Reply 1 and 2 , 150 words each one add references by 10/24 /2020 at

Reply 1

Hypothesis testing involves using statistics by analysts or researchers to determine the strength or weakness of an assumption on a resident’s parameter (Shreffler & Huecker, 2020). On the other hand, a confidence interval is a measure of statistics that offer a range of values, upper and lower limits, that can be plausible to a particular population. Confidence intervals use CI to show the upper and lower limit; hence a 90% CI would indicate that if that research undertaking can be done for up to 100 times, the valid values will be 90 (Shreffler & Huecker, 2020). Also, a confidence interval will only show the aptitude of analysis to come up with accurate results, and this can only happen if many intervals are assessed. Notably, the CI width is affected by factors like standard errors and the number of selected participants. Therefore, having a significant CI would indicate that a small sample size was taken. With these two measures of statistics, more evidence on a particular hypothesis is presented. One can develop a research hypothesis, and the confidence interval determines the inclusion or exclusion of significant values in medicine (Shreffler & Huecker, 2020).

In a hospital, doctors decided to test the effectiveness of two medicines, drug A and drug B. The hypothesis was that drug A was much more effective than drug B. The healthcare professionals then undertook to assess this hypothesis’s truthfulness by researching on patient’s response to these two medications. In 4.2 days, those who took drug A indicated much faster healing than those who took drug B, with p= 0.009. hence, (95% CI: 1.9-7.8). This means that drug A was more effective than drug B; thus, the hypothesis stands, and also, with the big CI range, the results can be extrapolated to a larger population.

References

Shreffler, J., & Huecker, M. R. (2020). Hypothesis Testing, P Values, Confidence Intervals, and Significance. In StatPearls [Internet]. StatPearls Publishing.

Reply 2

As defined by Ambrose (2018):

• Hypothesis: A testable statement of a relationship; an epidemiologic hypothesis is the relationship is between the exposure (person, time, and/or place) and the occurrence of a disease or condition.
• Confidence Interval (CI): The range of values around the statistic within a population parameter, at a specific parameter. The 95% confidence interval is the specified probability (Ambrose, 2018).

Hypothesis testing and confidence intervals are used together in health care research by making a hypothesis is made of what it thought to happen because of past experience and then the confidence interval is tested with specific parameters and the estimation that it will happen within a certain percentage if tested over and over again, usually within 95%. The larger the sample, the narrower the results should be as there should be less room for error.

Some examples are (1) testing how fast one medication works in comparison to another, (2) susceptibility of lifestyle depending on family history, or (3) the chances of having a hereditary disease.

1. From Shreffler & Huecker (2020):

Individuals who were prescribed Drug 23 had no symptoms after three days, which was

significantly faster than individuals who were prescribed Drug 22; there was a mean difference between the two groups of days to the recovery of 4.2 days (95% CI: 1.9 – 7.8). Reporting both hypothesis and CI, individuals who were prescribed Drug 23 had no symptoms after three days, which was significantly faster than individuals who were prescribed Drug 22, p = 0.009. There was a mean difference between the two groups of days to the recovery.

1. There are several variabilities with obesity, but one is family history. “A child with one obese parent has a 50 percent chance of being obese. When both parents are obese, their children have an 80 percent chance of obesity” (Benioff Children’s Hospital, n.d.). Researchers can take one part of their hypothesis to determine the main factor, but this should be a survey that measures multiple factors like food consumption types, physical activity, or family history to name a few. The probability could differ from one community to the next.

An example that could be used within my work would be (3) a family concern of getting schizophrenia because their loved one has it. A study was done to show the probability of getting schizophrenia with a family member who has it within the psych hospital. Statistics from schizophrena.com (n.d.):

• One parent – 10% chance (1% in general population)
• Both parents – approx. 40% chance

Many patients within the psych hospital have schizophrenia along with other disorders (bipolar, depression) that can exacerbate their symptoms of schizophrenia. Clozaril is a commonly used drug to help treat/manage schizophrenia and researchers test the effectiveness by using bloodwork to measure ANC on a specific schedule; statistics can be found at: https://www.accessdata.fda.gov/drugsatfda_docs/label/2010/019758s062lbl.pdf.

Reference

• Ambrose, J. (2018). Applied statistics for health care.Retrieved from https://lc.gcumedia.com/hlt362v/applied-statistics-for-health-care/v1.1/
• Shreffler, J. & Huecker, M. R. (2020). Hypothesis Testing, P Values, Confidence Intervals, and Significance. [Updated 2020 May 6]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; Retrieved from https://www.ncbi.nlm.nih.gov/books/NBK557421/
• com. (n.d.) Frequently asked questions and answers – from sons/daughters. Retrieved from http://schizophrenia.com/family/FAQoffspring.htm#:~:text=While%20this%20may%20be%20true,risk%20in%20the%20general%20population).