Skip to content

[kalman_2] Some Comments for first three subsections #902

@longye-tian

Description

@longye-tian

Hi @jstac

I have two questions
Here are some comments for the lecture kalman_2 's first three subsections.

Begining paragraph

The begining paragraph contains some typos.

  • quantecon should likely be QuantEcon

  • “how the much firm pays” should be “how much the firm pays”.

A worker's output

The section A worker's output contains several notation and exposition issues.

  • “The workers' output” should likely be “The worker's output”.

  • In the human capital equation, c_{t+1} \sim {\mathcal N}(0,1) appears to be a typo. Since the shock enters as $c w_{t+1}$, this should likely be $w_{t+1} \sim N(0,1)$.

  • In the kalman_2 lecture, we use \sim \mathcal{N} but style guide qe-math-A3 says we should use \sim N

  • The shock $w_{t+1}$ is not defined in the “Here” list.

  • The notation $w_{t+1}$ for the human capital shock may be confusing because $w_t$ is later used for the worker's log wage. It may be clearer to rename the shock to something like $\epsilon_{t+1}$.

  • The parameter list uses $\sigma_h, \sigma_u$, but the initial distributions use $\sigma_{h,0}, \sigma_{u,0}$. These should be made consistent.

  • The equation $u_{t+1} = u_t$ is useful because it treats effort as a fixed unobserved component of worker type, but the text should explain this point more explicitly.

A firm's wage-setting policy

The section A firm's wage-setting policy contains some notation and exposition issues.

  • The expectation notation should change to \mathbb{E} following style guide qe-math-A1

  • The information timing is important but could be stated more clearly: the firm sets the wage at time $t$ using past output history $y^{t-1}$, before observing current output $y_t$.

Do these changes sound reasonable? I would be happy to open a PR if so

Best,
Longye

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions