class: center, middle, inverse, title-slide # Analysis of Education Expenditure and Standardized Test Scores ### Thomas, Kathleen, Dieter, Meg ### Bates College ### 2021-11-17 --- --- class: center, middle ## Our Goals and Research Questions We aim to produce analyses that are informative of the relationship between test scores and expenditure on a national and state level. Is there a notable relationship between expenditure and test scores? Does expenditure per student raise test scores? Do different kinds or sources of expenditure vary in effectiveness of improving performance? --- class: inverse, center, middle # How do Economic Factors Influence Test Scores? -- # Preliminary Exploration - The dataset we are using comes from U.S Education Datasets Unification project. This project seaks to combine multiple facets of U.S Education into one dataset. - We make use of a correlation matrix in order to guide our preliminary exploration of the data. - A correlation matrix allows us to quickly visualize the correlation coefficients between the variables in our dataset. - 1 indicates a perfectly negative linear correlation between two variables. - 0 indicates no linear correlation between two variables. - 1 indicates a perfectly positive linear correlation between two variables. --- # Correlation Matrix .pull-left[ ```r test_data <- data_set[,c(5,6,7,8,9,10,11,21,22,23)] res <- cor(test_data, use = "complete.obs") #round(res, 2) ``` ] .pull-right[ <img src="presentation_files/figure-html/unnamed-chunk-3-1.png" width="80%" /> ] --- # How have Test Scores Changed Over the Years? Despite considerable debate about their efficacy, standardized test scores continue to serve as the primary metric in assessing students and overall education system performance. Reachers at the Fordham Institue cite three main reasons for their continued use: - Objectivity - Comparability - Accountability --- <img src="presentation_files/figure-html/unnamed-chunk-4-1.png" width="80%" /> --- # Is There a Correlation Between Test Scores and School Revenue? ### An in depth look at DC's Data .pull-left[ <img src="presentation_files/figure-html/unnamed-chunk-6-1.png" width="80%" /> ] .pull-right[ <img src="presentation_files/figure-html/unnamed-chunk-7-1.png" width="80%" /> ] --- <img src="presentation_files/figure-html/unnamed-chunk-8-1.png" width="80%" /> --- # Does Increased Spending Influence Test Scores? ### Creating the Expenditure per Student Variable - Expenditure per student is calculated by dividing the total education expenditure of a state by the total number of students enrolled in its schools. - We find that the average expenditure per student, denoted by "NATIONAL", is $13,114 annually. ```r stats_percap = data_set %>% group_by(STATE) %>% summarise(enroll = mean(ENROLL, na.rm=TRUE), expenditure = mean(TOTAL_EXPENDITURE, na.rm=TRUE), AVG_MATH_8_NO_NA = mean(AVG_MATH_8_SCORE, na.rm=TRUE), AVG_READ_8_NO_NA = mean(AVG_READING_8_SCORE, na.rm=TRUE)) %>% mutate(enroll = enroll * 1e-6, expenditure = expenditure * 1e-6) stats_percap$expenditure_per_student = stats_percap$expenditure / stats_percap$enroll ``` --- <img src="presentation_files/figure-html/unnamed-chunk-11-1.png" width="80%" /> --- <img src="presentation_files/figure-html/unnamed-chunk-13-1.png" width="80%" /> --- <img src="presentation_files/figure-html/unnamed-chunk-14-1.png" width="80%" /> --- <img src="presentation_files/figure-html/unnamed-chunk-15-1.png" width="80%" /> --- <img src="presentation_files/figure-html/unnamed-chunk-17-1.png" width="80%" /> --- ``` ## [1] "SpatialPolygonsDataFrame" ## attr(,"package") ## [1] "sp" ```
---