Final Project

This is my R notebook for my final project.

I first loaded my data set.

data <- read.csv("Math_Test_Results_2013-2023") 

Warning: cannot open file 'Math_Test_Results_2013-2023': No such file or directoryError in file(file, "rt") : cannot open the connection

These are the necessary steps I took to clean my data set.

Now that my data set is cleaned I will begin my exploratory analysis.

I first made a scatter plot comparing the percentage of level 1 students vs. level 4 students.

Then I made a line plot comparing those who scored in the level 1 percentile based on year

After seeing that these graphs don’t tell me very much, I knew that I needed to look at more specific factors.

So I created a graph that compared male and female percentage scores.

I created a similar bar graph, comparing ethnicity instead of gender.

Another bar graph comparing students who are at an economic disavandtage and those who are not.

This is my first linear regression model. That looks at the correlation between gender and the percentage of students who scored in level 1.

# Print a summary of the regression results
summary(model)

Call:
lm(formula = Pct.Level.1 ~ gender_male + gender_female, data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-35.180 -19.837  -2.587  16.714  65.513 

Coefficients:
              Estimate Std. Error t value Pr(>|t|)    
(Intercept)    34.4868     0.3474  99.259   <2e-16 ***
gender_male     0.6937     1.1048   0.628    0.530    
gender_female  -1.2012     1.0699  -1.123    0.262    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 23.73 on 5724 degrees of freedom
Multiple R-squared:  0.0003175, Adjusted R-squared:  -3.184e-05 
F-statistic: 0.9088 on 2 and 5724 DF,  p-value: 0.403

This is my second linear regression model. That looks at the correlation between ethnicity and the percentage of students who scored in level 1.

# Print a summary of the regression results
summary(model2)

Call:
lm(formula = Pct.Level.1 ~ race_white + race_black + race_hispanic, 
    data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-44.949 -18.813  -2.413  16.006  66.006 

Coefficients:
              Estimate Std. Error t value Pr(>|t|)    
(Intercept)    33.9941     0.3408  99.762  < 2e-16 ***
race_white    -17.0903     1.6448 -10.390  < 2e-16 ***
race_black     10.9553     1.3097   8.365  < 2e-16 ***
race_hispanic   4.8186     1.1031   4.368 1.27e-05 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 23.32 on 5723 degrees of freedom
Multiple R-squared:  0.03489,   Adjusted R-squared:  0.03439 
F-statistic: 68.97 on 3 and 5723 DF,  p-value: < 2.2e-16

This is my final linear regression model. That looks at the correlation between economic disadvantaged and the percentage of students who scored in level 1.

# Print a summary of the regression results
summary(model3)

Call:
lm(formula = Pct.Level.1 ~ econ_disadv, data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-34.591 -19.891  -2.591  16.709  65.409 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  34.5912     0.3265 105.940   <2e-16 ***
econ_disadv  -2.0212     1.1687  -1.729   0.0838 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 23.73 on 5725 degrees of freedom
Multiple R-squared:  0.0005221, Adjusted R-squared:  0.0003476 
F-statistic: 2.991 on 1 and 5725 DF,  p-value: 0.08379