Created
May 18, 2020 19:33
-
-
Save EoinTravers/b848464200851833d08c34d9b9abc157 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(tidyverse) | |
# Simulate data under 1-cluster solution: | |
# Two Gaussians, with different means, same SD. | |
m1 = 10 | |
m2 = 20 | |
sd = 10 | |
n1 = 50 | |
n2 = 50 | |
x1 = rnorm(n1, m1, sd) | |
x2 = rnorm(n2, m2, sd) | |
data = data.frame( | |
group = rep(c(1, 2), c(n1, n2)), | |
x = c(x1, x2)) | |
ggplot(data, aes(x, fill=factor(group), group=group)) + | |
geom_histogram(position='identity', alpha=.5, binwidth=10) | |
# Means per condition | |
data %>% group_by(group) %>% summarise_at(vars(x), funs(mean=mean, sd=sd)) | |
## # A tibble: 2 x 3 | |
## group mean sd | |
## <dbl> <dbl> <dbl> | |
## 1 1 9.58 11.8 | |
## 2 2 19.4 11.6 | |
# Fit 2-cluster solution | |
k = 2 | |
km = kmeans(x, k) | |
if(km$centers[1] > km$centers[2]){ | |
data$com = ifelse(km$cluster==1, 1, 0) # Cluster 1 is COM | |
} else { | |
data$com = ifelse(km$cluster==2, 1, 0) # Cluster 2 is COM | |
} | |
# Proportion in COM cluster | |
data %>% group_by(group) %>% summarise_at(vars(com), funs(mean=mean, sd=sd)) | |
## # A tibble: 2 x 3 | |
## group mean sd | |
## <dbl> <dbl> <dbl> | |
## 1 1 0.38 0.490 | |
## 2 2 0.68 0.471 | |
glm(com ~ group, data=data, family=binomial) %>% summary() | |
## | |
## Call: | |
## glm(formula = com ~ group, family = binomial, data = data) | |
## | |
## Deviance Residuals: | |
## Min 1Q Median 3Q Max | |
## -1.5096 -0.9778 0.8782 0.8782 1.3911 | |
## | |
## Coefficients: | |
## Estimate Std. Error z value Pr(>|z|) | |
## (Intercept) -1.7329 0.6569 -2.638 0.00834 ** | |
## group 1.2433 0.4205 2.957 0.00311 ** | |
## --- | |
## Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 | |
## | |
## (Dispersion parameter for binomial family taken to be 1) | |
## | |
## Null deviance: 138.27 on 99 degrees of freedom | |
## Residual deviance: 129.09 on 98 degrees of freedom | |
## AIC: 133.09 | |
## | |
## Number of Fisher Scoring iterations: 4 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment