HW2 - STAPLE HERE Name _ Student ID_ HSCI 330 Spring 2011...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Page 1 of 6 b STAPLE HERE Name ________________________ Student ID______________________ HSCI 330 – Spring 2011 Assignment #2 Please download and print this assignment exactly as is it formatted here. Write your answers clearly on the pages here in the spaces provided. If we cannot read your handwriting, we will mark it as incorrect. You may NOT type the questions into another document and use typed answers. For written questions, if you need more space use the back of the same page. Please put a clear note that you have written on the back of the page. For multiple choice questions, you are asked to circle the best answer. Individual answers are indicated with “ “ and underline. For this assignment, you should read the following article, which is available in the homework 2 folder on WebCT: Cellular telephones and risk for brain tumors: a population-based, incident case-control study. Neurology. 2005 Apr 12;64(7):1189-95. (It is titled, “Neurology. 2005 Apr 12;64(7) 1189-95.pdf.”) NOTES: You should read through this paper to become familiar with it, but I will give you a little introduction here to orient you and help you to focus on those parts that are important for this homework. This is a prospective case-control study. We said that case-control studies are usually retrospective (which is true), but this one is prospective. They started their study and prospectively enrolled nearly all of the incident cases of two types of brain cancer (glioma and meningioma) in Denmark over approximately 2.5 years. They then used random sampling from the general population to find controls matched to the cases on age and sex (because age and sex were potential confounders). There is a question about matching in this homework assignment. They selected many more controls than cases, which is not a problem with the study design. (I emphasize it here because students often think it is a problem). We often select more controls than cases in our sample because the larger sample size will reduce random error and has no effect on bias. (How we select controls can affect bias because that affects the study population. But, the number of people we select into our sample has no effect on the study population and so cannot affect bias. The size of the sample can only affect random error.) In fact, the paper reports on three different case-control studies. They divided glioma into two types (low-grade and high-grade) to create a total of three disease variables: meningioma, low-grade glioma, and high-grade glioma. As you should remember, a case-control study can have many exposure variables (that is one of its strengths), but it can only have one disease variable. Thus, this paper reports on three different case-control studies, one for each disease variable. Although a case-control study can only have one disease variable, it can have multiple exposure variables. Each of the three case-control studies here uses the same set of exposure variables: regular cell phone use, time since
Background image of page 1

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

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 6

HW2 - STAPLE HERE Name _ Student ID_ HSCI 330 Spring 2011...

This preview shows document pages 1 - 2. Sign up to view the full document.

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