**Complete the following assignment. Your assignment should be at least 4 pages total. Use proper APA citations and list your references.**

** **

- Define and give the formula for an odds ratio:

According to Michigan Center for Public Health, “an odds ratio (OR) is defined as the ratio of the odds of an event occurring in the one group to the odds of it occurring in another group, or to a data-based estimate of that ratio” (Michigan Center for Public Health, n.d.). This is a basic estimate of the probability of the occurrence of a disease by measuring the approximate presence.

**An odds ratio formula looks like this:**

**(A/C)/(B/D)=(AD)/(BC) (Michigan Center for Public Health, n.d.).**

This considers the number of disease cases in each situation and calculates the probability that it will occur. In obtaining the value, it allows us to know if we may be subject to the exposure and the odds that it would happen in the absence of that exposure.

- Complete the 2 x 2 table below and calculate the Odds Ratio: There were 91 total with lung cancer of which 27 were not exposed to tobacco smoke; 173 total without lung cancer of which 56 were exposed to tobacco smoke. Show your work.

Disease Status | |||

Yes | No | ||

Exposure Status | Yes | ||

No |

Odds Ratio = #of exposed cases/# of unexposed cases**/**# of exposed non cases/#of unexposed non cases.

Yields: 64/27

________________ =4.9538

56/117

- Interpret the odds ratio / what does this finding mean?

Since the odds ratio is greater than 1, it tells us that the outcome of lung cancer and the exposure to smoking tobacco is directly related. The odds ratio of 4.95238 is basically stating that a smoker has 4.95238 times more of a chance than a non-smoker to have lung cancer. Although, it is scientifically based, the calculation does show that the incidence is higher in smokers due to chemicals than in non-smokers. This also does not account for second hand smoker contact.

- You are reviewing the results of a case-control study of vitamin D supplements and prostate cancer. The study had an alpha level of .05 and 95% CI. The study findings report an Odds Ratio of .49, p value = .001, 95% CI (.45 – .60).

Interpret these results: comment on the OR, p value, and CI.

The OR here is 0.49 which is less than 1, which says that the exposure and the outcome are not independent. The p-value of 0.001 is saying that the hypothesis result has a 0.001 probability of occurrence. This value is obviously smaller than 0.05 and 0.01 so with the 95% and the 99% confidence value we can say the exposure and outcome are dependent. The obtained OR value < 1 says that the exposure is associated with a lower outcome. Meaning that if a person was exposed, they have a lower chance of developing the disease. Last of all the 95% CI is stated to be (0.45-0.60), this value, I assume, that on an average case out of 100 people, 95 times out of 100 an exposed person will have a greater chance of an outcome compared to an unexposed person within the interval (Szumilas, 2010). “The 95% confidence interval is used to estimate the precision of the OR” (Szumilas, 2010). The confidence level in this case does not report the measure’s statistical significance. It is, however, inappropriate to interpret an OR with a 95% CI, because it is a lack of association between the exposure and outcome.

- Discuss some of the methodological limitations of the case-control study design.

A case control study according to Hummelfarb Library is “a study that compares patients who have a disease or outcome of interest (cases) with patients who do not have the disease or outcome (controls), and looks back retrospectively to compare how frequently the exposure to a risk factor is present in each group to determine the relationship between the risk factor and the disease” (Hummelfarb Science Library, 2011). With this being said, a case control study is one of the easiest tools to use to check for the interdependency of exposure cases to disease cases. Some of the methodological advantages of a case control study are as follows:

- This is a good design for studying rare diseases
- There is less time needed to do the study as the disease has already occurred
- Let’s you look at multiple risk factors at the same time
- Useful initiation studies to establish an association
- Can answer rough questions that cannot be readily answered through other design studies (Himmelfarb Library, 2011).

Limitations are as follows:

- Retrospective studies have bigger problems with data quality due to human memory error
- This is not good for evaluation of control testing as it is evidently clear that the disease group has the disease and the controls do not
- Difficulty finding a control group to run the testing on (Hummelfarb Library, 2011).
- This type of study only allows for one outcome and this would not be a suitable situation for studying more than one outcome.
- This is a process that works with data already obtained and is not suitable for current data gathering. This is not good for incidence data gathering.
- This is not a good tool for validity purposes
- The selection bias actually exists higher in this type of tool than in other types of tools because one is actually selecting the participants based on risk factors or a certain disease.
- It cannot be used in any case where follow up is needed.

Obviously some of the advantages and limitations can vary from one study to the next. This type of study is best used in tracking disease that have already occurred.

References

Michigan Center for Public Health. (n.d.). Odds ratio. Retrieved from http://practice.sph.umich.edu

Freedman, D. Michal; Looker, Anne C; Chang, Shih-Chen; Graubard, Barry L. (n.d.). Prospective study of serum vitamin D and cancer mortality in the United States. Retrieved from http://www.luzimarteixeira.com

Szumilas, Magdalena. (2010). Explaining odds ratios. J Can Acad Child Adolesc Psychiatry. 2010 Aug; 19(3): 227-229. Retrieved from http://www.ncbi.nlm.nih.gov

Himmelfarb Health Sciences Library. (2011). Case control study. Retrieved from https://himmelfarb.gwu.edu