Evaluate Statistical Reports

Página 1

when we read a statistical report we wish to see if its reasonable to draw conclusions based on the report.

sampling errors are potential errors that arise from us taking only part of the population. sample taken from sub population rather than whole population.

an experimental study is one in which two groups are compared. one group has a change to its environment and the other does not.

an observational study is where subjects are observed and the researcher does not intervene to change any variable. may be because of ethical reasons.

a causal claim is a conclusion as to what caused a change in the response variable.

--> therefore no causal claim can be supported by an observational study.

confounding variable is a variable the researcher had not considered. it is something related to the experiment that changes and effects the outcome but is not part of the experiment.

response variable is the variable that is measured to compare the two groups in the experiment.

explanatory variable is the variable you change. the one the researcher is experimenting with. used to predict changes in the response variable - things that impact the response variable.

treatment, a combination of explanatory variables assigned by the researcher.

non sampling errors, good surveys try and minimize

- question effects (subtle variation in wording, sway responses the way the interviewer/surveyor wants it),

- transferring findings (taking data from one population and transferring the results to another)

- self selection bias (people decide themselves whether to be surveyed or not)

CI, A confidence interval gives an estimated range of values which is likely to include an unknown population parameter, the estimated range being calculated from a given set of sample data.

MOE, The margin of error is a statistic expressing the amount of random sampling error in a survey's results. The larger the margin of error, the less confidence one should have that the poll's reported results are close to the "true" figures; that is, the figures for the whole population. Margin of error occurs whenever a population is incompletely sampled.

New Page