stats chapter 4
3 principles of statistical design
control, random assignment, replication
experiment
deliberately imposes some treatment on individuals to measure their responses
cluster sample
divide the population into groups/clusters. Randomly select some of these clusters. ALL individuals in the chosen clusters are included in the sample
how to store a variable
enter a random number, sto, math 1, enter sto, math 8
completely randomized design, block, matched pair
experimental design
explanatory variable
factors, may help or explain or influence changes in a response variable
systematic error that tends to occur in the same direction whenever you use this sampling method
bias is any
replication
certain number of subjects in each group
convenience sample
choosing individuals who are easiest to reach, uses bias and unlikely to represent the whole population
matched pairs design
common form of blocking for comparing just two treatments
response variable
measures an outcome of a study
nonsampling error
mistakes that occur after taking a sample
observational study
observes individuals and measures variables of interest but does NOT attempt to influence the responses
undercoverage
occurs when some groups in the population are left out of the process of choosing the sample (ex a sample of all households in an area leaves out the homeless, UNDERESTIMATE)
confounding
occurs when the two effects of variables cannot be separated, caused by lurking variables
simple random sample (SRS)
of size n consists of n individuals from the population chosen in such a way that every set of n individuals has an equal chance to be the sample actually selected
the results may be affected by response bias
32% say that they favor some kind of national proficiency test example
example of response bias
people lying and saying they voted when they didn't
only people aged 8-28 in Massachusetts
A company wishes to determine which of two video game systems is preferred. A large SRS of people aged 8-28 living in Massachusetts was surveyed to determine this. What population can the results of this survey be safely generalized?
voluntary response sample
A sample which involves only those who voluntary participate in the sampling, biased because it attracts passionate people, leads to an OVERESTIMATE
stratified random sample
First divide the population into groups of similar individuals, called strata. Then choose a separate SRS from EACH stratum to form the full sample.
sampling error
Mistakes made in the process of taking a sample that could lead to inaccurate information about the population. Bad sampling methods and undercoverage are common types of sampling error.
inference about cause and effect
randomly assigned
describe how you will select your sample
Put labels, look for 1 digit/2 digits in the table within my labels (inclusive). I will ignore repeats. I will be done when I have x people
which of the following is a true statement about experimental design
Randomization is a key component in experimental design. Randomization is used to reduce bias.
inference about population
randomly selected
simple random sample, stratified random sample, cluster random sample
sampling methods
A professor wants to study the effectiveness of a new study tool for a course. There are 150 students registered for the course.The professor assigns each student a number from 1 to 150 and uses a random number generator to assign the first 75 students selected to use the new study tool. The remaining 75 subjects are assigned to use the previous study tool.What type of experiment design is this?
completely randomized
a cause and effect relationship between two variables can best be determined from which of the following
a controlled experiment where the observation units are chosen randomly
block
a group of experimental units that are known before the experiment to be similar in some way that is expected to affect the response to the treatments
gives every possible sample of the same size the chance to be selected
a simple random sample is a sample that
treatment
a specific condition applied to the individuals in an experiment
response bias
a student tells each subject her personal opinion opposing marijuana, and then asks them their opinion. What is the existing flaw in the experimental design?
lurking variable
a variable that is not among the explanatory or response variables in a study but that may influence the response variable, makes it hard to see the true relationship between the explanatory and response variables
single blind experiment
an arrangement in which participants remain unaware of whether they are in the experimental group or the control group, but they know theres 2 groups
double blind experiment
an experiment in which neither the subjects nor the researchers know which subjects are members of the experimental group and which are serving as control subjects, until after the experiment is over.
statistically significant
an observed effect so large that it would rarely occur by chance
all planned studies must be reviewed in advance by an institutional review board, all subjects must give their informed consent, and all individual data must be kept confidential
basics of data ethics
nonresponse bias
bias introduced when a large fraction of those sampled fails to respond
bias
systematically favors certain outcomes
completely randomized design with two explanatory variables
the 30 second and 60 second commercial example
census
the official count of a population
randomized block design
the random assignment of experimental units to treatments is carried out separately within each block
placebo effect
the response to a dummy treatment
experimental units
the smallest collection of individuals to which treatments are applied
completely randomized design
the treatments are assigned to all the experimental units completely by chance
what is the purpose of using a control group
to provide a baseline for comparing the effects of the other treatments
when is it beneficial to use a blocked design
when a population consists of groups of individuals that are similar but different
when does randomization take place in a block design
when there's a lurking variable