#### Data Collection Methods

Download
Report

####
Transcript Data Collection Methods

Data Collection Methods
• In a population there is a parameter of
interest whose value is unknown.
• We use a sample estimator to estimate the
value of this parameter.
• The sample estimator is called a sample
statistic.
Some common parameters and sample
statistic
Name
Statistic
Parameter
Mean
Sample mean
Population mean
Standard deviation
Sample std deviation
Population std
deviation
correlation
sample correlation
coefficient
Population correlation
coefficient
proportion
Sample proportion
Population proportion
Data Collection Methods
• It is critical to get “Good Sample”.
• Good Sample is one that fairly represents
every member of the population
• How do we get a good sample?
Data Collection Methods
Examples
1.
2.
3.
4.
Internet polling
Telephone surveys
Taking surveys at the mall
Surveys through mail or e-mail
Data Collection Methods
• Basic Principles of Getting Good Sample
• Randomize: Select your sample randomly.
• Assign numbers to members of the population
• Use a random number generator to select
your sample
Data Collection Methods
• Sample size is important!
• You need a large enough sample so that you
can get fair representation.
Data Collection Methods
Types of Samples
Simple Random Sample (SRS): A sample in
which every group of n individuals has the
same chance of being selected.
Example: Select 5 students from a class of 50
students Use Excel’s random number
generator.
Data Collection Methods
• Stratified Samples: Used for large population
sizes.
• First divide the entire population into groups
(with common characteristics). Such groups
are called strata.
• Within each stratum use simple random
sampling method
Data Collection Methods
• Cluster sampling: Divide the population into
some clusters or groups.
• Then select randomly few clusters and
perform simple random sampling in the
clusters selected.
Data Collection Methods
• Multistage Sampling: Divide the population
into some clusters or groups.
• Select few groups randomly
• Divide the selected groups further into smaller
parts
• Then select a simple random sample from
each part