but they
carry information that cannot be obtained from other sources.
Internet in todays world is the fastest growing source of information. The internet
has become mature and today you can get any information from the internet. Most
of the books are available on the internet in e-book format. You can get information
while staying at home. The information can be obtained faster than you can obtain
from any other source. On the internet you can get e-books, e-journals, e-periodicals
and e-magazines. The internet is a multiple source of information as all of the above
mentioned sources can be obtained from the internet. Most recent and most up to
date information can be obtained from the internet as it wont be available in books
and other forms. Getting information from the internet is inexpensive as compared
to other sources. You can get membership of different periodicals, sometimes this
membership is free otherwise you have to pay a small amount of money.
Secondary data are market research data collected for a purpose other than the one
on hand. The data have the advantage of being much less expensive and more
quickly available than primary data. However, because secondary data are collected
for a different purpose, one must carefully evaluate their appropriateness for a
given market research situation. Secondary data should be evaluated with respect
to several important criteria. The data should be accurate, that is, without errors.
The data should be relevant to the particular research need on hand. Relevance is a
function of the level of aggregation of the data, as well as the units and time
increments in which the data are reported. The data should also come in a format
that can be utilized easily. In addition, secondary data should not be out of date.
Consideration should also be given to the format of the data and any restrictions on
their use. When secondary data are evaluated carefully with these criteria, they can
be an excellent source of inexpensive yet valuable information.
A good questionnaire should not be too lengthy. Simple English should be used and
the question shouldnt be difficult to answer. A good questionnaire requires sensible
language, editing, assessment, and redrafting.
1. State the information required- This will depend upon the nature of the
problem, the purpose of the study and hypothesis framed. The target
audience must be concentrated on.
c. Use the third person technique (For example - Mark needed a job badly
and he used wrong means to get it - Is it right?? Different people will
have different opinions depending upon the situation)
a. Yes
b. No
So, the key to creating best questionnaire questions is, understanding the
questionnaire format, and the type of questions that can be asked to respondents
using a survey.
Multiple choice questions, where respondents are restricted to choose among any of
the given multiple choice answers are known as closed format or closed-ended
questions. There is no fixed limit as to how many multiple choices should be given;
the number can be even or odd.
There are 7 ways in which pollsters can create polling or survey questions for their
respondents to collect accurate statistical data. Following is a list of 7 types of
closed-ended questions that can be a part of your questionnaire design:
A. Leading Questions
Questions that force your audience for a particular type of answer are known as
leading questions. In a leading question, all the answers would be equally likely. An
example of a leading question would be a question with choices such as, fair, good,
great, poor, superb, excellent etc. These questions are meant to get an opinion from
the audience in limited words.
Example of a Closed-Ended Leading Question
B. Importance Questions
In importance questions, the respondents are usually asked to rate the importance
of a particular issue, on a rating scale of 1 to 5. These questions can help you
understand things that hold significance to your respondents and allow you make
business critical decisions.
C. Likert Questions
Likert questions can help you ascertain how strongly your respondents agree to a
particular statement. Such type of questions also help you assess how your
customers feel towards a certain issue, product or service.
D. Dichotomous Questions
These are simple questions that ask respondents to answer in a yes or no. One
major drawback with dichotomous questions is that it cannot analyze the answers
between yes and no, there is no scope for a middle perspective.
E. Bipolar Questions
Bipolar questions are the ones having two extreme answers written at the opposite
ends of the scale. The respondents are asked to mark their responses between
those two.
In rating scale questions, the respondents are asked to rate a particular issue on a
scale that ranges between poor to good. Rating scale questions usually have an
even number of choices, so that respondents are not given the choice of selecting a
middle option.
Buying propensity questions try to assess the future intentions of customers and
determine respondent's buying intention. These questions ask respondents if they
want to buy a particular product, what requirements they want to be addressed, and
whether they would buy such a product in future.