AP Stat Chapter 4 Flashcards
Terms : Hide Images [1]
| 15919528770 | Treatment | A specific condition applied to the individuals in an experiment. A combination of the different levels for each factor. | 0 | |
| 15919528771 | Population | The entire group of individuals we want information about. | 1 | |
| 15919528772 | Experimental Units | The collection of individuals to which treatments are applied. Who or what we are testing the effects or experimenting on. | 2 | |
| 15919528773 | Parameter | Numbers used to describe the population. *We usually don't know* Population Mean or Population Proportion | 3 | |
| 15919528774 | Sample | A subset of individuals in the population from which we actually collect data. | 4 | |
| 15919528775 | Random Assignment | Important in a randomized design where we randomly assign to which treatment group an individual should go. Allows for generalization to the experimental group | 5 | |
| 15919528776 | Completely Randomized Design | Start with experimental units. Randomize to treatment groups. Give treatment. Compare results. | 6 | |
| 15919528777 | Statistic | Numbers used to describe the sample. Sample Mean or Sample Proportion | 7 | |
| 15919528778 | Bias | Consistently underestimate or consistently overestimate the value you want to know. | 8 | |
| 15919528779 | Double-Blind | Where neither the subjects nor those who interact with them know which treatment a subject received. | 9 | |
| 15919528780 | Statistically Significant | An observed effect so large that it would rarely occur by chance alone | 10 | |
| 15919528781 | Convenience Sample | Choosing individuals from the population who are easy to reach | 11 | |
| 15919528782 | Voluntary Response Sample | Made up of people who self-select into a survey Examples: Mail-In Surveys, Online Polls | 12 | |
| 15919528783 | Blocking/Randomized Block Design | 1) Block purposely FIRST. 2) THEN, randomize assignment within each block. Prevents confounding. | 13 | |
| 15919528784 | Matched Pairs | A form of a randomized block design where there is a one-to-one comparison. Examples: Twins, Testing the same plot of land (same everything) split it in half. | 14 | |
| 15919528785 | Simple Random Sample | Sample chosen in such a way that every group of "n" individuals in the population has an equal chance to be selected as the sample. Examples: Names in a hat, Random # Generator | 15 | |
| 15919528786 | Placebo Effect | the response to the "dummy" treatment. | 16 | |
| 15919528787 | Stratified Random Sample | A population divided into categories (or strata), then a random sample is taken from each category, then combined to get the overall random sample. "Some from all" | 17 | |
| 15919528788 | Systematic Random Sample | Sampling with a random starting point and a fixed, periodic interval. "Every nth person" | 18 | |
| 15919528789 | Inference about a population | Random selection from the population | 19 | |
| 15919528790 | Inference about cause-and-effect | Random assignment to the treatment groups. | 20 | |
| 15919528791 | Cluster Sample | The researcher divides population into separate groups (clusters). Then, a random sample of clusters is selected from the population and everyone in the cluster is used in the sample. "All from some" | 21 | |
| 15919528792 | Undercoverage | When some members of the population are inadequately represented in the sample. We are "under-representing" our sample because we are missing out on people who should be considered. | 22 | |
| 15919528793 | Factor | The variables that you wish to test the effects of. Usually the same as the explanatory variables | 23 | |
| 15919528794 | Level | The different categories used for each factor | 24 | |
| 15919528795 | Nonresponse | People have the opportunity to answer, but they choose not to, which misrepresents the population | 25 | |
| 15919528796 | Response Bias | When subjects respond in a way that is other than the truth, which usually is because of some outside pressure or wording of the question. | 26 | |
| 15919528797 | Observational Study | Observes individuals and measures variables but does NOT attempt to influence the responses. Can establish the existence of an association between two variables but NOT cause-and-effect | 27 | |
| 15919528798 | Confounding | Occurs when two variables are associated in such a way that you can't tell which is affecting the response variable. | 28 | |
| 15919528799 | Experiment | Deliberately imposes some treatment on individuals to measure their responses. Not intended to make generalizations about a population but can measure cause-and-effect. | 29 |