stst-discusion and response-04
Jambo
Discussionandresponse_04.docx
Stating the null and alternative hypotheses correctly is crucial to using data to answer health questions. But is there only one correct way to define the null and alternative hypotheses to address the health question you are studying? Why or why not?
Response one
To what extent does gender influence length of hospital stay for MI patients?
This is probably the question of the majority of us and I would like to think the easiest way to answer this discussion would be to say that of course there is only one correct way to define null and alternative hypotheses to address this question. I mean, either gender influences the length of stay or it doesn't. "The null and alternative hypotheses are set up in such a way so that one or the other must be true and the other must be false." (Gerstman 2015) However, in Chapter 9 we discuss zstat and standard error; changing the zstat to a P value; all of these statistics and probabilities we are learning will put us one step closer to finding out if there is the possibility of influence at the slightest or none at all. Our questions in the Problem Set kind of set the tone for which hypotheses will be true and which one will be false.
Version:1.0 StartHTML:000000197 EndHTML:000031760 StartFragment:000031534 EndFragment:000031722 StartSelection:000031534 EndSelection:000031722 SourceURL:https://mbsdirect.vitalsource.com/
Gerstman, B. B. Basic Biostatistics, 2nd Edition. Jones & Bartlett Learning, 2015. [MBS Direct].
Response two
To what extent does gender influence length of hospital stay for MI patients?
I invite any responses to help me correctly answer this question but in regards to my question, there are two ways to define the hypothesis because there are two genders that affect the length of hospital stay for MI patients. Although the question doesn't claim that one particular gender influences the length of hospital stay by more or less days, it does however claim to ask if any one gender influences the length of hospital stay. With that, I can say that the null hypothesis for male patients are equal to female patients in regards to length of hospital stay; same goes for the woman patients. The alternative hypothesis for both the male and the female data on length of hospital stay would be two-sided.
Response three
The null and alternative hypotheses theories are as follows. “The null hypothesis (Ho) is a statement of “no difference”. The alternative hypothesis (Ha) contradicts the null hypothesis”. (Gerstman, 2015). When applying this to a research question, like the ones we picked, you can rephrase it to a statement such as; males have longer hospital stays after an MI than females. That is what we are trying to prove by finding a statistically significant correlation. The null hypothesis would be; men and women have the same length of stay at the hospital post MI. The alternative hypothesis would be the opposite; men have longer hospital stays post MI. To correlate a connection between gender and LOS for MI patients we must find a statistically significant relationship. There are 3 possible conclusions. The Ho=Ha, The Ho>Ha or Ho<Ha. (Rumsy, 2016.) In the case of my research question the answers could be; men and women have the same LOS post MI, men have longer LOS post MI or women have longer LOS post MI.
References
Gerstman, B. B. (2015). Basic biostatistics: Statistics for public health practice. Burlington, MA: Jones & Bartlett Learning.
Rumsey, D. J. (2016). How to Set Up a Hypothesis Test: Null versus Alternative. Retrieved August 8, 2018, from https://www.dummies.com/education/math/statistics/how-to-set-up-a-hypothesis-test-null-versus-alternative/
