In Torabi et al. (2016) article, researchers evaluate the operational policies that may improve the proportion of eligible stroke patients within a population that would acquire intravenous recombinant tissue plasminogen activator and reduce time to treatment among eligible patients. In doing so, the study employed a Monte Carlo simulation to examine two primary factors of interest. The first factor was the availability of telemedicine in various hospitals. In examining the first factor, three deployment policies, including no telemedicine in the region, telemedicine in all hospitals throughout the region, and telemedicine only in outer-ring hospitals, were considered. The second factor was the location of the stroke team physicians while on call. Various probability distributions, including Weibull, Gamma, Triangular, and Uniform Distribution, were used depending on the variable in question.
Weibull distribution falls under the continuous probability distribution category. It is one of the widely known lifetime distributions ( Shakhatreh et al., 2019 ). It is best used in reliability and survival analysis. In the study conducted by Torabi et al. (2016), the Weibull distribution is used on two occasions. Two variables, namely the Recognition time duration and the EMS patient prep time duration, have Weibull as its best-fit probability density function. Since the variables are continuous data, the Weibull distribution is a perfect choice for the continuous probability distribution.
Delegate your assignment to our experts and they will do the rest.
Gamma distribution, on the other hand, is the preferred distribution when one wants a right-skewed distribution of nonnegative quantity. The right-skewed distribution of nonnegative values is particularly useful for many quantities, such as the lifetime of an appliance ( Albright et al., 2017 ). One only needs the mean and the standard deviation to successfully calculate the parameters of a gamma distribution. Torabi et al. (2016) uses gamma distribution in the analysis of three variables, namely the Call ambulance duration, Patient handover duration, and the duration from CT order to reading. These three variables form parts of a queuing model often used in hospitals. One of the applications of the gamma distribution is the queuing models.
The triangular distribution has many similarities to the normal distribution in terms of its density function, which increases to a given point before taking a decreasing trend ( Albright et al., 2017 ). However, a triangular distribution is more flexible and intuitive that the normal distribution. Therefore, triangular distribution is a quality option for most continuous input variables. The triangle distribution is specified by three parameters, including the maximum possible value, the minimum possible value, and the most likely value ( Albright et al., 2017 ). This is the widely used probability distribution, with various input variables, including the Bedside prep duration, the Pharmacy prep duration, additional tests and evaluations, telemedicine set-up time duration, and the ED triage time duration. All input variables are continuously distributed with the minimum, maximum, and modal values, and thus making the triangular distribution a viable option.
Tobari et al. (2016), has also used uniform distribution for one of its input variables. A uniform distribution is bounded by a minimum and a maximum value. All values that lie in between have equal chances of occurring. This distribution is applicable where research knows the range of the expected outcome but is uncertain about the exact values of the result ( Albright et al., 2017 ). In the study, the researcher employed uniform distribution to examine the delay in calling the stroke team after patient arrival. The hospitals might know the fastest time it can take the stroke team to respond and the maximum possible delay that might occur. However, the researchers do not know the expected delay times between the minimum and the maximum delay and thus making this option a viable one.
References
Albright, C., & Winston, W. (2017). Business Analytics: Data Analysis and Decision Making. 6 th Ed. Cengage Learning.
Shakhatreh, M. K., Lemonte, A. J., & Moreno–Arenas, GE-200802202515. (2019). The log-normal modified Weibull distribution and its reliability implications. Reliability Engineering & System safety , 188 , 6-22.
Torabi, E., Froehle, C. M., Lindsell, C. J., Moomaw, C. J., Kanter, D., Kleindorfer, D., & Adeoye, O. (2016). Monte Carlo simulation modeling of a regional stroke team's use of telemedicine. Academic Emergency Medicine , 23 (1), 55-62.
