Ch3 Surveys and Sampling
Wednesday, January 29, 2014
Three Ideas of Sampling
1. Draw a sample.
1. chosen from the population.
2. Samples that over- or underemphasize some characteristics of the population: biased
a. we should select sample at random
difference between the sample and population values is considered as sampling error or
3: The Sample Size Is What Matters
• How large a random sample do we need for the sample to be reasonably representative of
• sample size matters - regardless of the population size
** important! parameter & statistic
if the sample estimate the corresponding parameters accurately, the sample is representative.
---- Homework question: researcher went to car dealer and ask every 20th people if they care about
environment.What's the population?
• Hey! The population is people not people who go to dealers!
• people who go to dealers is the Sampling Frame.
• sample is the everything 20th people!
population parameter of interest
Sampling Techniques Nonstatistical sampling --> not random sampling
• Collected in the most convenient manner for the researcher (ask whoever is around)
• Bias: Opinions limited to individuals present
• Individuals choose to be involved.These samples are very susceptible to being biased
because different people are motivated to respond or not. Often called “public opinion polls,”
these are not considered valid or scientiﬁc
Bias: Sample design systematically favors a particular outcome
Statistical Sampling --> Individuals in the sample are chosen based on known or calculable
1. Simple Random Sampling
• Every possible sample of a given size has an equal chance of being selected
The simplest way to obtain a sample is to draw names out of a hat
• The sample can be obtained using a table of random numbers or computer random number
• to select sample at random, we need to deﬁne a sampling frame
from the whole population, we obtain a List of population - a list of individuals from which
the sample is drawn.
• Phone book
• Registered voter list
• Membership lists
• aka Effective population --
2. Stratiﬁed Random Sampling
• Divide population into homogenous subgroups (called strata) according to some common
• must determine ﬁrst: population is dividable
• e.g. gender / major
• Select a simple random sample from each subgroup
Combine samples from subgroups into one
3. Cluster Sampling
• Divide population into several “clusters,” each representative of the population (e.g., county)
• here, the population cannot be divided into distinct groups
• e.g. when measuring fertilizer use, because there are too many fertilizer brands,
types, we measure clusters - counties -
• Select a simple random sample of clusters
• All items in the selected clusters can be used, or items can be chosen from a cluster
using another probability sampling technique