Hi everyone! I've been working on my animation skills lately and made a new version of this tutorial with some animation and plotting (although I'm still gonna leave this old version up). Here's the new version if you want to check it out: th-cam.com/video/7uaQX76e4EI/w-d-xo.html Thanks for watching and let me know if you have any questions! 🙂
Hi Yaroslav! I'm not sure if I exactly understand your question. But both types of models could include a threshold if you want them to, or could not. With a determinstic model, the results will either cross the threshold or not cross it every time for a given set of parameters and initial conditions. However for a stochastic model, the results might cross it sometimes and not cross it other times, even for the same parameters and initial conditions.
Thanks Mike for this informativ video. I am interested in Modeling and simulation in health care as a help tool in decision making. do you have date about the benefit of it especially from financial point of view ? many Thanks in advance
Hi Mohamed, thanks for watching! Yes I think these modeling techniques can be used for optimizing healthcare systems. This isn't my current area of research, but I've seen some papers that attempt to use modeling and simulation to figure out how to maximize efficiency in healthcare. Here's one example of a paper about this: journals.sagepub.com/doi/full/10.1177/0037549718776765 I hope that helps! Good luck with your research!
Hi Mike. Thanks for this video! I'm delving into actuarial software tools for work and know that insurance actuaries have traditionally used deterministic models for reserving (setting aside assets to ensure they have the money to pay a life insurance claim 20 years down the road, for example). Many are now supplementing this with stochastic modeling as the computing power becomes available. I'm trying to understand the difference in practice. Surely the models they've always used would give them likelihoods of a person with a given set of starting conditions dying in a certain period? Is the advantage of stochastic that it allows greater insights into tail risks? Any help you can provide would be much appreciated!
Hey Charles, that's a good question! So just to give a disclaimer, I really don't know anything about actuarial science so I'm kinda just guessing here. But I think you could be right about it providing greater insight into tail risks. With deterministic models, there is only one possible result for a given set of initial conditions. But for a stochastic model, if you run it several times, you will get a distribution of results, even for the same initial conditions. So you can model not only the average/expected outcome, but also how variable it is, how wide the tails are, whether it follows a normal distribution, multi-modal distribution, or something else, and generally how much risk there is of deviation away from the average outcome. Another possible use of stochastic modeling is if the initial conditions themselves are uncertain and need to be chosen probabilistically for the model. For example, maybe you have a health insurance model where some of the some of the inputs are whether the person is a smoker, how much alcohol they drink, how much they exercise, etc. But these things might not be known for everyone, so it may be necessary to choose these inputs randomly and run the model many times to get a distribution of the results. Anyway like I said I don't know anything about actuarial science and am guessing here, but I think there's also some good information on Wikipedia about this from people more knowledgeable than me: en.wikipedia.org/wiki/Stochastic_modelling_(insurance)#Stochastic_modelling Hope that helps! Thanks for watching!
Hi everyone! I've been working on my animation skills lately and made a new version of this tutorial with some animation and plotting (although I'm still gonna leave this old version up). Here's the new version if you want to check it out:
th-cam.com/video/7uaQX76e4EI/w-d-xo.html
Thanks for watching and let me know if you have any questions! 🙂
Great video! The terms are intimidating and technical, but your breakdown is extremely clear and concise. Perfect for students.
Thanks for watching Sam 🙂
Thank you! Simple, straightforward and I understand it!
Thanks for watching!
this is an excellent illustration of the 2 models. Thanks
Thanks for watching, and let me know if you have any questions!
simple and good explain
Thanks for watching Ali! 🙂
Is there a threshold in the both models ?
Hi Yaroslav! I'm not sure if I exactly understand your question. But both types of models could include a threshold if you want them to, or could not. With a determinstic model, the results will either cross the threshold or not cross it every time for a given set of parameters and initial conditions. However for a stochastic model, the results might cross it sometimes and not cross it other times, even for the same parameters and initial conditions.
@@MikeSaintAntoine thank you Mike!
Thanks Mike for this informativ video. I am interested in Modeling and simulation in health care as a help tool in decision making. do you have date about the benefit of it especially from financial point of view ? many Thanks in advance
Hi Mohamed, thanks for watching! Yes I think these modeling techniques can be used for optimizing healthcare systems. This isn't my current area of research, but I've seen some papers that attempt to use modeling and simulation to figure out how to maximize efficiency in healthcare. Here's one example of a paper about this:
journals.sagepub.com/doi/full/10.1177/0037549718776765
I hope that helps! Good luck with your research!
@@MikeSaintAntoine many thanks Mike
Hi Mike. Thanks for this video! I'm delving into actuarial software tools for work and know that insurance actuaries have traditionally used deterministic models for reserving (setting aside assets to ensure they have the money to pay a life insurance claim 20 years down the road, for example). Many are now supplementing this with stochastic modeling as the computing power becomes available. I'm trying to understand the difference in practice. Surely the models they've always used would give them likelihoods of a person with a given set of starting conditions dying in a certain period? Is the advantage of stochastic that it allows greater insights into tail risks? Any help you can provide would be much appreciated!
Thanks
Hey Charles, that's a good question! So just to give a disclaimer, I really don't know anything about actuarial science so I'm kinda just guessing here. But I think you could be right about it providing greater insight into tail risks. With deterministic models, there is only one possible result for a given set of initial conditions. But for a stochastic model, if you run it several times, you will get a distribution of results, even for the same initial conditions. So you can model not only the average/expected outcome, but also how variable it is, how wide the tails are, whether it follows a normal distribution, multi-modal distribution, or something else, and generally how much risk there is of deviation away from the average outcome.
Another possible use of stochastic modeling is if the initial conditions themselves are uncertain and need to be chosen probabilistically for the model. For example, maybe you have a health insurance model where some of the some of the inputs are whether the person is a smoker, how much alcohol they drink, how much they exercise, etc. But these things might not be known for everyone, so it may be necessary to choose these inputs randomly and run the model many times to get a distribution of the results.
Anyway like I said I don't know anything about actuarial science and am guessing here, but I think there's also some good information on Wikipedia about this from people more knowledgeable than me:
en.wikipedia.org/wiki/Stochastic_modelling_(insurance)#Stochastic_modelling
Hope that helps! Thanks for watching!
@@MikeSaintAntoine Thanks Mike! Excellent point about the uncertain initial conditions! I hadn't thought about that aspect.
Apt. Thank you
Thanks for watching!
Thank you!
Thanks for watching, Liliana!