Please enable JavaScript.

Coggle requires JavaScript to display documents.

Unit 3 Concept Map (Samples and Surveys (Convenience sampling-One of the …

- - - - Example-Only asking people in boston what their favorite baseball team is
    - - Non-response bias-Occurs when an individual chosen for the sample can't be contacted or refuses to participate.
        
        Bias-Using a method that will consistently overestimate or underestimate the value you want to know.
        
        Direction-Bias can operate in both directions. For example, they can over estimate and under estimate sources of data.
        
        Sources of Bias-Sources include selection bias, performance bias, and detection bias.
        
        Example- Asking people that live in New York who the best baseball team is.
        
        Good Sampling Techniques
        
        SRS- Subset of a statistical population in which each member of the subset has an equal probability of being chosen
        
        Example- 25 names of students being pulled from a hat of 200
        
        Stratified SRS-Method of sampling that involves the division of a population into smaller groups
        
        Example- A research team wants to do determine how many 17 year olds in the U.S has their licence. However, the team does not ask every 17 year old in the country, but only 2,000.
        
        Cluster Sampling- Sampling method where the researcher divides the population into separate groups called clusters.
        
        Cluster Sampling Example-Researchers want to survey the academic performances of students in Massachusetts high schools. The research is then divided into clusters by towns in Massachusetts. The data is further clustered depending through simple or systematic random sampling
        
        Advantages and Disadvantages- Cluster Sampling:Cheap, quick, and easy. Cluster sampling allows researchers to focus in on small clusters rather than large data sets. Disadvantages of Cluster is that your data might not be random because it is in a specific area. SRS: Easy to use and it is an accurate representation of the larger population. Disadvantages include time consuming and tedious. Stratified SRS: Good for minimizing sample selection bias and ensuring certain members are not overrepresented or underrepresented.
        
        Properly Designed Survey-Stratify hockey rinks in Massachusetts. Put the rinks in categories of rinks with more than one rink, single rinks, and arenas, What time do these rinks close? For example, lets take a look at the rinks in the single rink category. Order the rinks in alphabetical order and then assign them a number. Choose a random hockey rink out of 10 then have them answer when they close.
        
        Non-response bias example-People that did not vote in the election saying that they did vote.
      - Example- Only asking teachers their opinion on importance of education
  - - - Non-sampling Error-The deviations of estimates from their true values that are not a function of the sample chosen.
      - Example-Doing an experiment about what ethnic groups are lactose intolerant but only interviewing asian people.
    - - Example: A survey presenting the presidential candidates as follows. The crooked Hilary and successful Donald
    - - Placebo effect-A neutral treatment that has no real effect on the dependent variable is known as a placebo. The subject's positive response to a placebo is the placebo effect.
        
        Blinding-The practice of keeping patients in the dark of whether they are receiving a placebo or not.
    - - Replication-Repetition of the experiment on many experimental units. Functions of replication include to improve the precision of the experiment by reducing the standard error of the mean. Also to increase the scope of inference of the experiment, and to effect control over error variance.
      - Randomization-Use of chance to divide experimental units into groups. A process of assigning the treatments in the experiment so that every treatment has an equal chance of being assigned to an experimental unit. Functions of randomization include to provide the random sample of observation, to have a valid estimate of experimental error, to remove the bias of assigning treatments to favorable experimental units, to protect against the effects of factors that cannot be controlled perfectly.
      - Control-The process of minimizing the experimental error. Techniques include balancing, blocking, and grouping of experimental units. Other techniques include using an appropriate experimental design, comparing several treatments, proper handling of experimental units, and refinement of experimental units.
      - Randomized Design Example-In this design, the experimenter randomly assigned subjects to one of two treatment conditions. They received a placebo or they received a cold vaccine. The same number of subjects (500) are assigned to each treatment condition (although this is not required). The dependent variable is the number of colds reported in each treatment condition. If the vaccine is effective, subjects in the "vaccine" condition should report significantly fewer colds than subjects in the "placebo" condition.
        
        Treatment
        Placebo Vaccine
        500 500
- - - - Treatments-Combination of factor levels.
        
        Response variable-Variables of interest that are measured or observed.