Unit 3.1
when collecting data, what is the entire group we want information about?
population
samples are what if they are systematically not representative of the desired population.
Biased
observes individuals and measures variables but does not attempt to influence the response.
observational study
what is a dummy treatment?
placebo
Why do we use control groups in experiments?
To reduce the variability in the response variable between the two groups so that any difference is due to the treatment alone
When an item from a population can be selected only once, this is called
without replacement
Occurs when an individual chosen for a sample can’t be contact or refuses to respond. Non-response is a big problem in mail surveys.
non response
deliberately imposes some treatment on individuals to measure their responses.
Expirement
when the subject does not know what treatment they are receiving?
blinding
what is it called when you send a survey to every person who visited somewhere on a random day then collect the data
a census
When an item from the population can be selected more than once, this is called
With replacment
giving a wrong answer simply because respondent doesn’t remember the correct answer.
lack of memory
What is the number one advantage of an experiment over an observational study?
Only with a well-designed, controlled experiment can we say that one variables causes a change in another variable. We CANNOT infer causation with an observational study.
it might be difficult to tell if the explanatory caused a change or if it was another variable that wasn't measured
Researchers plan to use a completely randomized design, describe how they should assign treatments to their 126 experimental units
Give each a random number between 1-126, use a random number generator to choose 20 random samples
what type of sampling uses subjects that are readily available?
Convenience sampling
occus when the sample data is incorrectly collected, recorded, or analyzed.
In a gym class, the effect of exercise on blood pressure is studied by requiring that half of the students walk a mile each day while the other students run a mile each day.
experiment - treatment of walking or running
Random selection of individuals
allows inference for the population
We want to make sure we are using a design that compares two or more treatments. We need to make sure that the groups we are comparing though don’t differ greatly before our experiment beings or bias can result. To avoid this, we use....
comparison
what is it called when you randomly select an arbitrary starting point, then select every kth member of the population.
Systematic Random Sampling
Subtle differences in phrasing make large differences in the results.
phrasing
A medical team examines the records of 5 large hospitals and compares the survival times of those cancer patients who had surgery versus those who had chemotherapy.
Observational study - examined records only
Random assignment in an experiment
permits infrence about cause and affect
The most important element of any experiment. It must be incorporated either in the selection process of experimental units and/or the distribution of experimental units into treatment and control groups. You can use your calculator, the random digit table or names out of a hat or flipping a coin to randomize an experiment.
randomization