Ch. 9 - Research Participants
Sunday, December 16, 2012 12:36 PM
PSYC 2520: Introduction to Experimental Psychology
Beginning Behavioral Research: A Conceptual Primer (7th ed. 2012) Rosnow & Rosenthal
Chapter 9: Survey Research and Subject Recruitment
What are opportunity and probability samples?
• Opportunity samples are the first units that are available, whereas probability sampling plans use a random procedure for selecting a sample that is expected to be
representative of the target population. However, to be absolutely sure that a sample is representative, we would have to know the true population value in advance, in which
case (practically speaking) there would be no reason to study the sample.
• Researchers who use a sample can never be 100% sure of their generalizations; they can make a reasonable guess, however, by first developing an accurate sampling frame
that defines the target population and then relying on a carefully designed blueprint (the sampling plan) to select the sample by means of probability sampling
○ The term probability sampling implies that randomness enters into the selection process at some stage so that the laws of mathematical probability apply
○ Probability refers to the mathematical chance of an event's occurring
What is meant by bias and instability in survey research?
• Two important statistical requirements of a probability sampling plan are
○ That the sample be unbiased
○ That there be stability in the samples
• A biased sample overestimates or underestimates the true population
○ Bias = systematic error
• An unstable sample is characterized by sampling units that vary greatly from one another (sample is highly variable)
○ Generally speaking, the more homogenous the population, the fewer the sampling units needed
○ Stability is estimated by statistical procedures such as variance and standard deviation
Why do we not know " for sure" the bias in sampling?
• We can never know for sure the bias in sampling results unless we know the results for the entire population
How is simple randomsampling done?
• In simple random sampling, the sample is selected from an undivided population (or from a relatively homogenous stratum), and each unit has the same chance of being
selected on any draw
○ In order for this to occur, the selection of one unit must have no influence on the selection of other units
○ A further assumption is that we have an understanding of the existence of all the units in the population
○ Simple random sampling is useful when the population is known to be homogeneous or when its precise composition is unknown
• Sampling with replacement means that the selected units are placed in the selection pool again and may be reselected on subsequent draws
○ Every unit continues to have the same probability of being chosen every time a number is read
• In sampling without replacement , a previously selected unit cannot be reselected and the population shrinks each time you remove a unit, but all the units remaining have the
same likelihood of being drawn on the next occasion
What are stratified random sampling and area probability sampling?
• When we know something about the exact composition of the population, a more efficient method of sampling is to sample from the different substrates of the population
(this is known as stratified random sampling)
○ A separate sample is randomly selected from each homogeneous stratum (or "layer") for the entire population
• A popular variant of this sampling approach is called area probability sampling because the population is divided into geographic areas
What did the Literary Digest case teach pollsters?
• Literary Digest predicted the repub