15.S03: Metascientific examination of social & behavioral sciences reflection (test:Abdullah Almaatouq)

[hyunjimoon]

Team: Abdullah Almaatouq

marginnote3app://note/19FD87D9-71BC-4E59-8649-5D42AC9AB093

Discussed in #187

^{Originally posted by hyunjimoon February 12, 2024}
syllabus

[hyunjimoon]

goal:

• narrowing belief and goal prior with abudllah (A)
• establish narrative structure that maximizes reception efficiency

action:

• after receiving informative prior on problem solving process in A's domain, i updated my prior in startup domain and further pooled prior from disease treatment (raw data: 15.363 W5.txt) where we can have more information gain on solution process.

• shared the above with A and prompted for feedback input

• based on A's input on informative prior for "Social Science column", add more structure in solution rows (4,5) which is not informative yet

problem

Step	Substep	Disease Treatment	Social Science	Startup Social Science
1. Problem to intervene		Disease is treated only at the symptom level without addressing underlying causes.	Social science is non-cumulative.	Startups fail at a higher rate than necessary.
2. Cause of 1		Lack of understanding of the fundamental biological processes leading to disease.	High causal density and methodological incompatibility.	Inadequate adaptation to rapidly changing environments and market signals.
	2.1 Nature	Everything is a symptom of deeper level cause.	High causal density (many things matter).	Idiosyncratic signal from dynamic environment.
	2.2 Agent level use based on 2.1	Traditional approaches focus on symptom relief rather than root cause.	Incommensurability (design choices); focus on not hypothesis testing.	Too reactive from conflated effects of belief and goal (confusion of misalignment), agent and environment's uncertainty, and overconfidence and optimism (value of misalignment).
	2.3 Institution level use based on 2.1, 2.2	Regulatory frameworks prioritize demonstrable efficacy over understanding complex biological interactions.	Existing methods ignore root causes.	Non-cumulative learning from success and failed startup cases.
3. Solution for 2		Develop targeted therapies based on precise understanding of disease mechanisms.	Develop cumulative and integrative research methodologies.	Implement adaptive learning frameworks for rapid response to market changes.
	3.1 Solution for 2.1	Invest in genomic and proteomic research to understand disease at a molecular level.	Facilitate compatibility and commensurability across studies.	Show agents potential choices through higher quality information with dashboard 🖥️, offering training 🏋️, and testing their belief with interactive simulation 🖱️.
	3.2 Solution for 2.2	Adopt a precision medicine approach to develop treatments targeting specific molecular pathways.	Promote hypothesis testing and evidence-based research.	Enhance decision-making process.
	3.3 Solution for 2.3	Implement adaptive clinical trial designs to allow for iterative learning about the disease.	Implement integrative research methodologies.	Develop comprehensive platforms for iterative learning and adaptation.

solution

Step	Substep	Disease Treatment	Social Science	Startup Social Science
4. Theory of problem-solving action mechanism		The theory focuses on adopting a precision medicine approach (3.2) to target specific molecular pathways and implementing adaptive clinical trials (3.3) for iterative learning, addressing the traditional focus on symptom relief and improving understanding of biological processes.	The theory emphasizes promoting hypothesis testing and evidence-based research (3.2) and integrating diverse methodologies (3.3) to overcome the challenges of high causal density and methodological incompatibility, aiming for a more cumulative and systematic approach.	The theory advocates enhancing decision-making processes (3.2) and developing platforms for iterative learning (3.3) to counter startups' high failure rates due to inadequate adaptation to market changes and non-cumulative learning experiences.
5. Implementing action mechanism based on 4		Implementation through precision medicine and adaptive trials leads to targeted, efficient treatments, directly addressing the fundamental biological processes of diseases.	Implementing hypothesis-driven, evidence-based, and integrative research methodologies tackles the non-cumulative nature and methodological challenges of social science.	Developing agile platforms that enhance decision-making and promote continuous learning and adaptation helps startups navigate and thrive in dynamic market environments.

[hyunjimoon]

Would like to get Matt's opinion on

• framing one paper as modules of experiment with the goal of persuading the policy maker

[hyunjimoon]

with prompt below,

Hi, based on belief, help me achieve goal!

[goal] construct problem and solution dictionary (encyclopedia), group them so that we can prescribe solution to scientists facing specific problem
 
[belief]
1. 15.S03 syllabus is professor Abdullah and his class member (including Johanna and Angie )'s compilation of relevant literature
2. MSC111213.pdf is reading list in solution section (Week 11-13) of syllabus
3. literature(problem).csv is Johanna's first draft on connecting problem structure with literature (for dictionary)
4. attached two figure (problem.jpg, solution.jpg) are our framework on root cause and solution

5. below is Angie's reflection along with part of class' transcript https://github.com/Data4DM/BayesSD/discussions/187

exported from miro
literature(problem).csv
problem.jpg
solution.jpg

gpt gave:

Structural Framework for Problem and Solution Encyclopedia

1. Problem Identification:

   • Categories: Classify problems under broad categories derived from the "Things That Make Social Sciences Different from Physics" image. These categories might include:
     • Nature of Subject Matter (e.g., High Causal Density, Path Dependence)
     • Research and Human Elements (e.g., Confirmation Bias, Limited Cognitive Capacity)
     • Institutional Factors (e.g., Lack of Mathematical Training)

2. Solution Proposals:

   • Solution Mapping: Align solutions from the "Solution Space" image to the problems identified. This can include:
     • Reproducible Code and Transparent Manuscript Writing for issues like Confirmation Bias or the inability to directly observe phenomena.
     • Preprints and Open Science Journal Club for overcoming institutional barriers like Publish & Perish pressures.

3. Literature Integration:

   • Source Connection: Use the MSC111213.pdf as a foundational source for literature that supports the solutions. Ensure that each solution is backed by robust literature as referenced in the syllabus and further readings.
   • Problem-Solution Linking: Utilize the literature(problem).csv file to connect each problem with existing literature, thereby enriching the dictionary with a solid theoretical foundation.

4. User Interface Design:

   • Interactive Elements: Design the digital version of the encyclopedia to include interactive elements like clickable categories, which expand to show detailed problems and linked solutions.
   • Search Functionality: Include a search bar that allows users to search for specific problems, solutions, or literature references.

5. Feedback and Updates:

   • Community Engagement: Integrate a system for users to submit feedback on existing entries and suggest new problems or solutions, fostering a collaborative and evolving resource.
   • Regular Updates: Plan for periodic updates to the encyclopedia based on new research findings, changes in the field, and user feedback.

6. Educational Integration:

   • Academic Use: Collaborate with educational institutions to incorporate the encyclopedia into curricula, enhancing both teaching and learning experiences.
   • Workshops and Seminars: Organize workshops and seminars to introduce the encyclopedia to the academic community, focusing on its practical use in addressing common research problems.

Prioritization and Implementation

• Start Small: Begin with a pilot version focusing on a few major problems and solutions. Gather feedback and refine the approach.
• Scale Gradually: Expand the encyclopedia gradually, adding more problems and solutions as the platform stabilizes and user engagement increases.

This structured approach not only helps in organizing the vast amount of information but also ensures that the encyclopedia is practical, user-friendly, and dynamically responsive to the changes in the field of social sciences.