polisci 3 problem set 1 - Eric Han Sean Gailmard GSI:...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Eric Han Sean Gailmard GSI: Andrej Krickovic February 13 th , 2008 PS3: Problem Set I Part I 4a. The Public Health Services would have to address the confounding factors (a variable that may effect the outcome of the experiment that is not the treatment) that may occur during an experiment dealing with smoking and its association with the status of one’s health. The problem may lie within how the conductors of the experiment select the groups to be studied—for example, do the control and treatment groups share similarities rather than the contact to cigarettes? Experimenters must, therefore, find a way to control for the confounding factors in an observational study. The Public Health Services are then addressing the confounding factors of sex and age (i.e. it is assumed that men are more likely than women to fail in their health [i.e. heart disease] and that older people would probably have different smoking habits than younger people.) with hopes of obtaining a more consistent and accurate study. By making the groups separate, homogenous and smaller, it eliminates misleading results that would have more than likely have occurred if we only observed the health of smokers and non-smokers. 4b. While the study may produce results that come from a seemingly unflawed experiment, it does not necessarily mean that said results might be entirely accurate. As the authors point out, “association is not the same as causation”, since there may be “hidden confounders” that the experiment did not account for. In the context of this study, it does not take in account the emotional/psychological aftereffects of persons who have just recently stopped smoking. For example, quitting smoking can lead people to binge on unhealthy foods in order to fill the void, which may lead to an unhealthy dietary lifestyle (an example of hidden confounders). Furthermore, the study only looks at subjects that recently stopped smoking and does not take any heed to some sort of long-term study. In order to address this confounding variable, a more comprehensive re-examination of long-term health should be included. 7a If Kaiser Permanente conducted an experiment in which they chose both the treatment group (those exposed to oral contraceptives) and the control group (those who did not get the treatment) then it is a controlled experiment. If Kaiser just played the role of observers and let the subjects choose which groups they belong too, then it is an observational study. It would seem that this particular study is an observational study, since the conductors of the experiment are simply just observing the subjects. In addition,
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
no person would ever put him or herself in danger of cervical cancer for the sake of science. 7b
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/11/2008 for the course POL SCI 108 taught by Professor Rust during the Summer '08 term at University of California, Berkeley.

Page1 / 6

polisci 3 problem set 1 - Eric Han Sean Gailmard GSI:...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online