Chapter 6.2 Part 1

review Randomized Comparative Experiments Compares two or more treatments The diagram illustrates the paths Conclusion drawn from the response variable

Randomized Comparative Experiments All subjects are treated alike except for the treatment they receive Experiments are designed to compare

Randomized Comparative Experiments The logic of randomized comparative experiments assumes that all the subjects are treated alike except for the treatments they receive. Any other unequal treatment can cause bias. But treating subjects exactly alike is hard to do. We also know that placebos work! Medical studies must take special care to show that a new treatment is not just a placebo. Part of equal treatment for all subjects is to be sure that the placebo effect operates on all subjects.

Example Want to help balding men keep their hair? Give them a placebo – one study found that 42% of balding men maintained or increased the amount of hair on their heads when they took a placebo. Another study told 13 people who are very sensitive to poison ivy that the stuff being rubbed on one arm was poison ivy, It was a placebo, but all 13 broke out in a rash. The stuff rubbed on the other arm really was poison ivy, but the subjects were told it was harmless – and only 2 of the 13 developed a rash.

Continued When the ailment is vague and psychological, like depression, some experts think that about ¾ of the effects of the most widely used drugs is just the placebo effect. Others disagree. The strength of the placebo effect in medical treatments is hard to pin down because it depends on the exact environment. How enthusiastic a doctor seems to matter a lot. But “placebos work” is a good place to start when you think about planning medical experiments. What can be done to counteract a doctor’s attitude?

Double Blind Experiments Neither the subjects nor the people working with them know which treatment each subject is receiving Until the study ends and results are in, only the statistician knows which treatment the subject is receiving. Reports in medical journals regularly begin with, “this study was a randomized, double- blind, placebo-controlled trial.”

Bias in Experiments Those who refuse to participate are systematically different from those who cooperate. EX: a specific group underrepresented. Subjects who participate but do not follow the experimental treatment are called nonadherers. Dropouts, subjects that begin the experiment but do not complete it .If the reason the subject leaving is unrelated to experimental treatments, no harm is done. If the subject drops out because of their reaction to a treatment bias can occur.

Can we generalize? A well designed experiment tells us a cause- and-effect relationship between the subjects and the treatments. But we want to be able to say something about a population. How do we go from a subject group to wider population? Results must be statistically significant Treatment, subject and environment of the experiment must be realistic.

Example: studying frustration A psychologist wants to study the effects of failure and frustrations on the relationships between members of a work team. She forms a team of students, brings them to the psychology lab, and has them play a game that requires teamwork. The game is rigged so that they lose regularly. The psychologist observes the students through a one-way window and notes the changes in their behavior during an evening of playing games.

Continued Playing a game in a lab for small stakes, knowing that the session will soon be over, is a long way from working for month developing a new product that never works right and is finally abandoned by your company. Does the behavior of the students in the lab tell us much about the behavior of the team whose product fails?

Completely Randomized Designs Divide subjects at random into as many groups as there are treatments. Apply each treatment to one of the groups Single explanatory variables EX: drugs vs. placebo, classroom vs. online Completely randomized design can have any number of explanatory variables.

Example: Durable Fabric A fabrics researcher is studying the durability of a fabric under repeated washings. Because the durability may depend on the water temperature, and the type of cleaning agent used, the researcher decided to investigate the effect of these two explanatory variables on durability.

Continued Variable A is water temperature and has 3 levels: Hot (145 degree F), Warm (100 degrees F), and cold (50 degrees F). Variable B is the cleansing agent and also has three levels: regular Tide, low-phosphate Tide, and Ivory Liquid. A treatment consists of washing a piecec of fabric (a unit) 50 times in a home automatic washer with a specific combination of water temperature and cleansing agent.

Continued The response variable is strength after 50 washes, measured by a fabric-testing machine that forces a steel ball through the fabric and records the farbic’s resistances to breaking. How many possible treatments are there? What are they? This combination effect is called an Interaction

Homework