HLT-362V-O503 Topic 5 Summary and Descriptive Statistics GCU
Table showing statistics from the National Cancer Institute on lung and bronchus cancer cases across ethnicities.
The table above outlines the number of lung and bronchus cancer cases across various ethnicities per 100,000 people. Analyzing the data using measures of central tendency, the group with the highest average cases is the Blacks with 70.06875, followed by whites with 62.75 cases, American Indians follow with 43.28, the Asian Pacific Islanders are next with 38. 51 cases and the group with the least cases is the Hispanic group with 31.49 (Yadav, Singh & Gupta, 2019; NCI,2018). The median also projects a similar trend with the Blacks leading and the Hispanics coming last. In terms of occurrence of a similar number of cases across the years, it’s only Pacific Islanders, Hispanics and Whites who have more than one similar number of cases. The Pacific Islanders have 36.6 cases in 2011 and 2013, Hispanics had 34.1 cases in 2001 and 2002 while Whites had 65.8 cases in 2004 and 2006.
Analysis of the data using measures of variation offers deeper insights (Deshpande, S., Gogtay, & Thatte, 2016). For instance, the number of lung and bronchus cancer cases among Pacific Islanders and Hispanics has not fluctuated much but rather seems to occur within a close range across years because their Variance is 5.68 and 8.40 respectively. However, the number of cases among Blacks indicates a downward trend with cases reducing from 77.8 in 2000 to 57.4 in 2015. The Blacks, therefore, have a high variance score which is 45.42. The number of cases among American Natives has also reduced since their variance score is equally high at 27.72, followed by Whites whose variance is 26.162. The trend is also similar looking at the standard deviation since a figure close to zero indicates low dispersion from the mean, while a higher number indicates highly variables data. the standard deviation is higher among blacks at 6.74, followed by American Natives at 5.26, whites at 5.11, Hispanics at 2.90 and lastly Pacific Islanders at 2.38.
Deshpande, S., Gogtay, N. J., & Thatte, U. M. (2016). Measures of central tendency and dispersion. Journal of the Association of Physicians of India, 64, 64-66.
National Cancer Institute (2018) Lung and bronchus cancer. Retrieved from January 8, 2019, from https://seer.cancer.gov/explorer/application.php?site=47&data_type=1&graph_type=2&compareBy=race&chk_sex_1=1&chk_race_5=5&chk_race_4=4&chk_race_3=3&chk_race_6=6&chk_race_2=2&chk_age_range_1=1&chk_data_type_1=1&advopt_precision=1&advopt_display=1&showDataFor=sex_1_and_age_range_1_and_data_type_1
Yadav, S. K., Singh, S., & Gupta, R. (2019). Measures
Topic 3 DQ 2
Aug 29-Sep 2, 2022
Evaluate and provide examples of how hypothesis testing and confidence intervals are used together in health care research. Provide a workplace example that illustrates your ideas.
REPLY TO DISCUSSION
To understand how hypothesis testing and confidence intervals (CI) work together we must first understand what exactly they are. Hypothesis Tests are tests conducted by forming two opposing hypothesis (Research HA and Null Ho) and attempting to validate each in order to reach a possible outcome. Confidence Intervals are a “range of likely values of the parameter with a specified level of confidence (similar to a probability)” (Sullivan, 2022). Both of these are known as inferential methods which both rely on approximated sampling distributions. CI is used to find a range of possible values and an estimate on the overall accuracy of the parameter value. Hypothesis testing is useful because it tells us how confident we can be when drawing conclusions about the parameter of our sample population.
An example of this is testing the overall performance of a new medication being offered at a clinic. One must hypothesise the effect it will have on the patient population and try to find the parameters on the satisfaction of those taking said medication. By using these two methods in conjunction, the provider can have a good educated guess on the outcome and prepare accordingly.
Sullivan, L. (2022, January 1). Confidence Intervals. Retrieved from Boston University School of Public Health: https://sphweb.bumc.bu.edu/otlt/mph-modules/bs/bs704_confidence_intervals/bs704_confidence_intervals_print.html
The hypothesis is a question the researcher would like to answer. A hypothesis drives a better outcome for patient care that goes evidence-based practice. The person must collect data in a controlled manner designated best to test the hypothesis. When using the Null hypothesis as current information, the alternative hypothesis attempts to reject the null. At the same time, the Ho and the Ha are mathematic opposites. Clinical significance is the application in improving the quality of life of an individual and provides the bridge from health research to patient care (Ambrose, 2018).
While confidence intervals and hypothesis tests are similar, they contain inferential methods relying upon sampling. The LOC is a percentage of confidence level in deciding the difficulty of rejecting the hypothesis. Most people doing this research are > 90% LOC; otherwise, the test would not be warranted. The level of significance is α=1-c. Both the LOC and level of relevance reflect how sure you are of whether the data is making the correct decision or not.
The American Heart Association guidelines for resuscitation were based on the pneumonic of ABC- Airway, Breathing, and Circulation. The pneumonic is the null hypothesis. The alternative view was the use of Circulation, airways, and breathing. The research data reflected the Ha > Ho. The concentration of effective quality chest compressions leads to a worldwide change in how CPR is performed. The LOC was high enough to recruit large city Fire Dept such as Phoenix Fire to provide data regarding cardiac arrest and outcomes.