Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Additional checks on expenditures #24

Open
2 tasks
AlexGherardelli opened this issue Jul 26, 2024 · 0 comments
Open
2 tasks

Additional checks on expenditures #24

AlexGherardelli opened this issue Jul 26, 2024 · 0 comments
Labels
enhancement New feature or request indicator Data quality check on a new indicator
Milestone

Comments

@AlexGherardelli
Copy link
Collaborator

AlexGherardelli commented Jul 26, 2024

  • HH reported with high food consumption score, but expenditure is below minimum expenditure threshold
  • HH reported with low food consumption score, but expenditure is above maximum expenditure threshold

 Number of interviews with total food or non-food consumption expenditures of 0. Observing a household with 0 food or NF consumption expenditures is very unlikely.
 Check values that do not make economic sense, e.g., food expenditures of 1 or 2 units when a unit of bread costs 50 local currency. If spotted, investigate the extent to which these values occur, and the potential reasons (e.g., misunderstanding with currencies or anomalies with a specific enumerator). These checks should be done with original values and, optionally, also on per capita values.
 Check for outliers. Use different statistics related to individual expenditure items (and/or aggregates of various kind) by enumerator/admin, to spot incorrect application of the module. These checks can be done in different ways, but they should all be done in per capita terms and taking into account potential large difference in prices across survey areas. Examples of possible checks include:
o Comparing mean/median expenditure by enumerator to identify enumerators who might systematically overreport/underreport expenditure
o Identify outliers using a statistical procedure like that described in the “Cleaning” section and compute occurrences of outliers by enumerator
o Box plots can be a handy way of comparing median, minimum, maximum and extreme expenditure values by enumerator to detect possible issues with the administration of the module
o While some outliers are likely on the high-end (e.g., excessive health expenditures), whereby a household has anomalously high expenditures, enumerators might also have included extra zeros by mistake. So, it is best to verify with the field team, where possible.
 Check for atypical values like ‘33’ ‘77’ ‘88’ ‘99’ or other overly specific, out of the ordinary figures to flag to enumerators and check if they meant not applicable (which is a practice that should not be applied in the expenditure module).

@AlexGherardelli AlexGherardelli added the indicator Data quality check on a new indicator label Jul 26, 2024
@AlexGherardelli AlexGherardelli added this to the v0.2.0 milestone Jul 26, 2024
@AlexGherardelli AlexGherardelli added the enhancement New feature or request label Aug 8, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request indicator Data quality check on a new indicator
Projects
None yet
Development

No branches or pull requests

1 participant