Like this presentation? Why not share!

# 26738157 sampling-design

## by mb861972 on Oct 21, 2011

• 4,211 views

sampling theory

sampling theory

### Views

Total Views
4,211
Views on SlideShare
4,211
Embed Views
0

Likes
1
252
0

No embeds

### Categories

Uploaded via SlideShare as Microsoft PowerPoint

## 26738157 sampling-designPresentation Transcript

• SAMPLING DESIGN
• The Nature of Sampling
• The basic idea of sampling is that by
• selecting some of the elements in
• population, we may draw conclusions
• Nature of Sampling
• A population element is the unit of study
• The unit of study might be a person or just about anything else
• Why Sample?
• Lower cost
• Greater accuracy of results
• Greater speed of data collection
• Availability of Population elements.
• What is Good Sample?
• How well it represents the characteristics of the population it purports to represent
• In measurement terms, the sample must be valid.
• Validity of a sample depends on two considerations
• Accuracy and precision.
• Accuracy
• Degree to which bias is absent from the sample.
• Some sample elements underestimate the population values being studied and other overestimate them.
• How do Bring in Accuracy?
• Under-estimation and over-estimation offset each other and gives a sample value that is generally close to the population value.
• Offsetting requires large number of elements
• Precision
• No sample will fully represent its population in all respects
• Differences in the sample and population values occurs due to random fluctuations inherent in the sampling process.
• This is called sampling error and reflects the influences of chance in drawing the sample members.
• Sampling Error
• What is left after all known sources of systematic variance have been accounted for.
• In theory, sampling error consists of random fluctuations only
• Some unknown systematic variance may be included when too many or too few sample elements possess a particular characteristic.
• Precision
• Measured by the standard error of estimate
• Type of standard deviation measurement
• The smaller the standard error of estimate, the higher is the precision
• Samples of the same size can produce different amounts of error variance.
• Classification of Sample Techniques Sampling Techniques Probability Non-Probability
• Probability Sampling Probability Sampling Simple Random Sampling Systematic Sampling Cluster Sampling Stratified Random Sampling Proportion ate Dis Proportion ate One- Stage Two Stage Multi- Stage
• Non-Probability Non- Probability Convenience Sampling Quota Sampling Judgment Sampling Snowball Sampling
• Steps in Sampling Design
• What is the Relevant Population?
• The definition of the population
• Whether the population consists of individuals, households, families or a combination of these
• What are the Parameters of Interest?
• Population parameters are summary descriptors (proportion, mean, variance) of variables of interest in the population.
• Sample statistics are descriptors of the relevant variables computed from sample data.
• Sample statistics are used as estimators of population parameters
• What is the Sampling Frame?
• The sampling frame is closely related to the population.
• It is the list of elements from which the sample is actually drawn.
• Ideally, it is a complete and correct list of population members only.
• What is the Type of Sample?
• Choosing a probability sampling technique has several consequences.
• A researcher must follow appropriate procedures, so that :
• What is the Type of Sample?
• Interviewers cannot modify the selections made.
• Only those selected elements from the original sampling frame are included.
• Substitutions are excluded except as clearly specified and controlled according to pre-determined decisions rules.
• What Size Sample is Needed ?
• Some Myths
• A sample must be large or it is not representative.
• A sample should bear some proportional relationship to the size of the population from which it is drawn.
• Some principles that influence sample size include :
• The greater the dispersion or variance within the population, the larger the sample must be to provide estimation precision.
• The greater the desired precision of the estimate, the large the sample must be.
• The narrower the interval range, the larger the sample must be.
• Some Principles that Influence Sample Size Include :
• The higher the confidence level in the estimate, greater the sample size must be
• If the calculated sample size exceeds 5 percent of the population, sample size may be reduced without sacrificing precision.
• How Much Will it Cost?
• Almost all studies have some budgetary
• constraint, and this may encourage a
• researcher to use a non-probability sample
• Probability sample surveys incur list costs for sample frames, and other costs that are not necessary when more haphazard or arbitrary methods are used.
• Probability Sampling
• Based on the concept of random selection
• A controlled procedure
• Assures that each population element is given a known nonzero chance of selection.
• Non-probability Sampling
• In contrast, is arbitrary (nonrandom) and subjective
• Allowing interviewers to choose sample elements “at random”
• Probability Sampling- Simple Random Sampling
• Each element in the target population has an equal chance or probability of being selected in the population
• Numbers can be randomly generated by computers or picked out of a box
• In small population random sampling is done without replacement
• Requisites
• Target population size is small
• Homogeneous sampling frame is defined
• Not much information is available regarding the population
• Free of classification error
• Elimination of human bias
• Non-dependency on the availability of the element
• Imperative to list every item in the population prior to sampling
• Requires constructing very large sampling frames
• Hence requires extensive sampling calculations
• Hence excessive costs
• Systematic Sampling
• Selecting every k th from a sampling frame
• K represents the skip interval
• Formula
• k = population size /
• Sample Size
• Used in industrial operations where equipments in the production are checked for defects
• Questioning people in a sample survey
• Necessary to select first element randomly and then apply k
• Economical and less time consuming
• Stratified Random Sampling
• Process of grouping members into relatively homogenous groups before sampling
• Each element of the population must be included in a stratum
• Strata should be exhaustive so as not to leave any element of the population
• Then random sampling is applied within each stratum
• Proportional Stratified sampling
• Number selected from each strata depends on the homogeneity and std dev of elements present in it
• Proportional Stratified sampling – A smaller sample can be drawn out of the stratum known to have the same value
• Disproportionate Stratified Sampling
• Samples can be drawn in a much higher proportion from another stratum where values are known to differ.
• Higher number of respondents are required to minimise sampling errors because of the high variability
• Improves representativeness by reducing sampling error
• Greater statistical efficiency over simple random sampling
• Groups are represented when strata are combined
• There can be errors in designating bases due to time and cost factors
• Multistage Cluster Sampling
• Involves grouping the population into various clusters and then selecting a few clusters for study
• Clusters should be homogenous in nature
• Elements within each cluster should be heterogeneous
• Cluster should be similar to the population
• Multistage Cluster Sampling
• Suitable for studies that cover large geographic areas
• Researcher can go for 1, 2 or multi-stage cluster sampling
• In single stage- all elements from each cluster are studied
• Two Stage
• Two stage - uses random sampling to select a few elements from each of selected clusters
• Multi-stage - selecting a sample in 2 or more successive stages.
• Cluster / units is selected in the first stage and further divided into clusters / units
• Non- Probability Sampling