Iss416 #452
Iss416 #452
Conversation
06_neighborhoods/social-capital/economic_connectedness_county_2022.qmd
Outdated
Show resolved
Hide resolved
06_neighborhoods/social-capital/economic_connectedness_county_2022.qmd
Outdated
Show resolved
Hide resolved
06_neighborhoods/social-capital/economic_connectedness_city_2022.qmd
Outdated
Show resolved
Hide resolved
| # and also include total ZCTAs in Place & how many of those partially fall outside the Place | ||
|
|
||
|
|
||
| wtd_merged_ec_city <- merged_ec_city |> |
There was a problem hiding this comment.
There is a lot happening in this chunk that I think deserves individual attention. Creation of the zip_total and zips_in varaibles is fairly complex, I would do this in a seperate step and add a bit more explenation.
There was a problem hiding this comment.
I have added explanations for each of these code transformations. I think that leaving this chunk of code unchanged is fine because of the grouping level, otherwise will have to do more manipulations to get the data to the place level. I think zip_total could have been achieved without num_ZCTAs_in_place but it's alright, hopefully my explanation makes more sense.
I also changed the way num_ZCTAs_in_place was computed to give more intuition as to what is happening here. Let me know if it makes sense now!
There was a problem hiding this comment.
This looks good to me, I think the added detail is helpful
| ```{r} | ||
| #| label: data-quality-flag | ||
|
|
||
| # Data Quality 1 = 50% or more of the ZIPs fall mostly (>50%) in the census place |
There was a problem hiding this comment.
Double-check this step for me. I don't believe the code is actually doing what this explenation says. The variable zips_in is the sum of portion_in which I believe is 1 if the entire ZCTA falls in the place and zero if not. To match the explenation given here for quality I believe you would have to swap the variable mostly_in for portion_in above in the code-chunk labeled collapse-estimates. Please give this a close look.
There was a problem hiding this comment.
Thank you for pointing this one out! If you refer Tina's code, she left a comment that she never used mostly_in variable after creating it (I have left this comment in the qmd file too). Based on referring the original code, I think Tina intended to use portion_in here. I believe the confusion stems from the word mostly in the quality variable explanation which I have changed to fully now.
The gist is that quality variable considers what percentage of ZCTAs are fully within the boundaries of a Place. So higher the ZCTAs that are encompassed by a Place, the more confidence we have in the transformed economic connectedness value linked with that place. Does this make sense?
There was a problem hiding this comment.
Yes this makes a lot more sense now, great clarification!
|
Hi @jwalsh28! I updated the files based on your review and added responses to your comments. I have tried to provide answers to some of the questions you had about methodology. Please let me know if you have any more thoughts/questions. Thank you! |
| ), | ||
| # calculate lower bound from standard error | ||
| share_economic_connectedness_lb = | ||
| share_economic_connectedness - ( qnorm(0.975) * ec_se_county_updated ), |
There was a problem hiding this comment.
@awunderground Flagging for you if you have a second to share any thoughts here, though I think Ridhi's explanation makes sense.
| ```{r} | ||
| #| label: data-quality-flag | ||
|
|
||
| # Data Quality 1 = 50% or more of the ZIPs fall mostly (>50%) in the census place |
There was a problem hiding this comment.
Yes this makes a lot more sense now, great clarification!
Mobility metric pull request template
Please include the following points in your PR:
A link to the issue that this PR relates to. You can bring up a list of suggested issues and pull requests within the repository by typing #. Review new way to display data and adjust display of social capital2 metric #416
A description of the content in this pull request.