Based on data from the United States Census and renowned Cook Partisan Voting Index (CPVI), congressional districts with more educated residents are more likely to pledge their electoral votes to Republican presidential candidates. Conversely, congressional districts with less educated residents are more likely to pledge their electoral votes to Democratic presidential candidates.

As demonstrated below, there is a statistically significant positive correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Republican presidential candidates. Comparatively, there is a statistically significant negative correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Democratic presidential candidates.

As a point of probable interest, seven of the ten most educated congressional districts are partisan Republican districts and three are partisan Democratic districts. All ten of the least educated congressional districts are partisan Democratic districts. As a preliminary matter, the following is a list of these twenty congressional districts, their general geographic areas, high school (or higher) graduation percentages, and their Cook Partisan Voting Index (CPVI) values:

**Most Educated **

1. Colorado-6 (Littleton-Castle Rock, 96%, CPVI Republican +8);

2. Minnesota-3 (Edina-Maple Grove, 94.7%, CPVI Republican +0);

3. California-30 (Beverly Hills-Malibu, 94.2%, CPVI Democrat +18 );

4. Washington-1 (Redmond-Edmonds, 94.1%, CPVI Democrat +9);

5. Wisconsin-5 (Waukesha-West Bend, 93.6%, CPVI Republican +12);

6. Minnesota-2 (Apple Valley-Lakeville, 93.6%, CPVI Republican +4);

7. Massachusetts-10 (Cape Cod, 93.6%, CPVI Democrat +5);

8. Georgia-6 (Dunwoody-Canton, 93.5% CPVI Republican +19);

9. Minnesota-6 (Woodbury-St. Cloud, 93.4%, CPVI Republican +7);

10. Illinois-13 (Downers Grove-Orland Park, 93.4%, CPVI Republican +1)

**Least Educated **

1. Texas-29 (South Houston-Baytown, 53%, CPVI Democrat +8);

2. California-34 (East Los Angeles, 54.4%, CPVI Democrat +22);

3. California-20 (Fresno-Lamont, 55.2%, CPVI Democrat +5);

4. California-47 (Garden Grove-Santa Ana, 55.8%, CPVI Democrat +4);

5. New York-16 (Bronx, 58.5%, CPVI Democrat +41);

6. California-31 (Northeast Los Angeles-Hollywood, 59.2%, CPVI Democrat +29);

7. Illinois-4 (Chicago-Cicero, 61.7%, CPVI Democrat +32);

8. Arizona-4 (Phoenix-Guadalupe, 63.6%, CPVI Democrat +13);

9. Texas-15 (Corpus Christie-McAllen, 64.7%, CPVI Democrat +3);

10. Texas-28 (Laredo-San Antonio, 65%, CPVI Democrat +0).

**Null Hypotheses**

1. There is no correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Republican presidential candidates.

2. There is no correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Democratic presidential candidates.

Alternative Hypotheses

1. There is a correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Republican presidential candidates.

2. There is a correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Democratic presidential candidates.

Statistical Correlation Measure

The statistical correlation measure used herein is the Pearson product-moment correlation coefficient (denoted by *r*) which measures the linear correlation between two variables X and Y, giving a value between -1 and +1. The nearer the *r* statistic is to +1, the greater the positive correlation between two variables. The nearer the *r* statistic is to -1, the greater the negative correlation between two variables.

For purposes of the studies herein, an *r* statistic of +1 would indicate a perfect positive correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for either Republican or Democratic presidential candidates. Alternatively, an *r* statistic of -1 would indicate a perfect negative correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support for either Republican or Democratic presidential candidates.

An *r* statistic of 0 indicates no statistical correlation.

**Data**

X variables are the percentage of residents in each of the 436 U.S. congressional districts who are high school graduates (or higher). Y variables are the Cook Partisan Voting Index (CPVI) values of the 436 U.S. congressional districts: measures of how strongly the voters of each district leaned toward one political party compared to the nation as a whole in the last two presidential elections.

**Statistical Significance: Critical Value Range**

-.09 to .09 (434 degrees of freedom at an alpha of .05; two-tailed test)*****

***Explanation****:** In order to reject either null hypothesis and accept the corresponding alternative hypothesis, the *r* statistic for X and Y must be .09. In such a case, there is at least a 95% probability that the correlation did not simply occur by mere chance. Any *r* statistic between -.09 and .09 indicates no statistically significant correlation between X and Y.

**Findings**

Percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Republican presidential candidates. *r* = .23 (p-value=.000001)

Percentage of residents in each congressional districts who are high school graduates (or higher) and support by those districts for Democratic presidential candidates. *r* = -.23 (p-value=.000001)

Conclusions

The alternative hypotheses are accepted because the respective *r* statistics of .23 and -.23 are outside of the critical value range.

There is a statistically significant positive correlation between the percentage of residents in each congressional district who are high school graduates (or higher) and support by those districts for Republican presidential candidates. There is a statistically significant negative correlation between the percentage of residents in each congressional districts who are high school graduates (or higher) and support by those districts for Democratic presidential candidates.

The p-values for these studies are .000001; therefore, there is a 1 in 1,000,000 chance that these correlations occurred circumstantially rather than because of a true relationship.

Source(s):

“Cook Partisan Voting Index,” *The Cook Political Report * “2006-2008 American Community Survey (ACS),” U.S. Census Bureau

Embedded Links