HLT 362 Topic 3 DQ 2 Evaluate and provide examples of how hypothesis testing and confidence intervals are used together in health care research

HLT 362 Topic 3 DQ 2 Evaluate and provide examples of how hypothesis testing and confidence intervals are used together in health care research

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.

Great discussion this week, sharing your examples of how hypothesis testing and confidence intervals are used together in health care practice. You also highlighted the criteria we use in rejecting the null hypothesis. In summary, this week we were able to:

  • Evaluate hypothesis testing approaches and their applications to health care.
  • Describe the roles of dependent and independent variables in hypothesis testing.
  • Describe the evidence used to “reject” or “do not reject” the null hypothesis.
  • Evaluate the relationship between hypothesis testing and confidence intervals.

Watch “When Should I Use Qualitative vs. Quantitative Research?” on the YouTube website located at http://www.youtube.com/watch?v=638W_s5tRq8&feature=youtube_gdata to help you understand when you use qualitative and quantitative research in your clinical practice.

This short video was very helpful. Thank you for sharing it.

My understanding of the difference between the use of Qualitative vs. Quantitative research is: Quantitative studies rely on numerical or measurable data. In contrast, qualitative studies rely on personal accounts or documents that illustrate in detail how people think or respond within society. For example, qualitative data is collected by surveys and questionnaires,  interviews, focus groups, and observations just to mention some. Quantitative has a numeral value therefore it is measured in numerical value.

Hypothesis testing and confidence intervals are used together in healthcare research.  A hypothesis is a forecast statement of what will occur between two variables.  The independent and dependent variables are identified in the hypothesis and analyzed with gathered data to show correlations and relationships between variables.  A hypothesis is created when variables are identified.

A confidence interval (CI) is an interval estimate of the mean which is a range of values of the data.  These values are close to the mean in a negative or positive direction.  The CI shows the risks of being wro

HLT 362 Topic 3 DQ 2 Evaluate and provide examples of how hypothesis testing and confidence intervals are used together in health care research

HLT 362 Topic 3 DQ 2 Evaluate and provide examples of how hypothesis testing and confidence intervals are used together in health care research

ng. If the CI reduces the risk of error increases.  A CI of 95% says that 5% of the mean will not be true yet 95% will be a true mean.  (Ambrose, 2018)

A workplace example where the CI is used is a study suggesting that working shift work for long hours during pregnancy can be associated with adverse pregnancy risks.  The study showed that working a fixed night shift measured a CI of 95% with increased odds of miscarrying when compared to standard working hours.  The study also revealed that working rotating shifts revealed a CI of 95% of increasing odds for preterm delivery. (Cai et al., 2019)  Using CIs with multiple variables, this study concluded that pregnant women increase risks of adverse pregnancy outcomes if working rotating shifts, fixed night shifts or longer hours.

I work in a female-dominated industry and department.  I frequently see my pregnant colleagues being placed on alternative duty or light duty while pregnant.  This study concerns me because the “light duty” does not decrease their hours but instead keeps them from working “on their feet” all shift.  It would be interesting to see if these coworkers have increased adverse pregnancies in their work situations.

Ambrose, J. (2018). Applied Statistics for Health Care. Gcumedia.com. https://lc.gcumedia.com/hlt362v/applied-statistics-for-health-care/v1.1/#/chapter/3

Cai, C., Vandermeer, B., Khurana, R., Nerenberg, K., Featherstone, R., Sebastianski, M., & Davenport, M. H. (2019). The impact of occupational shift work and working hours during pregnancy on health outcomes: a systematic review and meta-analysis. American Journal of Obstetrics and Gynecology, 221(6). https://doi.org/10.1016/j.ajog.2019.06.051

Thank you, Kristine, for your post. Confidence intervals are useful when looking at the conclusions of a specified study. They are used to interpret the reliability of the research, whereas the p-value pertains to the statistical significance.

Both confidence intervals and hypothesis tests are inferential methods that depend on a sample distribution that is approximated. Confidence intervals are used to measure a population parameter using data from a survey. Hypothesis experiments are used to test a hypothesis using data from a study. Hypothesis testing necessitates the presence of a parameter that has been hypothesized. A hypothesis test determines whether the outcome is exceptional, whether it is reasonable chance variation, or whether it is too extreme to be considered chance variation.

In health-care science, hypothesis testing, and confidence intervals are used together. This is used as an interval estimation for the mean with confidence interval (CI). A confidence interval (CI) is a set of values that are like the mean and can affect the direction in either a positive or negative way. Means using a procedure that contains the population mean with a defined proportion of the time, usually 95 percent or 99 percent of the time, are given a confidence interval (CI). The CI is the range in which the researcher could be incorrect. A 95% confidence interval indicates that 95% of a research sample will contain the true mean, while the remaining 5% will not. Confidence intervals will help you compare the accuracy of various estimates with this in mind. For example, 95 percent of the data collected in a test survey of 100 participants will be correct, while five out of 100 will be incorrect. If the 95 percent is decreased, the chance of error increases (Ambrose, 2018). Since hypothesis testing and confidence intervals are used together in health care research, this is important to note.

If you wanted to know the mean of temperatures obtained in a hospital with COVID-19 patients, you’d need to think about hypothesis testing and confidence intervals. Since it’s necessary to have a true mean of the temperatures of the sample collected, a CI of 95 percent will be better than a CI of 90 percent for this example. This is because the CI is determined by first determining the sample size, then determining the mean and standard deviation, and finally determining the degree of confidence interval.

It’s crucial to understand analytical quantitative analysis, which requires hypothesis testing and confidence intervals, to produce reliable findings from samples for the populations being studied. This is particularly relevant in health care, where positive outcomes can be established to enhance patient care.


How hypothesis tests work: Confidence intervals and confidence levels. (2019, June 25). Statistics By Jim. https://statisticsbyjim.com/hypothesis-testing/hypothesis-tests-confidence-intervals-levels/

LibGuides: Maths: Hypothesis testing. (2020, May 13). LibGuides at La Trobe University. https://latrobe.libguides.com/maths/hypothesis-testing

More about hypothesis testing. (n.d.). https://bolt.mph.ufl.edu/6050-6052/unit-4/module-12/more-about-hypothesis-testing/

Thank you, Amber, for your post. A 95% confidence interval is a range of values that you can be 95% certain contains the true mean of the population. With a small sample size, the 95% confidence interval is similar to the range of the data. With large samples, which is with more precision than with a small sample, the confidence interval is quite narrow when computed from a large sample.

Hypothesis testing is using multiple statistical tests to determine whether or not an outcome happens by chance or if it is affected by a true effect. A researcher will typically begin their study with the development of a null hypothesis, which essentially assumes there is no difference between sample populations, and it will have no effect on the study. A confidence interval is a range of values that described uncertainty around an estimate (US Census Bureau, 2021). An example of this in practice is that if a researcher has a confidence interval of 95%, it means that there is a 95% chance that the effect of the study will fall within the values provided by the interval.

Both of these are statistical tools that are used in healthcare research to allow researchers to draw conclusions about the effectiveness of treatments or other related interventions. When conducting these studies, it is important to assess the magnitude of the effect when using confidence intervals. A wide confidence interval means that the estimate will be less precise and there is more uncertainty, whereas if the confidence interval is narrow, it means that the clinical significance is greater.

An example of these is if a researcher is evaluating the effectiveness of a new drug. They will start by developing a null hypothesis which will have no effect on the outcome of the study but will provide a foundation for the direction of the study. If the researcher predicts a narrow confidence interval and it is accurate, this will provide more clinical significance to their study. Hypothesis testing and confidence intervals both use the same underlying methodology to prove or disprove an outcome in statistical testing (Frost, 2022).


Bureau, U. S. C. (2021, October 8). A basic explanation of confidence intervals. Census.gov. https://www.census.gov/programs-surveys/saipe/guidance/confidence-intervals.html#:~:text=A%20confidence%20interval%20is%20a,the%20uncertainty%20surrounding%20an%20estimate.

Frost, J. (2022, March 17). Hypothesis testing and confidence intervals. Statistics By Jim. https://statisticsbyjim.com/hypothesis-testing/hypothesis-tests-confidence-intervals-levels/

Hypothesis testing and confidence intervals are significant contributors to evidence-based practice and guide the protocols of patient intervention, ultimately influencing patient outcomes. Hypothesis testing can be employed to correlate associations between variables, which leads to quality improvement and supports improvements to standard practice. However, it is the role of nursing leadership to responsibly interpret research and apply it for the improved patient outcomes (Ambrose, 2021). Confidence intervals represent the risk that the research could be wrong. The combined use of hypothesis testing with confidence intervals allows for results to be extrapolated and applied to the general population. While the confidence interval can be important in applying the research results from the sample to the population, it is important to be aware of the ability to manipulate the confidence interval if thorough methods are not employed. Small sample size and lack of replication are both contributing factors to misinterpreted p-values or statistical significance.

In the example of a 2019 study by Henson et al., the authors compared select outcomes associated with postoperative analgesic approaches in patients undergoing TKA. The two approaches were femoral nerve blocks and periarticular injections. Using 2-tailed t tests, the researchers examined pain perception, use of opioid analgesics, length of stay and total cost of care. Additionally, they examined readmission rates using a 2-sample z test for proportions. With a stratified population sample of 144 patients, the authors found an association between patients who received an FNB with a lower pain perception (p = .0497). Results also showed a possible correlation between a decrease in opioid consumption in those who received a PAI (p = .037). By calculating the mean, along with the standard deviation of the five selected variables, the authors were able to gain data regarding reported decrease in pain, it is clear that the study needs further replication with additional factors examined (Henson, et al., 2019). However, studies like this set the groundwork for future studies to build upon and gain even more in-depth knowledge regarding the topic or practice at hand.


Ambrose, J. (2021). Clinical inquiry and hypothesis testing. In Grand Canyon University (Ed.). Applied statistics for health care (ch.3). https://bibliu.com/app/#/view/books/1000000000581/epub/Chapter3.html#page_31

Henson, K. S., Thomley, J. E., Lowrie, L. J., & Walker, D. (2019). Comparison of Selected Outcomes Associated with Two Postoperative Analgesic Approaches in Patients Undergoing Total Knee Arthroplasty. AANA Journal87(1), 51–57.