Types of Bias
This type of bias occurs when some members of the population are less likely to be chosen or cannot be chosen.
What is undercoverage?
The part of an experiment that the researcher actively changes about the subjects.
What is the treatment?
In an experiment, this is the process of grouping similar experimental units together and then randomly assigning treatments within these groups.
What is blocking?
A sample is said to be this if it (on average) over-estimates or under-estimates the parameter of interest.
What is biased?
This response bias occurs when sampling units are unreachable or fail to answer a survey.
What is nonresponse bias?
This tool is a treatment that has no active ingredients but is otherwise like all other treatments.
What is a placebo?
"Would you go against the Second Amendment and support the harsher regulation of firearms?" is an example of this type of bias.
What is response bias?
An example of this technique would be to randomly select a few Freshmen, Sophomores, Juniors, and Seniors while studying the opinions GHS students have with the school mascot.
What is a Stratified Random Sample?
In order to study a new granola's effect on metabolism, units are randomly assigned either the new or old granola but are not told which. The researchers do not know who has been assigned each granola type. This experiment is said to be
What is a double blind?
Bias is present in this design. Name the type of bias and if over/underestimates the true population parameter.
A political pollster is seeking information on public attitudes toward funding of pornographic art by the National Endowment for the Arts (NEA). He asks an SRS of 2000 U.S. adults, “Rather than support government censorship of artistic expression, are you in favor of continuing federal funding of artists whose work may be controversial?” 85% of those surveyed answer “yes.”
Response Bias (wording of the question). It is an overestimation because they are trying to get you to answer yes.
While studying the proportions of colors of plain M&M's, you randomly select a few packages from the store and check all the candy in the packages. This is an example of this sampling technique.
What is a Cluster Sample?
An experiment is run in which the treatment group is given a specific diet and exercise routine, and the control is asked to eat and exercise normally. Their current level of health and gender are said to be these.
What are confounding variables?
You can only do this with the results of an experiment if you have randomly sampled.
Generalize the results to the population.
Bias is present in this design. Name the type of bias and if over/underestimates the true population parameter.
In 2003, the AARP conducted a survey of their members (people over age 50 who pay membership dues) on proposed Medicare legislation. One of the questions was: “Even if this plan won’t affect you personally either way, do you think it should be passed so that people with low incomes or people with high drug costs can be helped?” 75% of respondents answered yes.
Undercoverage. They only asked those in AARP. Those that are young, low income, have high drug costs would probably want it to be passed. So it underestimates the true proportion.
(you could also argue for response bias)
Name all the possible sampling designs.
SRS, Systematic, Cluster, Stratified, Convenience, Voluntary.
The four principales of an experiment.
What are control, randomization, replication, and comparison?
If the observed result of a study are too unusual to be explained by chance of the random assignment of treatments, the results are called...
What is Statistically Significant?
In an experiment on young group dynamics, a teacher divides a class into eight groups, four groups of boys and four groups of girls. The groups of boys are then given three, two, one, or no pieces of candy, as are the groups of girls. In the experiment, the gender and the amount of candy are these.
What are the factors?