Presented in full: an IHP 340 Module 5 short paper testing whether check-in kiosks reduced outpatient lab wait times, with hypotheses, assumptions, a two-sample t test (t = 3.85, p < .001), a confidence interval, Cohen's d, limitations and a recommendation. Searches like "ihp 340 module 5 assignment", "ihp340 module 5 hypothesis testing short paper" and "ihp 340 module 5 example" land here.
The IHP 340 Module 5 example, in full
Did the Kiosks Cut the Wait? A Two-Sample Hypothesis Test of Outpatient Laboratory Wait Times
[Student Name]
Southern New Hampshire University
IHP 340: Statistics for Healthcare Professionals
Module Five Short Paper
[Instructor Name]
[Date]
The organization, setting and figures below are a composite written as a model document. No real employer, client, colleague or patient is described.
Did the Kiosks Cut the Wait? A Two-Sample Hypothesis Test of Outpatient Laboratory Wait Times
The Question
A composite hospital outpatient laboratory draws blood for about 300 patients a day. Patients used to check in with a registration clerk, who verified identity, insurance and orders before sending them to the waiting area. Six months ago, the lab installed three self check-in kiosks that scan a driver's license and insurance card and print a queue ticket. The laboratory manager wants to know whether the kiosks reduced the time from arrival to blood draw. To answer, the lab timed a random sample of 20 visits during the month before installation and 20 visits during the fifth month after installation, on comparable weekday mornings.
Hypotheses and Significance Level
The null hypothesis is that the mean wait time after installation equals the mean wait time before installation. The alternative hypothesis is that the mean wait times differ. A two-sided alternative was chosen, even though the lab hoped for a reduction, because the kiosks could also have lengthened waits if patients struggled with them. An alpha of .05 was fixed in advance, before any wait times were examined.
The Data
The table summarizes the two samples.
Table 1
Wait Time From Arrival to Blood Draw Before and After Kiosk Installation
| Statistic | Before kiosks | After kiosks |
|---|---|---|
| Number of visits | 20 | 20 |
| Mean wait (minutes) | 27.6 | 21.4 |
| Standard deviation (minutes) | 5.8 | 4.4 |
| Median wait (minutes) | 27 | 21 |
| Range (minutes) | 18 to 40 | 14 to 30 |
Choosing the Test and Checking Assumptions
Because the two samples contain different patients and the outcome, minutes of waiting, is a ratio-level variable, an independent-samples t test is appropriate (Daniel & Cross, 2018). The test assumes that observations are independent, that each group is approximately normally distributed and, for the pooled version, that the variances are similar. The visits were sampled randomly on different days, so independence is reasonable. In each group the mean and median are close and the data show no extreme outliers, suggesting approximate normality. The standard deviations, 5.8 and 4.4 minutes, differ somewhat, so the result was also checked with the Welch version of the test, which does not assume equal variances.
Results
The mean wait fell from 27.6 minutes before the kiosks to 21.4 minutes after, a difference of 6.25 minutes. The pooled independent-samples t test gave t = 3.85 with 38 degrees of freedom and p < .001. The Welch test gave the same conclusion, t = 3.85 with about 35 degrees of freedom and p < .001. Because the P value is far below .05, the null hypothesis is rejected. If the kiosks truly made no difference, a gap between sample means this large would occur by chance less than one time in a thousand.
Around the 6.25-minute difference, the 95 percent interval stretches from 3.0 to 9.5 minutes. The reduction could plausibly be as small as 3 minutes or as large as 9.5, but it is unlikely to be zero. The effect size, Cohen's d, is 1.22, which is large by conventional guidelines, where 0.8 or above is considered large (Sullivan & Feinn, 2012).
The Risk of Error
Every hypothesis test carries a risk of a wrong decision. A Type I error would mean rejecting the null hypothesis when the kiosks actually made no difference; the significance level of .05 caps that risk at 5 percent before the data are seen, and the very small P value here makes such an error unlikely. A Type II error would mean failing to detect a real improvement. With only 20 visits per group, the lab would have had limited ability to detect a small reduction of one or two minutes, so a nonsignificant result would not have shown that the kiosks failed. In this case the effect was large enough to be detected, but the lab should remember that a small sample favors finding only large effects.
What the Difference Means in Practice
Translating the result into operational terms helps the manager judge its value. If the average saving of about 6 minutes applied to all 300 daily patients, the lab would remove roughly 1,875 patient-minutes of waiting each day, a little over 31 hours. Using the lower end of the confidence interval, 3 minutes, the saving would still be about 15 hours of patient time daily. Even the conservative estimate represents a meaningful improvement in patient experience and waiting room crowding, which is why the effect size matters more to the decision than the P value.
What the Test Does Not Prove
A significant result does not prove that the kiosks caused the reduction. This is a before-and-after comparison, not a randomized experiment. Other things changed during those months as well: the lab hired one additional phlebotomist three months ago, and fewer patients may have arrived in the later month. The P value also says nothing about whether the difference matters; that judgment comes from the size of the effect. The American Statistical Association has cautioned that conclusions should not rest on a P value alone and that effect sizes and study design must be considered (Wasserstein & Lazar, 2016). Here the effect is large and practically meaningful, but its cause is not fully established.
Recommendation
The results support keeping the kiosks and suggest they are contributing to shorter waits. To separate the effect of the kiosks from staffing changes, the lab could compare wait times on days when the kiosks are down for maintenance with similar days when they are working, and track patient-level check-in times, which would show whether the time saved occurs at check-in, where the kiosks act, or later in the process. Patient satisfaction and any difficulties among older patients using the kiosks should also be monitored, because a faster average could hide longer waits for patients who need help.
Conclusion
An independent-samples t test on 40 timed visits found that mean wait from arrival to blood draw fell by about 6 minutes after the kiosks were installed, a statistically significant and large difference with a 95 percent confidence interval of 3.0 to 9.5 minutes. The design cannot rule out other causes, so the finding supports keeping the kiosks while the lab gathers evidence that isolates their effect.
References
Daniel, W. W., & Cross, C. L. (2018). Biostatistics: A foundation for analysis in the health sciences (11th ed.). Wiley.
Sullivan, G. M., & Feinn, R. (2012). Using effect size, or why the P value is not enough. Journal of Graduate Medical Education, 4(3), 279-282. https://doi.org/10.4300/JGME-D-12-00156.1
Wasserstein, R. L., & Lazar, N. A. (2016). The ASA statement on p-values: Context, process, and purpose. The American Statistician, 70(2), 129-133. https://doi.org/10.1080/00031305.2016.1154108
How this IHP 340 Module 5 example is structured
Hypothesis testing follows a fixed sequence, and the paper uses it as its structure. After the question, it states null and alternative hypotheses and the significance level. The data are summarized in a table, and assumptions are checked before the test is chosen. The test result is reported with the P value, then the confidence interval and effect size show how large the difference is. The paper closes by explaining the limits of a before-and-after comparison and making a recommendation that matches the evidence.
Get IHP 340 Module 5 written to your instructions
Send your IHP 340 Module 5 prompt, rubric and data or output. A hypothesis testing paper written around your numbers comes back within 24 to 48 hours, and the first is free. The paper above is an original model document written by our desk, not a submitted student paper and not an official Southern New Hampshire University document.
IHP 340 Module 5 questions, answered
What does IHP 340 Module 5 usually cover?
Mid-course modules in healthcare statistics typically cover hypothesis testing: stating null and alternative hypotheses, choosing a significance level, selecting a test, interpreting a P value and deciding whether to reject the null hypothesis, often applied to a healthcare scenario in a short paper.
What is the difference between the null and alternative hypothesis?
The null hypothesis states that there is no effect or no difference, such as mean wait time is the same before and after a change. The alternative states the effect the researcher is looking for, such as mean wait time is lower after the change. The test assesses whether the data are inconsistent enough with the null to reject it.
Why report an effect size as well as a P value?
A P value indicates how surprising the observed difference would be if nothing had changed, but with a large sample even tiny differences can be significant. An effect size, such as the difference in minutes or Cohen's d, shows how large the difference is, which is what a manager needs to judge whether it matters.