0% found this document useful (0 votes)
16 views2 pages

Hiring Coding-Deliverable

Coding

Uploaded by

csd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
16 views2 pages

Hiring Coding-Deliverable

Coding

Uploaded by

csd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Hiring: Research & Innovation Department at Youth Impact

Coding Deliverable

Hiring by the Research & Innovation Department, Youth Impact:


Coding Deliverable
You should take 60 minutes or less to complete this deliverable, which requires
● this 2-page pdf containing the instructions,
● our zip-folder containing (i) the data and (ii) a Stata do-file, and
● access to statistical software, either Stata (preferred) or R.

The deliverable contains five questions, and each question is graded with 0 to 1 point,
except question 5 which is graded with 0 to 2 points.

The data
The data is shared in Stata’s .dta format which can also be imported into R, see LINK. It is
based on Teaching at the Right Level (TaRL), our foundational numeracy program, and
contains the following variables:
● An anonymized region name
● An anonymized school name
● An anonymized student ID
● The numeracy level of pupils at baseline and at endline, with values from 0 to 4:
○ 0=Beginner, 1=Addition, 2=Subtraction, 3=Multiplication, 4=Division
○ For instance, “2=Subtraction” means that a student has mastered addition
and subtraction but not multiplication and division.

The script
We share a Stata do-file that contains further instructions; R-users can open it in RStudio or
any text editor. Rename the do-file to “coding-deliverable_fname_sname.do” where fname
is your first name and sname is your surname. Also specify your first name (line 2), surname
(l. 3), and the date (l. 4) at the top of the do-file. Please code succinctly.

Submission
Upload your Stata or R script together with your application via our GoogleForm Application
Survey on our “Join Us” website (LINK). Please do not submit the data or output. We will
only evaluate your Stata or R script and the outputs we produce from running it.

Tasks
1. Set the folder path to your working directory with a global macro. Your code should
be executable without any changes by our reviewers, except one line of code in
section "1. Set the folder path to your working directory with a global macro".

2. Load the Stata dataset "coding_deliverable.dta" provided in the "data" folder and
create the following Key Performance Indicators (KPIs):
○ Binary indicators for innumeracy at baseline and endline taking the values
■ 1 if the numeracy level equals 0 (=beginner)
■ 0 if the numeracy level ranges from 1 (addition) to 4 (division).
Hiring: Research & Innovation Department at Youth Impact
Coding Deliverable

○ Binary indicators for numeracy at baseline and endline taking the values
■ 1 if the numeracy level equals 4 (division)
■ 0 if the numeracy level ranges from 0 (beginner) to 3 (multiplication).
Note: We expect that Stata users employ a foreach-loop for efficient coding.

3. Create the subfolder “outputs” from within Stata or R in your working directory, i.e.

4. Export an excel file “school_level_results.xlsx” to “outputs” with three region-specific


tabs containing school-level information as displayed below:

Note: We expect that Stata users employ a foreach-loop for efficient coding.

5. Replicate our Key Performance Indicator figure (shown below) and save it as
"kpi_figure.png" in "outputs". You do not need to exactly clone the figure, as there are
many adequate ways of visualizing the same data. However, we will deduct half a point
for each of the following elements that are missing in your solution: (i) Bar labels, (e.g.,
“Innumeracy: BSL”), (ii) value labels (e.g., 22.6), (iii) customized color scheme, (iv) the
number of observations (important: do not write “2194” into your script, since the
number should dynamically update if the dataset changes).

You might also like