1. In the video scientific variables Dr. Koning explains scientific variables to Jacob using an example (i.e., how much plants grow based on how much water they get). Is Dr. Konings experiment an example of a correlational study or of causal study? Why?
Example:
How can you tell the difference between causation and correlation? Causation occurs when you have direct evidence that a change in one variable causes a change in another variable. For example, administering blood pressure medication (e.g., Losartan) to a patient with high blood pressure will reduce their blood pressure. In the previous example, a change in medication (one variable) caused a change in another variable (blood pressure). In some cases, you cannot definitively determine if a change to one variable was the direct cause of a change to another variable, in this case, you may have a correlation. For instance, a patient with high blood pressure takes some time off from their high-stress job and goes on a vacation. When the patient returns from vacation, their blood pressure is reduced. Did the vacation directly cause a reduction in blood pressure? Perhaps, but there is not enough evidence to prove a causal link between the vacation and the reduction in the patients blood pressure. In other words, there is only a correlation (i.e., a significant relationship) between the vacation and a reduction in the patients blood pressure. To determine if a causal between two variables exists, it is important for the researcher to be able to control all variables. Typically, this control can only occur in a laboratory environment (Fuhlbrigge, 2018).
Reference
Fuhlbrigge, A. L. (2018). Correlation or Causation? The Journal of Allergy and Clinical Immunology: In Practice, 6(1), 114-115. doi:https://doi.org/10.1016/j.jaip.2017.09.017
Replies
Reply
2. Why is it important for researchers to eliminate significant outliers from their data before running a statistical test? Would the impact of a significant outlier be the same on a small dataset N = 20 and a large dataset N = 1,000,000? Why or why not? N = the sample size, or the number of people in your dataset. Use the terms variance and normality in your response.
Example: An outlier is a data point that is apart from most other data points, assuming that you have a normally distributed dataset. The presence of significant outliers in a data set can impact a researchers interpretation of the data. Consider how the mean of a dataset is calculated. All the data points are added together and divided by the number of data points. Say that a researcher wanted to calculate the average amount of money that a person has in her purse. The researcher has a sample of 5 people count the amount of money they are carrying in person: $10, $10, $40, $250, $30. The presence of an outlier can impact the researchers interpretation, for example, based on this dataset, the researcher may conclude that the average amount of money people carry with them is $68 (($10 + $10 + $40 + $250 + $30)/5). Is this amount of money really representative of the sample? If the outlier is removed from the calculation, the average amount of money people carry with them is $22.50 (($10 + $10 + $40 + $30)/4), a more representative, or accurate description, of the sample (Schiff et al., 2017).
Reference
Schiff, G. D., Volk, L. A., Volodarskaya, M., Williams, D. H., Walsh, L., Myers, S. G., . . . Rozenblum, R. (2017). Screening for medication errors using an outlier detection system.Journal of the American Medical Informatics Association. doi:10.1093/jamia/ocw171
Use the order calculator below and get started! Contact our live support team for any assistance or inquiry.
[order_calculator]