Introduction

I chose to break use the WV checkbook to further break down spending into categories. My thesis is that if schools spend more to attract teachers(higher pay, better benefits, etc) then proficiency will rise in that school. The Categories I chose to look further into were:

Professional Personnel
Books
Technology
Benefits

Data

Original spending data

I was interested in more specific spending by county but still used the enrollment numbers from this table to be able to get spending based off of number of students.

## # A tibble: 55 × 8
##    name                  enroll tfedrev tstrev tlocrev totalexp ppcstot county  
##    <chr>                  <dbl>   <dbl>  <dbl>   <dbl>    <dbl>   <dbl> <chr>   
##  1 BARBOUR CO SCH DIST     2144    7559  16584    5872    28021   11885 Barbour 
##  2 BERKELEY CO SCH DIST   19722   48407 140127   86699   264253   12704 Berkeley
##  3 BOONE CO SCH DIST       3177    8194  26858   14564    48642   14663 Boone   
##  4 BRAXTON CO SCH DIST     1747    5479  12748    6404    24417   13153 Braxton 
##  5 BROOKE CO SCH DIST      2582    6791  17114   21352    41908   15642 Brooke  
##  6 CABELL CO SCH DIST     11667   42518  88337   66699   183621   14538 Cabell  
##  7 CALHOUN CO SCH DIST      861    3254   9953    3190    15154   16085 Calhoun 
##  8 CLAY CO SCH DIST        1669    6157  17655    2791    25963   13825 Clay    
##  9 DODDRIDGE CO SCH DIST   1082    3455   3999   31752    38493   23563 Doddrid…
## 10 FAYETTE CO SCH DIST     5594   15293  51759   23477    83373   13777 Fayette 
## # ℹ 45 more rows

Spending Data by County

I used the checkbook to individually download each county’s spending data into a csv and used a function to make a table of all csv files in my folder automatically, this helped when I went from originally using 22 counties to using all counties of the state.

## 
## The downloaded binary packages are in
##  C:\Users\cgoum\AppData\Local\Temp\RtmpQ9D32k\downloaded_packages

## package 'maps' successfully unpacked and MD5 sums checked
## 
## The downloaded binary packages are in
##  C:\Users\cgoum\AppData\Local\Temp\RtmpQ9D32k\downloaded_packages

## package 'viridis' successfully unpacked and MD5 sums checked
## 
## The downloaded binary packages are in
##  C:\Users\cgoum\AppData\Local\Temp\RtmpQ9D32k\downloaded_packages

##                teachers  technology      books proficiency
## teachers     1.00000000 -0.02174409  0.2404514   0.3045906
## technology  -0.02174409  1.00000000 -0.1525747  -0.1938212
## books        0.24045142 -0.15257468  1.0000000   0.1783361
## proficiency  0.30459062 -0.19382121  0.1783361   1.0000000

## Decision Tree

## [1] "Mean Squared Error Train:  45.5"

## [1] "Mean Squared Error Test:  9.64"

Limitations

High error in decision tree was not optimal and I felt limited that the spending categories while broken up still felt very broad. Being able to break the data to a school level would be interesting to see if there are any traits that all good schools specifically share.

Conclusions

Schools that spend more money on teachers generally do have higher proficiency. Schools with better teachers make the increased book spending have a further positive impact. Higher pay gets teachers in the door but it is how they make an impact once they get through the doors that drives positive effects on proficiency.

References

WV Checkbook used to get all spending data for all counties

Copilot used on graphs to get titles and themes