Categorías: Todo - institutions - models - design - analysis

por Anton Tkachenko hace 10 años

232

model thinking

The text discusses the importance and application of models in various analytical contexts. Models serve as tools for understanding complex systems and aiding decision-making processes, such as through comparative statics, counterfactual analysis, and real-time decision aids like the Monty Hall paradox.

model thinking

model thinking

section 2: segregation and peer effects

4. peer effects
Subtopic
model

avg value - how likely that everyone will do it

each one has a threshold (how many people you need to join them)

N individuals

3. measuring segregation
1. rich/poor

for perfectly segregaged - 2; for perfectly mixed 0

total index: 6*1/45 + 6*1/9 + 12* 1/15= 72/45 (total index)

for blue - 1/15; yellow - 1/9; green - 1/45

| b/B - y/Y | - if equals 0, totally not segregated - index of similarity

b=rich in block; B - rich total; y/Y - poor

24 blocks: 12 rich, 6 50-50, 6 poor

2. schelling segregation
3. checkers model

3/7 good; 2/7 bad

how many people around you are rich

2. racial - "ghettos"
1. financial - by income (model of NY)
1. sorting and peer effects
peer effect: peers start acting like surrounding
sorting effect: people tend to communicate with similars (detroit - black and white or smokers)

section 1: why model

1.5 using models to analyse
7. help choose among institutions (democratics or communism?)
6. institutional design
5. experimental design (models instead of real experiments)
4. identifying leverages (if greece fails, all europe fails)
3. conterfactuals (with or without recovery plan - what would happen?)
2. comparative statics (as-ad curves)
1. rral time desicion aid (monty hall paradox)
1.4 analysing data
8. calibrate - make the model closer to real world - forest fires.
7. estimate hidden parameters (number of sick people and sickness progress)
6. inform data collection - which data do we need?
5. predict sth else (planet with big mass)
4. retrodict - test models by running from past
3. predict boundaries ( infl 0..3%)
2. predict points (for ex., price of the house basing on metrage)
1. see patterns (horizontal, rising, falling, cyclical...)