Please enable JavaScript.
Coggle requires JavaScript to display documents.
Unit 4 Vocab (Vocabulary of Experiments (Experimental Units: The physical…
Unit 4 Vocab
-
Good Sampling Techniques
Simple Random Sample (SRS): A sample from a set of statistical information where each member has an equal chance of being chosen. An example would be the names of 25 employees being chosen out of a hat from a company of 250 employees.
-
-
Stratified Random Sample: Divides a population into subgroups. Fore example, Taking the population of a town and asking just the children a question.
-
Disadvantages: A large population would take too much time to effectively do the full experiment. Also, time is money so the cost would be high.
Cluster Sample: a type of sampling method where the researcher divides the population into separate groups, called clusters. Then, a simple random sample of clusters is selected from the population. An example of this would be boxing off an acre of land in the woods and looking to see how many inch worms are in that random acre.
-
Disadvantages: May take lots of time, time is money
Non-sampling Error:
Non-response: When individuals are unwilling to respond to a survey. For example, when a survey gets sent in the mail to people and some decide do not answer it.
-
-
Sampling Errors:
Voluntary Response Sample: a sample made up of volunteers that is always biased. An example would be call-in radio shows that solicit audience participation in surveys on controversial topics
Convenience Sample: One of the main types of non-probability sampling methods. For example a psychology teacher asking her students to complete the study.
Undercoverage: A type of sampling bias that happens when members of the sample are inadequately represented
The three principles of experiment design are replication, randomized, and control.
-
Randomization is important because it is a way to eliminate any possible biases that may happen in the experiment.
-
-
Lurking Variable: A well designed experiment including a design feature that allows researchers to eliminate extraneous variable. An example would be the education level of SAT test takers.
Confounding: A confounding variable is one that affects the dependent variable other than the independent variable between independent and dependent variables. For example, in a study that is researching is weight gain is affected by amount of physical activity, the calories consumed daily would be the confounding variable.
A lurking variable can lead to a confounding variable due to the fact that they are both indistinguishable. A confounding one is in the design of the study, and a lurking one is not. However, a lurking variable could lead to a confounding one due to the fact that it could be noticed over time and put in the design.
Properly Designed Survey
We are going to go to the football game on Friday night and ask if people enjoy the music that the pep band plays or if they find it annoying.
1) List the amount of people at the football game alphabetically. We will ask their name when they purchase their ticket. Then, we will assign a four digit number to each person. For the purpose of this survey we will assume there is 1500 and we are surveying 150.
-
Population: The entire pool from which a statistical sample is drawn. For example, a population is a group of people that called in to participate in the study.
Sample: A set of data collected from a statistical population by a defined procedure. An example of sample could be population.
Observational Study: attempt to understand cause-and-effect relationships. An example would be a research study comparing the risk of developing lung cancer, between smokers and non-smokers.
Subjects: a person or thing that is being discussed, described, or dealt with. An example of a subject is a person that is undergoing the survey
Random Assignment: A technique for assigning participants to different groups in an experiment. An example would be an experimenter using an SRS to get a sample group that is completely random.
Completely Randomized Design: During a random sample when an experimenter randomly assigns subjects to one or two treatment conditions
Double Blind: the practice of keeping patients in the dark as to whether they are receiving a placebo or not.
Experiment: A scientific procedure that is done to make a discovery, test a hypothesis, or demonstrate a known fact. An example of an experiment could be a study on the number of students late to school using variables.
Treatment: The way someone behaves or deals with someone or something. An example would be the way the experimenter treats the sample group; either nicely or poorly.
Bias refers to the tendency of a measurement process to over- or under-estimate the value of a population parameter. In survey sampling, for example, bias would be the tendency of a sample statistic to systematically over- or under-estimate a population parameter.
Placebo Effect: In an experiment, subjects respond differently after they receive treatment, even if the treatment is neutral.
-