Final
Eliana Almazan
2023-04-20
For my final assignment, I used the dataset “Community Health Obesity
and Diabetes Related Indicators: 2008-2012”( Health.data.ny.gov., 2021
). It is comprised of 63 New York counties and their region names along
with numerous health indicators such as diabetes and obesity
hospitalizations for both adults and children, cirrhosis mortality
rates, diet and exercise habits, and others. Given the prevalent
mortality rates in the U.S, I was interested in analyzing the difference
in means of cardiovascular and cerebrovascular mortality rates per
100,000 people across the nine regions of New York. I was also
interested in verifying whether there was a liner relationship between
cardiovascular and cerebrovascular disease mortality rates and diet
(age-adjusted percentage of adults eating 5 or more fruits or vegetables
per day at a 95% CI), lack of exercise (age-adjusted percentage of
adults who did not participate in leisure time physical activity in last
30 days at a 95% CI.), and region.
For my first analysis, I conducted factorial ANOVA using cardiovascular
and cerebrovascular mortality rates as my dependent variable and NY’s
regions as my independent variable. The null hypothesis was that the
means of means of cardiovascular and cerebrovascular mortality rates
were the same. The alternate hypothesis was that the means of
cardiovascular and cerebrovascular mortality rates were not the same. I
also included interaction hypothesis. For my interaction null
hypothesis, there were no interactions among cardiovascular and
cerebrovascular mortality rates against regions. My interaction
alternate hypothesis was there were interactions among cardiovascular
and cerebrovascular mortality rates against regions. I used f-test to
make the statistical inference at a=0.05. If the p-value was less than
alpha, we rejected the null-hypothesis and infer that there were
differences among the means. If p-value was less than alpha for
interactions, we concluded that there were significant interactions
across the factors
ny_fit = manova(cbind(Cardiovascular.Mortality, Cerebrovascular.Mortality)~ `Region Name`)
summary(ny_fit)## Df Pillai approx F num Df den Df Pr(>F)
## `Region Name` 8 0.91817 5.7289 16 108 8.522e-09 ***
## Residuals 54
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1summary.aov(ny_fit)## Response Cardiovascular.Mortality :
## Df Sum Sq Mean Sq F value Pr(>F)
## `Region Name` 8 74168 9271.0 2.7946 0.01153 *
## Residuals 54 179147 3317.5
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Cerebrovascular.Mortality :
## Df Sum Sq Mean Sq F value Pr(>F)
## `Region Name` 8 4689.8 586.22 12.843 3.867e-10 ***
## Residuals 54 2464.9 45.65
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Based on the model above, we can see that the p-value was less than 0.05
therefore, we can reject the null hypothesis. There were significant
differences among the means for cardiovascular and cerebrovascular
mortality rates. There were also interactions among both factors on
regions.
I also conducted a post hoc Tukey Test to verify which two pairs had significant differences. For cardiovascular mortality rates, we can see that Western New York and Hudson Valley had a p-value of 0.0303363, making them the most significantly different. For cerebrovascular mortality rates, there were several regions that had significant differences. The most significantly different pairs were New York City and Finger Lakes, Northeastern New York and New York City, and Western New York and New York City all with a p-value of 0.0000001. Below is screenshot of the post hoc Tukey Test results:
ny_fit1Tukey = aov(Cardiovascular.Mortality ~ factor(`Region Name`), data = ny_data)
summary(ny_fit1Tukey)## Df Sum Sq Mean Sq F value Pr(>F)
## factor(`Region Name`) 8 74168 9271 2.795 0.0115 *
## Residuals 54 179147 3318
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1TukeyHSD(ny_fit1Tukey)## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Cardiovascular.Mortality ~ factor(`Region Name`), data = ny_data)
##
## $`factor(`Region Name`)`
## diff lwr upr
## Finger Lakes-Central New York 3.836364 -79.802605 87.47533
## Hudson Valley-Central New York -32.135065 -122.105985 57.83585
## Nassau-Suffolk-Central New York 18.336364 -124.708282 161.38101
## New York-Penn-Central New York 71.103030 -50.101351 192.30741
## New York City-Central New York -26.783636 -127.150399 73.58313
## New York State-Central New York -8.263636 -202.623036 186.09576
## Northeastern New York-Central New York 43.012834 -28.993298 115.01897
## Western New York-Central New York 69.811364 -16.654908 156.27764
## Hudson Valley-Finger Lakes -35.971429 -129.749433 57.80658
## Nassau-Suffolk-Finger Lakes 14.500000 -130.969304 159.96930
## New York-Penn-Finger Lakes 67.266667 -56.789972 191.32331
## New York City-Finger Lakes -30.620000 -134.413231 73.17323
## New York State-Finger Lakes -12.100000 -208.250769 184.05077
## Northeastern New York-Finger Lakes 39.176471 -37.533573 115.88651
## Western New York-Finger Lakes 65.975000 -24.446037 156.39604
## Nassau-Suffolk-Hudson Valley 50.471429 -98.728463 199.67132
## New York-Penn-Hudson Valley 103.238095 -25.172726 231.64892
## New York City-Hudson Valley 5.351429 -103.608766 114.31162
## New York State-Hudson Valley 23.871429 -175.061760 222.80462
## Northeastern New York-Hudson Valley 75.147899 -8.420755 158.71655
## Western New York-Hudson Valley 101.946429 5.638313 198.25454
## New York-Penn-Nassau-Suffolk 52.766667 -117.104882 222.63822
## New York City-Nassau-Suffolk -45.120000 -200.809846 110.56985
## New York State-Nassau-Suffolk -26.600000 -254.506598 201.30660
## Northeastern New York-Nassau-Suffolk 24.676471 -114.430410 163.78335
## Western New York-Nassau-Suffolk 51.475000 -95.638077 198.58808
## New York City-New York-Penn -97.886667 -233.783906 38.01057
## New York State-New York-Penn -79.366667 -294.239068 135.50573
## Northeastern New York-New York-Penn -28.090196 -144.621117 88.44073
## Western New York-New York-Penn -1.291667 -127.271779 124.68845
## New York State-New York City 18.520000 -185.325859 222.36586
## Northeastern New York-New York City 69.796471 -24.873697 164.46664
## Western New York-New York City 96.595000 -9.489748 202.67975
## Northeastern New York-New York State 51.276471 -140.203372 242.75631
## Western New York-New York State 78.075000 -119.297904 275.44790
## Western New York-Northeastern New York 26.798529 -52.984738 106.58180
## p adj
## Finger Lakes-Central New York 1.0000000
## Hudson Valley-Central New York 0.9625381
## Nassau-Suffolk-Central New York 0.9999719
## New York-Penn-Central New York 0.6197978
## New York City-Central New York 0.9940387
## New York State-Central New York 1.0000000
## Northeastern New York-Central New York 0.5968282
## Western New York-Central New York 0.2072971
## Hudson Valley-Finger Lakes 0.9437791
## Nassau-Suffolk-Finger Lakes 0.9999960
## New York-Penn-Finger Lakes 0.7122793
## New York City-Finger Lakes 0.9884582
## New York State-Finger Lakes 0.9999999
## Northeastern New York-Finger Lakes 0.7729623
## Western New York-Finger Lakes 0.3279830
## Nassau-Suffolk-Hudson Valley 0.9728569
## New York-Penn-Hudson Valley 0.2118419
## New York City-Hudson Valley 1.0000000
## New York State-Hudson Valley 0.9999831
## Northeastern New York-Hudson Valley 0.1102021
## Western New York-Hudson Valley 0.0303363
## New York-Penn-Nassau-Suffolk 0.9839598
## New York City-Nassau-Suffolk 0.9897149
## New York State-Nassau-Suffolk 0.9999863
## Northeastern New York-Nassau-Suffolk 0.9996720
## Western New York-Nassau-Suffolk 0.9667971
## New York City-New York-Penn 0.3448155
## New York State-New York-Penn 0.9545372
## Northeastern New York-New York-Penn 0.9970230
## Western New York-New York-Penn 1.0000000
## New York State-New York City 0.9999981
## Northeastern New York-New York City 0.3146074
## Western New York-New York City 0.1013307
## Northeastern New York-New York State 0.9938975
## Western New York-New York State 0.9334433
## Western New York-Northeastern New York 0.9739940ny_fit2Tukey = aov(Cerebrovascular.Mortality ~ factor(`Region Name`), data = ny_data)
summary(ny_fit2Tukey)## Df Sum Sq Mean Sq F value Pr(>F)
## factor(`Region Name`) 8 4690 586.2 12.84 3.87e-10 ***
## Residuals 54 2465 45.6
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1TukeyHSD(ny_fit2Tukey)## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = Cerebrovascular.Mortality ~ factor(`Region Name`), data = ny_data)
##
## $`factor(`Region Name`)`
## diff lwr upr
## Finger Lakes-Central New York 0.6424242 -9.168298934 10.45314742
## Hudson Valley-Central New York -15.9194805 -26.472931836 -5.36602920
## Nassau-Suffolk-Central New York -16.3409091 -33.119827293 0.43800911
## New York-Penn-Central New York 2.9090909 -11.307997661 17.12617948
## New York City-Central New York -26.7709091 -38.543776902 -14.99804128
## New York State-Central New York -15.0909091 -37.888969576 7.70715139
## Northeastern New York-Central New York -2.6026738 -11.048882986 5.84353539
## Western New York-Central New York 0.9090909 -9.233270583 11.05145240
## Hudson Valley-Finger Lakes -16.5619048 -27.561921290 -5.56188823
## Nassau-Suffolk-Finger Lakes -16.9833333 -34.046660235 0.07999357
## New York-Penn-Finger Lakes 2.2666667 -12.284987409 16.81832074
## New York City-Finger Lakes -27.4133333 -39.588120618 -15.23854605
## New York State-Finger Lakes -15.7333333 -38.741518634 7.27485197
## Northeastern New York-Finger Lakes -3.2450980 -12.243068844 5.75287277
## Western New York-Finger Lakes 0.2666667 -10.339582696 10.87291603
## Nassau-Suffolk-Hudson Valley -0.4214286 -17.922347702 17.07949056
## New York-Penn-Hudson Valley 18.8285714 3.766178465 33.89096439
## New York City-Hudson Valley -10.8514286 -23.632292818 1.92943567
## New York State-Hudson Valley 0.8285714 -22.505987412 24.16313027
## Northeastern New York-Hudson Valley 13.3168067 3.514331319 23.11928213
## Western New York-Hudson Valley 16.8285714 5.531776706 28.12536615
## New York-Penn-Nassau-Suffolk 19.2500000 -0.675672965 39.17567297
## New York City-Nassau-Suffolk -10.4300000 -28.692180927 7.83218093
## New York State-Nassau-Suffolk 1.2500000 -25.483095549 27.98309555
## Northeastern New York-Nassau-Suffolk 13.7382353 -2.578789109 30.05525970
## Western New York-Nassau-Suffolk 17.2500000 -0.006138975 34.50613898
## New York City-New York-Penn -29.6800000 -45.620538372 -13.73946163
## New York State-New York-Penn -18.0000000 -43.204204193 7.20420419
## Northeastern New York-New York-Penn -5.5117647 -19.180663592 8.15713418
## Western New York-New York-Penn -2.0000000 -16.777274570 12.77727457
## New York State-New York City 11.6800000 -12.230807558 35.59080756
## Northeastern New York-New York City 24.1682353 13.063569344 35.27290124
## Western New York-New York City 27.6800000 15.236421222 40.12357878
## Northeastern New York-New York State 12.4882353 -9.972057475 34.94852806
## Western New York-New York State 16.0000000 -7.151539867 39.15153987
## Western New York-Northeastern New York 3.5117647 -5.846690614 12.87022003
## p adj
## Finger Lakes-Central New York 0.9999999
## Hudson Valley-Central New York 0.0003238
## Nassau-Suffolk-Central New York 0.0619076
## New York-Penn-Central New York 0.9990676
## New York City-Central New York 0.0000000
## New York State-Central New York 0.4591752
## Northeastern New York-Central New York 0.9847517
## Western New York-Central New York 0.9999983
## Hudson Valley-Finger Lakes 0.0003341
## Nassau-Suffolk-Finger Lakes 0.0519779
## New York-Penn-Finger Lakes 0.9998759
## New York City-Finger Lakes 0.0000001
## New York State-Finger Lakes 0.4146541
## Northeastern New York-Finger Lakes 0.9603691
## Western New York-Finger Lakes 1.0000000
## Nassau-Suffolk-Hudson Valley 1.0000000
## New York-Penn-Hudson Valley 0.0049956
## New York City-Hudson Valley 0.1574265
## New York State-Hudson Valley 1.0000000
## Northeastern New York-Hudson Valley 0.0016395
## Western New York-Hudson Valley 0.0003985
## New York-Penn-Nassau-Suffolk 0.0659141
## New York City-Nassau-Suffolk 0.6527334
## New York State-Nassau-Suffolk 1.0000000
## Northeastern New York-Nassau-Suffolk 0.1651907
## Western New York-Nassau-Suffolk 0.0501477
## New York City-New York-Penn 0.0000055
## New York State-New York-Penn 0.3561110
## Northeastern New York-New York-Penn 0.9262125
## Western New York-New York-Penn 0.9999573
## New York State-New York City 0.8121237
## Northeastern New York-New York City 0.0000001
## Western New York-New York City 0.0000001
## Northeastern New York-New York State 0.6842352
## Western New York-New York State 0.4002308
## Western New York-Northeastern New York 0.9502758
I also created a box plot of the data using ggplot (Bedre, 2021) to help visualize the data and see the differences between the regions for cardiovascular and cerebrovascular mortality rates. With the graph below, we can easily identify the disparities across the regions.
library(gridExtra)
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.2.3p1 = ggplot(ny_data, aes(x = `Region Name`, y = Cardiovascular.Mortality, fill = `Region Name`)) + geom_boxplot(outlier.shape = NA) + geom_jitter(width = 0.2) + theme(legend.position="top") + theme(axis.text.x = element_text(size = 5))
p2 = ggplot(ny_data, aes(x = `Region Name`, y = Cerebrovascular.Mortality, fill = `Region Name`)) + geom_boxplot(outlier.shape = NA) + geom_jitter(width = 0.2) + theme(legend.position="top")+ theme(axis.text.x = element_text(size = 5))
grid.arrange(p1,p2, ncol=2)
To verify if there was a liner relationship between cardiovascular and cerebrovascular disease mortality rates and diet (age-adjusted percentage of adults eating 5 or more fruits or vegetables per day at a 95% CI), lack of exercise (age-adjusted percentage of adults who did not participate in leisure time physical activity in last 30 days at a 95% CI.), and regions, I conducted a multilinear regression. My null hypothesis was that the percentages of adults eating 5 or more fruits and vegetables p/day, the percentages of adults who did not participate in leisure time physical activity in the last 30 days, and Regions of New York were not predictors of cardiovascular mortality rates and cerebrovascular rates. My alternate hypothesis was that the percentages of adults eating 5 or more fruits and vegetables p/day, and/or the percentages of adults who did not participate in leisure time physical activity in the last 30 days, and/or Regions of New York were/are predictors of cardiovascular mortality rates and cerebrovascular rates. I used the F-test statistical inference at 0.01. If the p-value was less than 0.01, we rejected the null hypothesis. Below is a screenshot of the R-code and model:
cardiocerebrolm= lm(cbind(Cardiovascular.Mortality, Cerebrovascular.Mortality) ~ `Adults eating 5 or more fruits or vegetables per day`+
`Adults who did not participate in leisure time physical activity in last 30 days`
+ factor(`Region Name`))
summary(cardiocerebrolm)## Response Cardiovascular.Mortality :
##
## Call:
## lm(formula = Cardiovascular.Mortality ~ `Adults eating 5 or more fruits or vegetables per day` +
## `Adults who did not participate in leisure time physical activity in last 30 days` +
## factor(`Region Name`))
##
## Residuals:
## Min 1Q Median 3Q Max
## -130.94 -39.78 -3.17 30.22 121.57
##
## Coefficients:
## Estimate
## (Intercept) 507.923
## `Adults eating 5 or more fruits or vegetables per day` -3.236
## `Adults who did not participate in leisure time physical activity in last 30 days` -1.691
## factor(`Region Name`)Finger Lakes 8.463
## factor(`Region Name`)Hudson Valley -26.738
## factor(`Region Name`)Nassau-Suffolk 20.025
## factor(`Region Name`)New York-Penn 67.981
## factor(`Region Name`)New York City -92.394
## factor(`Region Name`)New York State -10.033
## factor(`Region Name`)Northeastern New York 43.084
## factor(`Region Name`)Western New York 57.412
## Std. Error
## (Intercept) 176.362
## `Adults eating 5 or more fruits or vegetables per day` 2.561
## `Adults who did not participate in leisure time physical activity in last 30 days` 2.337
## factor(`Region Name`)Finger Lakes 25.855
## factor(`Region Name`)Hudson Valley 28.317
## factor(`Region Name`)Nassau-Suffolk 43.945
## factor(`Region Name`)New York-Penn 38.159
## factor(`Region Name`)New York City 52.843
## factor(`Region Name`)New York State 59.803
## factor(`Region Name`)Northeastern New York 22.999
## factor(`Region Name`)Western New York 27.596
## t value
## (Intercept) 2.880
## `Adults eating 5 or more fruits or vegetables per day` -1.264
## `Adults who did not participate in leisure time physical activity in last 30 days` -0.723
## factor(`Region Name`)Finger Lakes 0.327
## factor(`Region Name`)Hudson Valley -0.944
## factor(`Region Name`)Nassau-Suffolk 0.456
## factor(`Region Name`)New York-Penn 1.782
## factor(`Region Name`)New York City -1.748
## factor(`Region Name`)New York State -0.168
## factor(`Region Name`)Northeastern New York 1.873
## factor(`Region Name`)Western New York 2.080
## Pr(>|t|)
## (Intercept) 0.00576
## `Adults eating 5 or more fruits or vegetables per day` 0.21203
## `Adults who did not participate in leisure time physical activity in last 30 days` 0.47276
## factor(`Region Name`)Finger Lakes 0.74472
## factor(`Region Name`)Hudson Valley 0.34943
## factor(`Region Name`)Nassau-Suffolk 0.65051
## factor(`Region Name`)New York-Penn 0.08067
## factor(`Region Name`)New York City 0.08629
## factor(`Region Name`)New York State 0.86741
## factor(`Region Name`)Northeastern New York 0.06665
## factor(`Region Name`)Western New York 0.04243
##
## (Intercept) **
## `Adults eating 5 or more fruits or vegetables per day`
## `Adults who did not participate in leisure time physical activity in last 30 days`
## factor(`Region Name`)Finger Lakes
## factor(`Region Name`)Hudson Valley
## factor(`Region Name`)Nassau-Suffolk
## factor(`Region Name`)New York-Penn .
## factor(`Region Name`)New York City .
## factor(`Region Name`)New York State
## factor(`Region Name`)Northeastern New York .
## factor(`Region Name`)Western New York *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 57.15 on 52 degrees of freedom
## Multiple R-squared: 0.3296, Adjusted R-squared: 0.2006
## F-statistic: 2.556 on 10 and 52 DF, p-value: 0.01361
##
##
## Response Cerebrovascular.Mortality :
##
## Call:
## lm(formula = Cerebrovascular.Mortality ~ `Adults eating 5 or more fruits or vegetables per day` +
## `Adults who did not participate in leisure time physical activity in last 30 days` +
## factor(`Region Name`))
##
## Residuals:
## Min 1Q Median 3Q Max
## -15.416 -3.218 0.000 3.370 13.266
##
## Coefficients:
## Estimate
## (Intercept) 35.97832
## `Adults eating 5 or more fruits or vegetables per day` -0.42712
## `Adults who did not participate in leisure time physical activity in last 30 days` 0.27758
## factor(`Region Name`)Finger Lakes 1.02704
## factor(`Region Name`)Hudson Valley -14.79418
## factor(`Region Name`)Nassau-Suffolk -16.35244
## factor(`Region Name`)New York-Penn 1.40310
## factor(`Region Name`)New York City -32.72582
## factor(`Region Name`)New York State -14.58252
## factor(`Region Name`)Northeastern New York -3.65383
## factor(`Region Name`)Western New York 0.09582
## Std. Error
## (Intercept) 20.77037
## `Adults eating 5 or more fruits or vegetables per day` 0.30162
## `Adults who did not participate in leisure time physical activity in last 30 days` 0.27528
## factor(`Region Name`)Finger Lakes 3.04493
## factor(`Region Name`)Hudson Valley 3.33496
## factor(`Region Name`)Nassau-Suffolk 5.17547
## factor(`Region Name`)New York-Penn 4.49406
## factor(`Region Name`)New York City 6.22340
## factor(`Region Name`)New York State 7.04304
## factor(`Region Name`)Northeastern New York 2.70856
## factor(`Region Name`)Western New York 3.25006
## t value
## (Intercept) 1.732
## `Adults eating 5 or more fruits or vegetables per day` -1.416
## `Adults who did not participate in leisure time physical activity in last 30 days` 1.008
## factor(`Region Name`)Finger Lakes 0.337
## factor(`Region Name`)Hudson Valley -4.436
## factor(`Region Name`)Nassau-Suffolk -3.160
## factor(`Region Name`)New York-Penn 0.312
## factor(`Region Name`)New York City -5.259
## factor(`Region Name`)New York State -2.070
## factor(`Region Name`)Northeastern New York -1.349
## factor(`Region Name`)Western New York 0.029
## Pr(>|t|)
## (Intercept) 0.08917
## `Adults eating 5 or more fruits or vegetables per day` 0.16272
## `Adults who did not participate in leisure time physical activity in last 30 days` 0.31797
## factor(`Region Name`)Finger Lakes 0.73725
## factor(`Region Name`)Hudson Valley 4.78e-05
## factor(`Region Name`)Nassau-Suffolk 0.00263
## factor(`Region Name`)New York-Penn 0.75613
## factor(`Region Name`)New York City 2.77e-06
## factor(`Region Name`)New York State 0.04339
## factor(`Region Name`)Northeastern New York 0.18318
## factor(`Region Name`)Western New York 0.97659
##
## (Intercept) .
## `Adults eating 5 or more fruits or vegetables per day`
## `Adults who did not participate in leisure time physical activity in last 30 days`
## factor(`Region Name`)Finger Lakes
## factor(`Region Name`)Hudson Valley ***
## factor(`Region Name`)Nassau-Suffolk **
## factor(`Region Name`)New York-Penn
## factor(`Region Name`)New York City ***
## factor(`Region Name`)New York State *
## factor(`Region Name`)Northeastern New York
## factor(`Region Name`)Western New York
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.73 on 52 degrees of freedom
## Multiple R-squared: 0.6708, Adjusted R-squared: 0.6074
## F-statistic: 10.59 on 10 and 52 DF, p-value: 1.704e-09
Based on the models above, we cannot reject the null hypothesis for
cardiovascular mortality rates. The p-value was greater than 0.01. There
was no significant evidence that the percentages of adults eating 5 or
more fruits and vegetables per day, percentages of adults who did not
participate in leisure time physical activity in last 30 days, and the
regions of New York when taken together were predictive of
cardiovascular mortality rates.
For cerebrovascular mortality rates, the p-value was less than 0.01. We
can reject the null hypothesis. There is significant evidence that the
percentages of adults eating 5 or more fruits and vegetables per day,
percentages of adults who did not participate in leisure time physical
activity in last 30 days, and the regions of New York when taken
together were predictive of cerebrovascular mortality rates. More
specifically, the regions of Hudson Valley, Nassau-Folk, and New York
City were significant predictors of cerebrovascular mortality rates.
While conducting my analyses, I did encounter some limitations. For the multilinear regression, I received a masking error which I was unable to solve. It analyzed 8 out of the 9 regions. I also wanted to get a clearer criterion of cardiovascular disease. Cardiovascular disease can be numerous conditions such as congenital or hereditary conditions. I believe this could’ve improved my analyses by being more specific on the exact mortality cause.
References
Bedre, R. (2021, October 1). Manova using R (with
examples and code). Data science blog. Retrieved April 29, 2023, from https://www.reneshbedre.com/blog/manova.html
Centers for Disease Control and Prevention. (2022, October 14). Stroke facts. Centers for Disease Control and Prevention. Retrieved April 29, 2023, from https://www.cdc.gov/stroke/facts.htm#:~:text=Stroke%20statistics,-In%202020%2C%201&text=Every%20year%2C%20more%20than%20795%2C000,are%20first%20or%20new%20strokes.&text=About%20185%2C000%20strokes%E2%80%94nearly%201,have%20had%20a%20previous%20stroke.&text=About%2087%25%20of%20all%20strokes,to%20the%20brain%20is%20blocked.
Danielle Navarro (bookdown translation: Emily Kothe). (2019, January 11). Learning statistics with R: A tutorial for psychology students and other beginners. (version 0.6.1). Chapter 16 Factorial ANOVA. Retrieved April 29, 2023, from https://learningstatisticswithr.com/book/anova2.html#factorialanovasimple
Health.data.ny.gov. (2021, February 25). Community health obesity and diabetes related indicators: 2008 - 2012. HealthData.gov. Retrieved April 29, 2023, from https://healthdata.gov/State/Community-Health-Obesity-and-Diabetes-Related-Indi/95h9-42q2
Socioeconomic status and cardiovascular outcomes | circulation. (n.d.). Retrieved April 29, 2023, from https://www.ahajournals.org/doi/10.1161/CIRCULATIONAHA.117.029652.
Zach. (2022, February 23). How to plot multiple linear regression results in R. Statology. Retrieved April 29, 2023, from https://www.statology.org/plot-multiple-linear-regression-in-r/