click below
click below
Normal Size Small Size show me how
business research
business research exam 1
Term | Definition |
---|---|
every individual in the population. | When we take a census, we attempt to collect data from |
experiment | In a(n) _____________, the environments of the subjects are controlled or manipulated by the researcher. |
high bias | Voluntary response polls almost always suffer from |
any systematic error that tends to occur in the same direction every time you use this sampling method. | Bias in a sampling method is |
sample | A(n) ____ is the subset of units that the experimenter actually measures. |
a simple random sample of the class | A teacher writes the names of her 30 students on small pieces of paper and places them into a box. She then draws out five names to select students to participate in a survey. These five students are |
smaller than before because the sample is larger. | If the producer took an SRS of 400 eggs instead of 200, the new margin of error would be |
about 95% of all samples taken will come at least this close to the truth. | When constructing a confidence interval, the “margin of error” means that, if there is no bias, |
if we took many samples, about 95% of the resulting intervals would contain the true value. | A confidence statement based on a probability sample says, “We are 95% confident that between 72% and 78% of all adult Americans believe that the country needs a national health-care system.” The phrase “95% confident” means that |
some people never answered the phone in several calls and some people chosen for the sample refused to answer questions | A Gallup Poll contacts people by dialing telephone numbers at random. A possible source of nonsampling error in this poll is that |
stratified random sample | A poll questioned 1025 women and 472 men. The design of the sample chose separate samples of men and women and planned to interview more women than men. This is a |
can’t contact some subjects; some subjects refuse to answer | Some common sources of nonsampling error in samples of human populations are |
nonsampling error | One source of error in pre-election polls is that some people in the sample say they will vote, but they end up not voting. This is an example of |
avoid confounding. | Randomization in experimental design is used to |
a lurking variable suspected of being confounded with the explanatory variable | In a randomized block design the blocks often represent levels of |
an experiment imposes treatments on subjects, while an observational study accepts existing treatments. | The difference between an experiment and an observational study is that |
randomization, control, and adequate numbers. | The keys to convincing experiments are |
The study systematically favors certain outcomes. | We say that the design of a study is biased if |
mean | An outlier will usually have a large effect on the |
a properly designed experiment | The best way to settle questions of causation is |
Students who choose to study statistics are probably already good at math, so we can’t conclude anything about cause-and-effect | Students who study statistics in college tend to score higher on the Graduate Record Examinations (GRE) math section than students who do not study statistics. Which is true? |