Chawarat Rotejanaprasert

Great question!

The choice between AI/ML models and traditional statistical models really depends on your research objective.

If your goal is prediction, AI and machine learning models are usually preferred (also depending on the prediction range as well) because they typically offer better predictive performance, even when the underlying…[Read more]

Hi Aung Thura Htoo,

Yes, in this case, “fever days” is modeled as having an influence on the dengue outcome, along with other possible factors. This reflects our assumption that the number of days with fever is an important observable indicator that can help inform the diagnosis. That said, I’d like to emphasize that the structure of the DAG (…[Read more]

Great question Chanapong!

In Bayesian networks, the direction of the arrows represents causal or probabilistic influence. In this case, the dengue infection is what causes changes in lab values, eg. NS1 or WBC, not the other way around. So, rather than lab abnormalities causing dengue, it’s the dengue infection that leads to those a…[Read more]

Hi everyone,

I understand that there may be some concerns about finding a partner for the assignments. Please don’t worry — there’s flexibility! If you prefer to work on your own for Module 1, that’s absolutely fine. But if you’d like to team up with a peer, you’re welcome to continue working in pairs.

To help with that, I’ll sent an email s…[Read more]

Great discussions! The connection between spatial epidemiology and communicable diseases is well established. In this class, I’d like you to further explore the intersection between spatial epidemiology and non-communicable diseases. Mental health issues, for instance, have been on the rise, especially following the COVID-19 pandemic. For the…[Read more]

The main task of the ‘maptools’ package is to use the function ‘readShapePoly’ to read a shapefile. If you encounter issues with ‘readShapePoly’ or the ‘maptools’ package, there are alternative packages and functions you can try. For instance, you can use the ‘shapefile’ function from the ‘raster’ package. Additionally, you can download the ‘m…[Read more]

Hello all,

The provided R code should work if all data and packages are downloaded properly. I suggest carefully checking the code, including spelling, packages,inputs, and data. If anyone can’t use the function ‘readShapePoly’, there are other functions you can try. Alternatively, you can try the ‘shapefile’ command in the ‘raster’ package.

Thank you for your comment, Soe Htike. You’ve raised a good point regarding the R version affecting the installation and functionality of INLA. I might have used a different R version when I prepared the materials, which could explain why I didn’t encounter this issue.

For those experiencing similar issues, the command provided on the INLA web…[Read more]

Hello both,

Thank you for sharing your tips and tricks, Kansiri. Your detailed setup for displaying PV_2015 cases is helpful. I appreciate your creativity in setting dot sizes and background colors. It’s great to see this collaborative spirit in our class. Please continue to share your insights and experiences.

Have a great day!

Hi Teerawat, Kansiri, and Nichcha,

Thank you for your feedback. I appreciate your suggestions to improve the QGIS instructions. Teerawat, incorporating bullets and more screenshots is a great idea. Kansiri and Nichcha, adding details on color settings and more visual cues will definitely help. I will work with the team on updating the document to…[Read more]

Hi Kansiri and Soe Htike,

Thank you both for sharing your experiences and tips with QGIS! It’s great to see students helping each other navigate different versions of the software. It’s common for software interfaces to change with updates, and your shared solutions are valuable for everyone in the class. I encourage all of you to continue using…[Read more]

Thank you, Nichcha, for sharing your experiences and solutions with the class. Your detailed account of the issues you encountered and how you resolved them would be valuable for your classmates.

To all students, I encourage you to use this forum to share and communicate with each other. Your experiences can help create a supportive and…[Read more]

Hello TMHG 517 class…

It’s truly great to see the collaboration and support you’re providing to one another during this course. I hope that these connections will continue to thrive beyond the classroom.

Regarding the recent change in the INLA system, there is a recent change internally within INLA. Specifically, the marginals of the linear…[Read more]

Hi class,

I would like to note that calculating fitted values in INLA can be approached differently based on the specific context. Departing from the class example, you might find it beneficial to explore the utilization of the ‘summary.fixed’ command, which offers an alternative method to determine the fitted values of relative risks. In regard…[Read more]

Hello everyone,

I’m glad to read your comments. Typically, spatial analysis in studies tends to concentrate on communicable diseases which you can see from TMHG549, GIS course. However, I think it would be also valuable to provide an alternative outlook from a view of non-communicable diseases. Despite the varying mode of transmission, the…[Read more]

Thank you, Chanapong, for your comment. I agree with you that spatial epidemiology’s interdisciplinary approach, which integrates advanced technologies and data from various scientific fields, allows us to gain valuable insights into disease patterns and their spatial context. Your point about considering the impact of location on disease factors…[Read more]

Thank you all for your contributions to this fruitful discussion! While communicable diseases are widely recognized for their spatial dimension, I also would like to emphasize that place can also serve as a proxy for non-communicable diseases, which we will further explore in this course. Understanding the geographic context and environmental…[Read more]