1
Ten things about Experimental Design AP Statistics, Second Semester Review

2
What is bias? Bias is the systematic favoring of a particular outcome A statistic is an unbiased estimator of a parameter when the center of the sampling distribution of the statistic is equal to the parameter it is trying to estimate.

3
6 Kinds of Bias Volunteer Sample Bias Undercoverage Bias Nonresponse Bias Response Bias Wording of Question Bias Convenience Sample Bias

4
6 Sampling Techniques 4 Random Sampling Techniques Simple Random Sampling Cluster Sampling Stratified Random Sampling Systematic Sampling 2 Non-Random Techniques Volunteer Sampling Convenience Sampling

5
Observational Study vs. Experiment? Experiment imposes a treatment on the experimental units. Observational studies do not attempt to change the units. Experiments allow us to claim causality, while observational studies do not.

6
Experimental Designs Controlled Randomly Assigned Treatments Block Blind Double-Blind Matched-Pairs

7
Lurking Variables & Confounding A lurking variable is a variable that is not among the explanatory or response variables in a study but that may influence the response variable. Confounding occurs when two variables are associated in such a way that their effects on a response variable cannot be distinguished from each other.

8
The Placebo Effect & Double Blind When an subject responds to a treatment simply based on trust of the professional applying the treatment, it may because of the Placebo Effect. A well designed experiment hides from the subject whether getting the placebo (blind) and hides from those applying the treatment whether they giving a placebo (double blind).

9
Significant Results When the actual results are so different from the expected results that we think it is likely that it didn’t happen may pure chance, we say the results are significant.

10
3 Principles of Experimental Design Control for lurking variable by using a comparative design. Random assignment to create roughly equivalent groups. Replication: Use enough experimental units so that any differences in the effects can be distinguished from random chance.

Similar presentations