mba 687 assignment
TRANSCRIPT
-
8/22/2019 Mba 687 Assignment
1/21
AN
ASSIGNMENTON
PROBABILITY SAMPLING
MARKETING RESEARCH(MBA 687)
PREPARED BY
MADUAKOR CHIDINMA IFEOMAADP11/12/H/0845
SUBMITTED TO
DR J O ADETAYODEPT OF MANAGEMENT & ACCOUNTING,
OBAFEMI AWOLOWO UNIVERSITY,ILE-IFE, OSUN STATE.
-
8/22/2019 Mba 687 Assignment
2/21
JULY, 2013
\
SAMPLING TECHNIQUES
Research studies are distinct events that involve a particular group of
participants. However, researchers usually intend on answering a general
question about a larger population of individuals rather than a small select
group. Therefore, the main aim of psychological research is to be able to make
valid generalizations and extend their results beyond those who participate. For
this reason, the selection of participants is a very crucial issue when planning
research. Obviously, researchers cannot collect data from every single
individual from their population of interest, since this would be extremely
expensive and take a very long time! So instead they use a small group of
individualscalled a sample. The sample is chosen from the population and is
used to represent the population. Researchers use sampling techniques to
select the participants for their sample these techniques help to minimise
cost whilst maximizing generalizability. I am going to be discussing the Non-
Probability sampling techniques and methods, and considering the issue of
sampling bias and the problems associated in research.
-
8/22/2019 Mba 687 Assignment
3/21
There are a variety of different sampling methods available to researchers to
select individuals for a study. Sampling method fall into two categories:
PROBABILITY SAMPLING
Historical background
Probability-based sampling is a development of the last 60 to 70 years. Around
the turn of thecentury Kiar, in Norway, was an advocate for sampling. In the
early work, purposive methods (ienon-probability sampling) predominated, but
in 1934 Neyman published a paper which laid the basis ofsampling theory,
and explained the advantages of random sampling over purposive selection. (He
used a number of examples in his paper, particularly an unsuccessful
purposive sub-sample drawn from the 1921 Italian Census by the Italian
census bureau.) Over the next 20 or so years, the theory of probability-based
sample design was further developed, and the major statistical offices were all
won over to probability-based design. The first generation of sampling
textbooks appeared around 1950.
Probability Sampling includes some form of random selection in choosing the
elements. Greater confidence can be placed in the representativeness of
probability samples. This type of sampling involves a selection process in which
each element in the population has an equal and independent chance of being
selected.
Four main methods include:
Simple Sampling
-
8/22/2019 Mba 687 Assignment
4/21
Sratified Sampling Cluster Sampling and Systematic Sampling
Non-probability sampling:
The elements that make up the sample are selected by non random methods.
This type of sampling is less likely than probability sampling to produce
representative samples. Even though this is true, researchers can and do
use non-probability samples.
The three main methods are:
Convenience Quota Purposive
.
NON PROBABILITY SAMPLING
The difference between non-probability and probability sampling is that non-
probability sampling does not involve random selection and probability
sampling does. Does that mean that non-probability samples aren't
representative of the population? Not necessarily. But it does mean that non-
probability 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
-
8/22/2019 Mba 687 Assignment
5/21
for the statistic. With non-probability samples, we may or may not represent
the population well, and it will often be hard for us to know how well we've
done so. In general, researchers prefer probabilistic or random sampling
methods over non-probabilistic ones, and consider them to be more accurate
and rigorous. However, in applied social research there may be circumstances
where it is not feasible, practical or theoretically sensible to do random
sampling. Here, we consider a wide range of non-probabilistic alternatives.
.
We can divide non-probability sampling methods into two broad types:accidental or purposive. Most sampling methods are purposive in nature
because we usually approach the sampling problem with a specific plan in
mind. The most important distinctions among these types of sampling methods
are the ones between the different f the population are chosen based on their
relative ease of access. To sample friends, co-workers, or shoppers at a single
mall, are all examples of convenience sampling. Such samples are biased
because researchers may unconsciously approach some kinds of respondents
and avoid others (Lucas 2012), and respondents who volunteer for a study may
differ in unknown but important ways from others (Wiederman 1999).
Snowball sampling -The first respondent refers a friend. The friend alsorefersa friend, and so on. Such samples are biased because they give people with
more social connections an unknown but higher chance of selection (Berg
2006).
http://en.wikipedia.org/wiki/Convenience_samplinghttp://en.wikipedia.org/wiki/Snowball_samplinghttp://en.wikipedia.org/wiki/Snowball_samplinghttp://en.wikipedia.org/wiki/Convenience_sampling -
8/22/2019 Mba 687 Assignment
6/21
Judgmental sampling or Purposive sampling - The researcher chooses thesample based on who they think would be appropriate for the study. This is
used primarily when there is a limited number of people that have expertise in
the area being researched.
Deviant Case - Get cases that substantially differ from the dominant pattern (aspecial type of purposive sample).
Case study - The research is limited to one group, often with a similarcharacteristic or of small size.
ad hoc quotas - A quota is established (say 65% women) and researchers arefree to choose any respondent they wish as long as the quota is met.
Even studies intended to be probability studies sometimes end up being non-
probability studies due to unintentional or unavoidable characteristics of the
sampling method. In public opinion polling by private companies (or other
organizations unable to require response), the sample can be self-selected
rather than random. This often introduces an important type of error: self-
selection bias. This error sometimes makes it unlikely that the sample will
accurately represent the broader population. Volunteering for the sample may
be determined by characteristics such as submissiveness or availability. The
samples in such surveys should be treated as non-probability samples of the
population, and the validity of the estimates of parameters based on them
unknown.
REASONS FOR USING NON-PROBABILITY SAMPLING
http://en.wikipedia.org/wiki/Self-selection_biashttp://en.wikipedia.org/wiki/Self-selection_biashttp://en.wikipedia.org/wiki/Self-selection_biashttp://en.wikipedia.org/wiki/Self-selection_bias -
8/22/2019 Mba 687 Assignment
7/21
No sampling frame is available. This is often true for the product dimension but
less frequently so for the outlet dimension, for which business registers or
telephone directories do provide frames, at least in some countries, notably in
Western Europe, North America and Oceania. There is also the possibility of
constructing tailor-made frames in a limited number of cities or locations,
which are sampled as clusters in a first stage. For products, it may be noted
that the product assortment exhibited in an outlet provides a natural sampling
frame, once the outlet is sampled as a kind of cluster, as in the BLS sampling
procedure presented above. So the absence of sampling frames is not a good
enough excuse for not applying probability sampling. Bias resulting from non-
probability sampling is negligible. There is some empirical evidence to support
this assertion for highly aggregated indexes. Dalen (1998b) and De Haan,
Opperdoes and Schut (1999) both simulated cut-offsam pling of products
within item groups. Dalen looked at about 100 groups of items sold in
supermarkets and noted large biases for the subindices of many item groups,
which however almost cancelled out after aggregation. De Haan, Opperdoes
and Schut used scanner data and looked at three categories (coffee, babies
napkins and toilet paper) and, although the bias for any one of these was large,
the mean square error (defined as the variance plus the squared bias) was
often smaller than that for pps sampling. Biases were in both directions and so
could be interpreted to support Dale ns findings. The large biases for item
groups could, however, still be disturbing. Both Dalen and De Haan,
-
8/22/2019 Mba 687 Assignment
8/21
Opperdoes and Schut report biases for single-item groups of many index
points.
We need to ensure that samples can be monitored for some time. If weare unlucky with our probability sample, we may end up with a product
that disappears immediately after its inclusion in the sample. We are
then faced with a replacement problem, with its own bias risks. Against
this, it may happen that short-lived products have a different price
movement from the price movement of long-lived ones and constitute a
significant part of the market, so leaving them out will create bias.
A probability sample with respect to the base period is not a proper probability
sample with respect to the current period. It is certainly true that the bias
protection offered by probability sampling is to a large extent destroyed by the
need for non-probabilistic replacements later on.
Price collection must take place where there are price collectors. Thisargument applies to geographical sampling only. It is, of course, cheaper
to collect prices near the homes of the price collectors, and it would be
difficult and expensive to recruit and dismiss price collectors each time a
new sample is drawn. This problem can be reduced by having good
coverage of the country in terms of price collectors. One way to achieve
this is to have a professional and geographically distributed interviewer
organization within the national statistical agency, which works on many
surveys at the same time. Another way of reducing the problem is to have
-
8/22/2019 Mba 687 Assignment
9/21
a firststage sample of regions or cities or locations which changes only
very slowly.
The sample size is too small. Stratification is sometimes made so finethat there is room for only a very small sample in the final stratum. A
random selection of 15 units may sometimes result in a final sample
that is felt to be skewed or otherwise to have poor representativity
properties. Unless the index for this small stratum is to be publicly
presented, however, the problem is also small. The skewness of small
low-level samples will even out at higher levels. The argument that
sample size is too small has a greater validity when it relates to first-
stage clusters (geographical areas) that apply to most subsequent
sampling levels simultaneously.
Sampling decisions have to be taken at a low level in the organization.Unless price collectors are well versed in statistics, it may be difficult for
them to perform probability sampling on site. Such sampling would be
necessary if the product specification that has been provide centrally
covers more than one product (price) in an outlet. Nevertheless, in the
United States (U.S. BLS, 1997) field representatives do exactly this. In
Sweden, where central product sampling (for daily necessities) is carried
to the point of specifying well-defined varieties and package sizes, no
sampling in the outlets is needed. In countries where neither of these
possibilities is at hand, full probability sampling for products would be
more difficult.
-
8/22/2019 Mba 687 Assignment
10/21
In some situations, there are thus valid reasons for using non-probabilitytechniques. We discuss two such techniques below.
Cut-off sampling
Cut-off sampling refers to the practice of choosing the n largest sampling units
with certainty and giving the rest a zero chance of inclusion. In this context,
the term largeness relates to some measure of size that is highly correlated
with the target variable. The word cut-off refers to the borderline value
between the included and the excluded units.
In general, sampling theory tells us that cut-off sampling does not produce
unbiased estimators since the small units may display price movements which
systematically differ from those of the larger units. Stratification by size or pps
sampling also has the advantage of including the largest units with certainty
while still giving all units a non-zero probability of inclusion. If the error
criterion is not minimal bias but minimal mean square error (=variance+
squared bias) then, since any estimator from cut-off sampling has zero
variance, cut-off sampling might be a good choice where the variance reduction
more than offsets the introduction of a small bias. De Haan, Opperdoes and
Schut (1999) demonstrate that this may indeed be the case for some item
groups.
Often, in a multi-stage sampling design there is room for only a very small
number of units at a certain stage. Measurement difficulties that are
sometimes associated with small units may then be a reason, in addition
to large variances, for limiting price collection to the largest units.
-
8/22/2019 Mba 687 Assignment
11/21
Note that a hybrid design can also be applied in which there is a certainty
stratum part, some probability sampling strata and a low cut-off point below
which no sample at all is drawn. In practice, this design is very often used
where the below cut-offsection of the universe is considered insignificant and
perhaps difficult to measure.
A particular CPI practice that is akin to cut-off sampling is for the price
collector to select the most sold product in an outlet, within a centrally defined
specification. In this case, the sample size is one (in each outlet) and the cut-
offrule is judgemental rather than exact, since exact size measures are only
rarely available. In all cases of size-dependent sampling in an outlet, it is
crucial to take a long-term view of size, so that temporarily large sales during a
short period of reduced prices are not taken as a size measure. Such products
will tend to increase in price in the immediate future much more than the
product group which they represent and thus create a serious overestimating
bias.
-
8/22/2019 Mba 687 Assignment
12/21
CONVENIENCE OR ACCIDENTAL SAMPLING
Definition
Distinctive Features One of the most common methods of sampling goes under
the various titles listed here. I would include in this category the traditional
"man on the street" (probably the "person on the street") interviews conducted
frequently by television news programs to get a quick (although non
representative) reading of public opinion. I would also argue that the typical
use of college students in much psychological 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 and in many cases we would clearly suspect that they
are not.
Distinctive Features
-
8/22/2019 Mba 687 Assignment
13/21
Convenience samples are also known as accidental or opportunity samples.
The problem with all of these types of samples is that there is no evidence that
they are representative of the populations to which the researchers wish to
generalize. This approach is often used when the researcher must make use of
available respondents or where no sampling frame exists. A good example is
provided by my own experience of conducting evaluative research designed to
explore the efficacy of community treatment programmes for sex offenders.
Here an accidental sample of those men sentenced to treatment was used by
necessity (Davidson, 2001). TV, radio station, newspaper and magazine polls
and questionnaires are also an example of this type of sampling, where
respondents may be asked to phone in or fill in a questionnaire.
-
8/22/2019 Mba 687 Assignment
14/21
PURPOSIVE SAMPLING
Definition
A form of non-probability sampling in which decisions concerning the
individuals to be included in the sample are taken by the researcher, based
upon a variety of criteria which may include specialist knowledge of the
research issue, or capacity and willingness to participate in the research.
Distinctive Features
Some types of research design necessitate researchers taking a decision about
the individual participants who would be most likely to contribute appropriate
data, both in terms of relevance and depth. For example, in life history
research, some potential participants may be willing to be interviewed, but may
not be able to provide sufficiently rich data. Researchers may have to select a
purposive sample based on the participants oral skills, ability to describe and
reflect upon aspects of their lives, and experience of the specific focus of the
research.
A case study design is another type of research that often requires a purposive
sample. Imagine that a research team wishes to explore the types of academic
-
8/22/2019 Mba 687 Assignment
15/21
support provided for students in a single high school. In selecting that school
the researchers may need to take a variety of factors into account. They may
want a school in which academic support is sufficiently innovative to make the
final research report of wide interest in the profession. They will require a
school in which the management are supportive of the research, and in that
the teachers and students show a willingness to participate. The researchers
may want a school that is exceptional in terms of overall academic
performance, or that has an average level of attainment. Finally, they may
prefer a school that is reasonably accessible for members of the research team.
When all relevant factors have been considered, the research team will select
the case study school, which will constitute the purposive sample. If it is
appropriate, a purposive sample may be combined with a probability sample.
Once the high school has been selected, a random sample of teachers and
students could be selected from whom to collect data.
Evaluation
The advantage of purposive sampling is that the researcher can identify
participants who are likely to provide data that are detailed and relevant to the
research question. However, in disseminating the findings, the researcher
should make fully transparent the criteria upon which the sampling process
was based.
The principal disadvantage of purposive sampling rests on the subjectivity of
the researcher's decision making. This is a source of potential bias, and a
-
8/22/2019 Mba 687 Assignment
16/21
significant threat to the validity of the research conclusions. These effects may
be reduced by trying to ensure that there is an internal consistency between
the aims and epistemological basis of the research, and the criteria used for
selecting the purposive sample.
QUOTA SAMPLING
Definition
A non-probability method of selecting respondents for surveys. The interviewer
begins with a matrix of the target population that is to be represented and
potential respondents are selected according to that matrix. Quota sampling is
also known as a purposive sample or a non-probability sample, whereby the
objective is to select typical, or representative, subjects and the skill and
judgment of selectors is deliberately utilized (Abrahamson, 1983).
Distinctive Features
Quota sampling allows the researcher to control variables without having a
sampling frame. This method is often used for market research because it does
not require a list of potential respondents. The interviewer finds respondents,
usually in public areas, who fit into the predetermined categories until the
quotas are filled. To that end, quota sampling is a convenient and inexpensive
method of research. If the interviewee is unavailable or refuses to participate
-
8/22/2019 Mba 687 Assignment
17/21
they can easily be replaced with another potential respondent who meets the
same criteria.
Evaluation
Statisticians criticize quota sampling for its methodological weakness. Although
the interviewer randomly chooses respondents he or she comes across on the
street, quota sampling cannot be considered a genuinely random method of
sampling because not every member of the population has an equal chance of
survey selection (for example, those who are at work or at home). Therefore, the
principles of statistical inference cannot be invoked.
There are a number of factors that can result in research bias. First,
interviewers may misjudge a potential respondent's characteristic, such as
their age. Secondly, the interviewer runs the risk of subconsciously making a
subjective judgment before approaching a potential respondent. As a result, the
interviewer may not approach those deemed unfriendly and runs the risk of
distorting the findings. This is also known as systematic bias (Abrahamson,
1983). Finally, quota sampling can never be truly representative because
certain factors may prevent certain groups of people from being chosen for the
research. For example, as noted above, market research conducted during the
day may over-represent housewives shopping in the city centre and under-
represent office workers.
Despite these limitations, quota sampling continues to be used because there
are circumstances when random or stratified random sampling is not possible.
-
8/22/2019 Mba 687 Assignment
18/21
SNOWBALL SAMPLING
Definition
A form of non-probability sampling in which the researcher begins by
identifying an individual perceived to be an appropriate respondent. This
respondent is then asked to identify another potential respondent. The process
is repeated until the researcher has collected sufficient data. Sometimes called
chain letter sampling.
Distinctive Features
Snowball sampling can be a useful technique in research concerned with
behavior that is socially unacceptable or involves criminal activity. The nature
of such activities may make it a virtually impossible task to identify all
members of the research population; even identifying a few members can be
very difficult. In the case of research on, say, shoplifting or car theft, the
identification of a single willing respondent may be difficult. The first stage in
the process usually involves a purposive sampling decision to identify one
respondent who is willing to provide data. Once the data collection has been
completed, the researcher asks the respondent to nominate another person
who may be willing to provide the type of data required. The process continues
-
8/22/2019 Mba 687 Assignment
19/21
until either the researcher fails to make any new contacts, or the new data do
not appear to add anything substantial to existing understanding.
Snowball sampling can also be a relevant technique for groups of people who
may feel lacking in confidence to participate in a research project. Such people
could include the homeless, alcoholics, or those who have suffered illness or an
assault. In such cases, they may have more confidence and be more likely to
participate if they are approached by a person with similar experiences.
Evaluation
The advantage of snowball sampling is that it enables the researcher to identify
potential participants when it would otherwise be extremely difficult to do so. It
is also a sampling strategy that demonstrates sensitivity to potential
participants, in that they are identified by people with a similar experience.
The disadvantage of the approach is that it is dependent upon each participant
sufficiently understanding the nature of the research in order to be able to
identify another suitable participant. The next nominated participant may have
a limited or biased understanding of the research issue. In addition, the
members of the snowball sample may have certain features in common which
are uncharacteristic of the research population as a whole. The very fact that
they are all acquainted with each other is a source of potential bias.
-
8/22/2019 Mba 687 Assignment
20/21
REFERENCES
1. Berg, Sven. (2006). "Snowball SamplingI," pp. 78177821 inEncyclopedia of Statistical Sciences, edited by Samuel Kotz, Campbell
Read, N. Balakrishnan, and Brani Vidakovic. Hoboken, NJ: John Wiley
and Sons, Inc.
2. Deming WE (1960), "Sample Design in Business Research", John Wileyand Sons, New York.
3. Denzin, N. K., & Lincoln, Y. S. (2000). Handbook of qualitative research.London: Sage Publications.
4.Neyman J, "On the two different aspects of the representative method:
the method of stratified sampling and the method of purposive selection",
Journal of the Royal Statistical Society, Vol. 97, pp 558-606.
5. Polit, D. F. & Beck, C. T. (2003). In Nursing Research: Principles andMethods. 7th ed.) (413-444). Philadelphia: Lippincott Williams & Wilkins.
6. Smith TFM (1983), "On the validity of Inferences from Non-randomSamples", Journal of the Royal Statistical Society, Vol. 146, pp 394-403.
7. Stephan FP and McCarthy PJ (1958), "Sampling Opinions", John Wileyand Sons, New York.
8. William M.K. Trochim,(2006) Research Methods Knowledge Base
-
8/22/2019 Mba 687 Assignment
21/21