RESEARCH METHODOLOGY (MGT 369)

Chapter 8: Sampling

.Most research are involving a sample that is a portion of the total population. This is the limitation..

Basic concept of sampling

Population- total of all things to be researched.

Elements- an individual member of the population

Population frame- complete list of all elements

found in a population Sample- a portion of the population Subject- an individual member from a sample taken.

Sampling a process of selecting elements from the population to make-up the

Steps in Sampling process

1

2
3 4 5

Determine the relevant population Choose a relevant sampling frame to use Determine the sampling design Determine the sample size Execute the sampling process

Rules of the Thumb of Sampling (Roscoe (1975)

1. Sample sizes larger than 30 and less than 500 are appropriate for most research

2. Where samples are to be broken into sub-samples (males/females, junior/senior, etc) a minimum sample size of 30 for each category is necessary.
3. In multivariate research (including multiple regression analyses), the sample size should be several times (preferably 10 times or more) as large as the number of variables in the study. 4. For simple experimental research with tight experimental controls (matched pairs, etc), successful research is possible with samples as small as 10 to 20 in size

Reasons for sampling

Inherent to human behaviour when one has to

make purchasing decision If constrained by time, cost and manpower Research process requires sample Sampling reflect confidence since there is enough similarity among the elements in a population.

Precision
This refers to how close our estimate is to the true population characteristic Precision is a function of the extent of variability in the sampling distribution of the sample mean. If we want to reduce the standard error or the extent of precision than we must increase the sample size.

Confidence
If precision denotes how close we estimate the population parameters based sample statistics, then confidence denotes how certain we are that our estimates will actually hold true for the population. Other things being equal the narrower the range the lower the confidence. The level of confidence can range between 0 to 100 percent. A 95 percent confidence is a conventionally accepted level for most business research, expressed by denoting the significant level as p .05 which means at least 95 times out of 100 our estimate will reflect the true population of the true population characteristic

PROBABILITY & NON-PROBABILITY SAMPLING

In probability sampling the elements in the population have some known chance or probability of being selected as sample subjects. This sampling design is used when the representativeness of the sample is of importance in the interest of wider generalizability. In non-probability sampling , the elements do not have a known or predetermined chance of being selected as a subject. This sampling design is used when time and other factors rather than generalizability become critical.

Types of Sampling
Stratified Random Sampling

Simple Random Sampling

Probability Samples

Systematic Sampling

Cluster and Areas Sampling

Simple Random Sampling

Every element in the population has a known and equal chance of being selected as a subject. Computers can assist in generating random numbers.This design has the least bias and offers the most generalizability but cumbersome and expensive with difficulty in acquiring updated population lists.

Systematic Sampling
This method involves drawing every nth element in the population starting with a randomly chosen element between 1 and n. Usually used for market surveys and consumer attitude surveys where telephone directory serves as the population frame.

Stratified Random Sampling

This method involves a process of stratification or segregation followed by random selection of subjects from each stratum.The population is first divided into mutually exclusive groups that are relevant, appropriate and meaningful in the context of the study.

Stratified Random Sampling (cont..)

Stratifying subjects on the basis of life stages, income levels and place of stay to study the buying patterns, stratifying companies according size, industry and profit to study stock market reactions are examples.
than within-group differences

Stratification is an efficient research sampling design since it provide more information with a given sample size. It ensures homogeneity within each stratum but heterogeneity between strata. There are more between-group differences

Cluster Sampling
Groups or chunks of elements that, ideally, would have heterogeneity among the members within each group are the focus of this sampling method. This method is in contrast with the methods before this. When several groups with intragroup heterogeneity and intergroup homogeneity are found, then a random sampling of the clusters or groups can be done and information gathered from each of the members in the randomly chosen clusters. Cluster samplings are prone to greater biases and is the least generalizable of all probability sampling designs..

Area Sampling
This constitute geographic clusters when the research pertains to populations within identifiable geographic areas such as counties, city blocks, or particular boundaries within a locality. This method is less expensive than most of the other probability designs and it is not dependent on a population frame.

Quota

Judgmental

Nonprobability

convenience

Snowball

NON PROBABILITY SAMPLING

In this sampling design the elements in the population have no probabilities attached to their being chosen as sample subjects. The findings from this sample cannot be confidently generalized to the population. Researchers at times are less concerned with generalizability but more towards quick information in an inexpensive way. Convenience Sampling Involves collecting information from members of the population who are conveniently available to provide it. It is normally used during the exploratory phase of research project and the best way in getting basic information quickly and efficiently.

Judgment Sampling This involves the choice of subjects who are in the best position to provide the information required. This method is used when a limited number or categories of people have the information that is sought.. This method may curtail the generalizability of the findings because we are using sample of experts who are conveniently available to us.

Quota Sampling
This method ensures that certain groups are adequately represented in the study through the assignment of a quota. The quota is fixed for each subgroup based on the total number of each group in the population. The result of this method are not generalizable to the population. It is considered a form of proportionate stratified sampling in which a predetermined proportion of people are sampled from different groups, but on a convenience basis.

Quota sampling ensures that all the subgroups in the population are adequately represented in the sample. It is basically stratified samples from which subjects are selected non-randomly.