Survey clustering
# import an excel file
mydata <- read_excel("C:/Users/eneja/OneDrive/Namizje/IMB R/anketa10.xlsx")
# delete first row in which the questions are written
mydata <- mydata[-1,]
# add an ID variable
mydata$ID <- 1:nrow(mydata)
mydata <- mydata[,c(93, 1:92)]
head(mydata)## # A tibble: 6 × 93
## ID Q1 Q2 Q3 Q4 Q5 Q6a Q6b Q6c Q6d Q7a_1 Q7b_1 Q7c_1 Q7d_1 Q7e_1 Q7f_1 Q8a Q8b Q8c Q8d Q9a
## <int> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr> <chr> <chr> <chr>
## 1 1 7 2 -2 -2 -2 1 5 5 5 7 10 16 16 16 80 3 5 2 4 5
## 2 2 6 2 -2 -2 -2 3 4 5 3 0 22 59 0 23 57 4 4 1 4 5
## 3 3 5 2 -2 -2 -2 4 4 3 3 0 26 63 17 0 100 4 2 2 4 4
## 4 4 7 1 3 4 2 5 4 3 2 82 0 85 63 85 100 5 4 1 4 5
## 5 5 7 2 -2 -2 -2 4 2 4 5 0 0 0 0 25 50 5 1 1 1 5
## 6 6 7 1 3 4 2 4 4 4 2 0 0 -1 0 0 70 4 4 1 2 5
## # … with 72 more variables: Q9b <chr>, Q9c <chr>, Q9d <chr>, Q10a <chr>, Q10b <chr>, Q10c <chr>, Q10d <chr>, Q10e <chr>,
## # Q10f <chr>, Q10g <chr>, Q10h <chr>, Q11 <chr>, Q11_9_text <chr>, Q12a <chr>, Q12b <chr>, Q12c <chr>, Q12d <chr>, Q12e <chr>,
## # Q12f <chr>, Q13a <chr>, Q13b <chr>, Q13c <chr>, Q13d <chr>, Q13e <chr>, Q14a <chr>, Q14b <chr>, Q14c <chr>, Q14d <chr>,
## # Q14e <chr>, Q15a <chr>, Q15b <chr>, Q15c <chr>, Q15d <chr>, Q15e <chr>, Q16a <chr>, Q16b <chr>, Q16c <chr>, Q16d <chr>,
## # Q16e <chr>, Q17a <chr>, Q17b <chr>, Q17c <chr>, Q17d <chr>, Q17e <chr>, Q18a <chr>, Q18b <chr>, Q18c <chr>, Q18d <chr>,
## # Q18e <chr>, Q19 <chr>, Q20 <chr>, Q21 <chr>, Q22 <chr>, Q22_4_text <chr>, Q23 <chr>, Q24a <chr>, Q24b <chr>, Q24c <chr>,
## # Q24d <chr>, Q24e <chr>, Q24f <chr>, Q24g <chr>, Q24h <chr>, Q24i <chr>, Q24j <chr>, Q24k <chr>, Q24l <chr>, …Description:
- ID: Respondents ID.
- Q1: Age select
- Q2: Ever borrowed more then 300 EUR?
- Q3: Max amount ever borrowed?
- Q4: Rate borrowing experience 1 -5.
- Q5: From whom borrowed the greatest amount?
- Q6a: Borrowing a necessary part of life? 1 - 5.
- Q6b: Feel burdened by the loan repaying? 1-5
- Q6c: Rather postpone a purchase than borrow? 1-5
- Q6d: Am confident that will not need to borrow before the age of 27. 1-5 Financing in the future 0-only savings, 100-only loans
- Q7a_1: Electronics
- Q7b_1: Furniture
- Q7c_1: Cars and motors
- Q7d_1: Medical and cosmetics surgeries
- Q7e_1: Education
- Q7f_1: Real estate If borrowing up to 25.000EUR, will probably from the following sources 1-5
- Q8a: Bank
- Q8b: Family
- Q8c: Friends
- Q8d: Commercial loans If borrowing above to 25.000EUR, will probably from the following sources 1-5
- Q9a: Bank
- Q9b: Family
- Q9c: Friends
- Q9d: Commercial loans If wanted to know more about finance, would search for information at 1-5
- Q10a: Bank employee
- Q10b: Family member
- Q10c: Friend
- Q10d: At school
- Q10e: Social media
- Q10f: Bank website
- Q10g: Financial literature
- Q10h: Internet
- Q11: Main obstacle for not borrowing from the bank
- Q11_9_text: Other options for Q11 How much you agree with the following 1-5
- Q12a: Bank have good reputation as money lender
- Q12b: Bank loans represent opportunity for the future
- Q12c: Positive perception on loan getting procedure
- Q12d: Would change bank if got better offer
- Q12e: Would only borrow from the bank if did not have other choice
- Q12f: Bank provide me all the necessary information How important are the following factors when choosing a lender 1-5
- Q13a: Clarity of conditions
- Q13b: Flexibility of repayment
- Q13c: Cost of borrowing
- Q13d: Simplicity of the procedure
- Q14d: …
#For those who did not move only one slider for question 7, insert 50 (midpoint - half savings, half loans) as the selected value
mydata$Q7a_1 <- ifelse((mydata$Q7a_1==-1)&(mydata$Q7b_1!=-1)&(mydata$Q7c_1!=-1)&(mydata$Q7d_1!=-1)&(mydata$Q7e_1!=-1)&(mydata$Q7f_1!=-1),50, mydata$Q7a_1)
mydata$Q7b_1 <- ifelse((mydata$Q7a_1!=-1)&(mydata$Q7b_1==-1)&(mydata$Q7c_1!=-1)&(mydata$Q7d_1!=-1)&(mydata$Q7e_1!=-1)&(mydata$Q7f_1!=-1),50,mydata$Q7b_1)
mydata$Q7c_1 <- ifelse((mydata$Q7a_1!=-1)&(mydata$Q7b_1!=-1)&(mydata$Q7c_1==-1)&(mydata$Q7d_1!=-1)&(mydata$Q7e_1!=-1)&(mydata$Q7f_1!=-1),50,mydata$Q7c_1)
mydata$Q7d_1 <- ifelse((mydata$Q7a_1!=-1)&(mydata$Q7b_1!=-1)&(mydata$Q7c_1!=-1)&(mydata$Q7d_1==-1)&(mydata$Q7e_1!=-1)&(mydata$Q7f_1!=-1),50,mydata$Q7d_1)
mydata$Q7e_1 <- ifelse((mydata$Q7a_1!=-1)&(mydata$Q7b_1!=-1)&(mydata$Q7c_1!=-1)&(mydata$Q7d_1!=-1)&(mydata$Q7e_1==-1)&(mydata$Q7f_1!=-1),50,mydata$Q7e_1)
mydata$Q7f_1 <- ifelse((mydata$Q7a_1!=-1)&(mydata$Q7b_1!=-1)&(mydata$Q7c_1!=-1)&(mydata$Q7d_1!=-1)&(mydata$Q7e_1!=-1)&(mydata$Q7f_1==-1),50,mydata$Q7f_1)#Identify values -1,-3 and replace them with NA. Identify also the -2
# -1 means: The person has not answered the specific question
# -2 means: Person did not respond because it did not satisfy if sentence
# -3 means: Person stopped answering questionnaire before coming to this sentence
mydata[mydata == -1] <- NA
mydata[mydata == -3] <- NA
# Get rid of those that are under 18 and over 27
mydata_t1<-mydata[!(mydata$Q2=="-2"),]
#solve some problems with 1ka (illogical -2 values)
mydata_t1 <- mydata_t1[!(mydata_t1$Q13a=="-2"),]
mydata_dropNA<-mydata_t1
mydata_dropNA <- na.omit(mydata_dropNA)# convert character to integer, except the variables where Other was typed in
mydata_dropNA <- mydata_dropNA %>%
mutate_at(c(2:33), as.integer)
mydata_dropNA <- mydata_dropNA %>%
mutate_at(c(35:74), as.integer)
mydata_dropNA <- mydata_dropNA %>%
mutate_at(c(76:88), as.integer)
mydata_dropNA <- mydata_dropNA %>%
mutate_at(c(89:93), as.integer)## Warning in mask$eval_all_mutate(quo): NAs introduced by coercionmydata_dropNA$Q1 <- mydata_dropNA$Q1 + 16Transform fo factors
mydata_dropNA$Sex_F <- factor(mydata_dropNA$Q19,
levels = c(1, 2,3),
labels = c("Female", "Male", "Other"))
mydata_dropNA$Region_F <- factor(mydata_dropNA$Q20,
levels = c(1,2, 3, 4, 5, 6, 7, 8, 9),
labels = c("Ljubljana z okolico","Štajerska","Prekmurje", "Dolenjska","Primorska" , "Gorenjska" , "Goriška", "Koroška" , "Notranjska"))
mydata_dropNA$Status_F <- factor(mydata_dropNA$Q22,
levels = c(1,2, 3),
labels = c("Single","In a relationship","Married"))
mydata_dropNA$Children_F <- factor(mydata_dropNA$Q23,
levels = c(2, 1),
labels = c("No", "Yes"))
mydata_dropNA$Education_F <- factor(mydata_dropNA$Q25,
levels = c(1,2,3,4,5),
labels = c("Primary school", "High school", "Vocational School", "Undergraduate", "Post-Graduate"))
mydata_dropNA$Employed_F <- factor(mydata_dropNA$Q26,
levels = c(2, 1),
labels = c("No", "Yes"))
head(mydata_dropNA)## # A tibble: 6 × 99
## ID Q1 Q2 Q3 Q4 Q5 Q6a Q6b Q6c Q6d Q7a_1 Q7b_1 Q7c_1 Q7d_1 Q7e_1 Q7f_1 Q8a Q8b Q8c Q8d Q9a
## <int> <dbl> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int> <int>
## 1 1 23 2 -2 -2 -2 1 5 5 5 7 10 16 16 16 80 3 5 2 4 5
## 2 2 22 2 -2 -2 -2 3 4 5 3 0 22 59 0 23 57 4 4 1 4 5
## 3 3 21 2 -2 -2 -2 4 4 3 3 0 26 63 17 0 100 4 2 2 4 4
## 4 4 23 1 3 4 2 5 4 3 2 82 0 85 63 85 100 5 4 1 4 5
## 5 5 23 2 -2 -2 -2 4 2 4 5 0 0 0 0 25 50 5 1 1 1 5
## 6 6 23 1 3 4 2 4 4 4 2 0 0 50 0 0 70 4 4 1 2 5
## # … with 78 more variables: Q9b <int>, Q9c <int>, Q9d <int>, Q10a <int>, Q10b <int>, Q10c <int>, Q10d <int>, Q10e <int>,
## # Q10f <int>, Q10g <int>, Q10h <int>, Q11 <int>, Q11_9_text <chr>, Q12a <int>, Q12b <int>, Q12c <int>, Q12d <int>, Q12e <int>,
## # Q12f <int>, Q13a <int>, Q13b <int>, Q13c <int>, Q13d <int>, Q13e <int>, Q14a <int>, Q14b <int>, Q14c <int>, Q14d <int>,
## # Q14e <int>, Q15a <int>, Q15b <int>, Q15c <int>, Q15d <int>, Q15e <int>, Q16a <int>, Q16b <int>, Q16c <int>, Q16d <int>,
## # Q16e <int>, Q17a <int>, Q17b <int>, Q17c <int>, Q17d <int>, Q17e <int>, Q18a <int>, Q18b <int>, Q18c <int>, Q18d <int>,
## # Q18e <int>, Q19 <int>, Q20 <int>, Q21 <int>, Q22 <int>, Q22_4_text <chr>, Q23 <int>, Q24a <int>, Q24b <int>, Q24c <int>,
## # Q24d <int>, Q24e <int>, Q24f <int>, Q24g <int>, Q24h <int>, Q24i <int>, Q24j <int>, Q24k <int>, Q24l <int>, …#mydata_dropNA <- mydata_dropNA[-c(255, 231, 107, 180, 188, 124),]
#mydata_dropNA <- mydata_dropNA[-c(112, 27, 212, 16, 216, 87, 291, 39, 188, 280, 300, 299, 3, 190, 140, 225, 103, 278, 101, 4, 217, 100, 171, 185, 211, 168, 167),]summary(mydata_dropNA[c("Q12f", "Q12a", "Q10a", "Q10f","Q10g")])## Q12f Q12a Q10a Q10f Q10g
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:3.000
## Median :3.000 Median :3.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.246 Mean :2.693 Mean :3.706 Mean :3.689 Mean :3.557
## 3rd Qu.:4.000 3rd Qu.:3.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000library(Hmisc)
rcorr(as.matrix(mydata_dropNA[ , c("Q12f", "Q12a", "Q10a", "Q10f","Q10g")]),
type = "pearson") ## Q12f Q12a Q10a Q10f Q10g
## Q12f 1.00 0.37 0.20 0.17 0.01
## Q12a 0.37 1.00 0.19 0.20 0.09
## Q10a 0.20 0.19 1.00 0.26 0.02
## Q10f 0.17 0.20 0.26 1.00 0.33
## Q10g 0.01 0.09 0.02 0.33 1.00
##
## n= 309
##
##
## P
## Q12f Q12a Q10a Q10f Q10g
## Q12f 0.0000 0.0003 0.0021 0.9296
## Q12a 0.0000 0.0008 0.0004 0.1102
## Q10a 0.0003 0.0008 0.0000 0.7763
## Q10f 0.0021 0.0004 0.0000 0.0000
## Q10g 0.9296 0.1102 0.7763 0.0000mydata_std <- as.data.frame(scale(mydata_dropNA[c("Q12f", "Q12a", "Q10a", "Q10f","Q10g")]))#mydata_std$Dissimilarity <- sqrt(mydata_std$Q12f^2 + mydata_std$Q12a^2 + mydata_std$Q10a^2 + mydata_std$Q10f^2 + mydata_std$Q10g^2)#head(mydata_std[order(-mydata_std$Dissimilarity), ], 5) #Finding top 5 objects with highest value of dissimilarity#mydata_dropNA <- mydata_dropNA[-c(39, 179),]
mydata1 <- mydata_stdlibrary(factoextra)
#Finding Eudlidean distances, based on 6 Cluster variables, then saving them into object Distances
Distances <- get_dist(mydata1,
method = "euclidian")
Distances2 <- Distances^2
fviz_dist(Distances2) #Showing matrix of distances
library(factoextra)
get_clust_tendency(mydata1, #Hopkins statistics
n = nrow(mydata1) - 1,
graph = FALSE) ## $hopkins_stat
## [1] 0.5365047
##
## $plot
## NULLlibrary(dplyr)
WARD <- mydata1 %>% #Selecting variables
get_dist(method = "euclidean") %>% #Selecting distance
hclust(method = "ward.D2") #Selecting algorithm
WARD##
## Call:
## hclust(d = ., method = "ward.D2")
##
## Cluster method : ward.D2
## Distance : euclidean
## Number of objects: 309library(factoextra)
fviz_dend(WARD) #Dendrogram## Warning: The `<scale>` argument of `guides()` cannot be `FALSE`. Use "none" instead as of ggplot2 3.3.4.
## ℹ The deprecated feature was likely used in the factoextra package.
## Please report the issue at <]8;;https://github.com/kassambara/factoextra/issueshttps://github.com/kassambara/factoextra/issues]8;;>.
set.seed(1)
#install.packages("NbClust")
library(NbClust)
OptNumber <- mydata1[c("Q12f", "Q12a", "Q10a", "Q10f","Q10g")] %>%
#scale() %>%
NbClust(distance = "euclidean",
min.nc = 2, max.nc = 10,
method = "ward.D2",
index = "all") 
## *** : The Hubert index is a graphical method of determining the number of clusters.
## In the plot of Hubert index, we seek a significant knee that corresponds to a
## significant increase of the value of the measure i.e the significant peak in Hubert
## index second differences plot.
## 
## *** : The D index is a graphical method of determining the number of clusters.
## In the plot of D index, we seek a significant knee (the significant peak in Dindex
## second differences plot) that corresponds to a significant increase of the value of
## the measure.
##
## *******************************************************************
## * Among all indices:
## * 6 proposed 2 as the best number of clusters
## * 9 proposed 3 as the best number of clusters
## * 2 proposed 4 as the best number of clusters
## * 2 proposed 7 as the best number of clusters
## * 4 proposed 10 as the best number of clusters
##
## ***** Conclusion *****
##
## * According to the majority rule, the best number of clusters is 3
##
##
## *******************************************************************mydata1$ClusterWard <- cutree(WARD,
k = 4) #Number of groups
head(mydata1[c( "ClusterWard")])## ClusterWard
## 1 1
## 2 1
## 3 1
## 4 2
## 5 3
## 6 3#Calculating positions of initial leaders
Initial_leaders <- aggregate(mydata1[, c("Q12f", "Q12a", "Q10a", "Q10f","Q10g")],
by = list(mydata1$ClusterWard),
FUN = mean)
Initial_leaders## Group.1 Q12f Q12a Q10a Q10f Q10g
## 1 1 0.46680896 0.84433703 0.1711896 0.5834527 0.4412628
## 2 2 -0.80102794 -0.95014985 -1.8107988 -1.0007866 -0.1160526
## 3 3 -0.07326677 -0.08358824 0.1897904 -0.4610423 -0.6686174
## 4 4 -0.17242822 -0.82240671 0.6564186 0.6265551 0.6906379library(factoextra)
kmeans_clu <- hkmeans(mydata1, #Data
k = 4, #Number of groups
hc.metric = "euclidean", #Distance for hierar. clus.
hc.method = "ward.D2") #Algorithm for hierar. clus.
kmeans_clu## Hierarchical K-means clustering with 4 clusters of sizes 105, 41, 108, 55
##
## Cluster means:
## Q12f Q12a Q10a Q10f Q10g ClusterWard
## 1 0.46680896 0.8443370 0.1711896 0.5834527 0.44126283 1.000000
## 2 -0.83840688 -0.9968851 -1.8328144 -0.8751368 0.02533057 2.097561
## 3 -0.01503778 -0.0078471 0.2024982 -0.5478557 -0.75196831 2.972222
## 4 -0.23665779 -0.8533747 0.6418305 0.6142997 0.61529868 3.909091
##
## Clustering vector:
## [1] 1 1 1 2 3 3 3 3 4 1 3 1 1 3 3 4 4 2 2 1 1 1 3 2 3 3 1 3 2 2 4 4 3 3 1 1 1 2 2 1 3 4 1 3 1 1 1 1 1 1 4 1 1 4 3 3 4 3 3 4 3 2
## [63] 4 1 3 1 1 3 1 1 3 1 3 3 1 1 1 2 4 1 4 1 1 3 1 4 3 1 1 3 1 1 1 1 4 1 3 3 1 1 1 3 4 3 3 1 2 1 3 1 3 1 3 3 1 3 2 4 3 4 1 1 2 2
## [125] 1 1 1 3 3 4 3 4 1 3 3 4 4 3 2 3 1 2 1 1 3 3 3 1 3 4 4 3 3 4 3 1 4 1 4 3 1 1 3 3 1 3 4 2 1 4 4 3 1 1 3 1 3 1 3 2 4 3 2 1 3 3
## [187] 1 2 1 3 1 3 1 1 2 3 3 2 3 3 2 3 3 1 1 3 3 3 3 3 2 3 1 3 4 3 1 1 1 3 4 1 1 3 2 3 3 3 2 3 2 3 1 2 3 3 1 1 2 3 1 1 2 4 4 4 3 4
## [249] 1 4 2 2 2 1 2 1 3 3 3 3 1 4 4 1 2 3 4 1 3 1 4 4 1 2 4 3 1 3 3 1 2 2 2 4 4 1 1 2 3 4 3 4 4 4 4 1 4 3 3 2 3 4 1 1 3 3 4 4 3
##
## Within cluster sum of squares by cluster:
## [1] 227.7933 220.3647 372.5455 129.3344
## (between_SS / total_SS = 50.5 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss" "betweenss" "size" "iter"
## [9] "ifault" "data" "hclust"library(factoextra)
fviz_cluster(kmeans_clu,
palette = "Set1",
repel = TRUE,
ggtheme = theme_bw())## Warning: ggrepel: 234 unlabeled data points (too many overlaps). Consider increasing max.overlaps
mydata1$ClusterK_Means <- kmeans_clu$cluster
head(mydata1[c( "ClusterWard", "ClusterK_Means")])## ClusterWard ClusterK_Means
## 1 1 1
## 2 1 1
## 3 1 1
## 4 2 2
## 5 3 3
## 6 3 3#Checking for reclassifications
table(mydata1$ClusterWard)##
## 1 2 3 4
## 105 40 114 50table(mydata1$ClusterK_Means)##
## 1 2 3 4
## 105 41 108 55table(mydata1$ClusterWard, mydata1$ClusterK_Means)##
## 1 2 3 4
## 1 105 0 0 0
## 2 0 37 3 0
## 3 0 4 105 5
## 4 0 0 0 50Centroids <- kmeans_clu$centers
Centroids## Q12f Q12a Q10a Q10f Q10g ClusterWard
## 1 0.46680896 0.8443370 0.1711896 0.5834527 0.44126283 1.000000
## 2 -0.83840688 -0.9968851 -1.8328144 -0.8751368 0.02533057 2.097561
## 3 -0.01503778 -0.0078471 0.2024982 -0.5478557 -0.75196831 2.972222
## 4 -0.23665779 -0.8533747 0.6418305 0.6142997 0.61529868 3.909091library(ggplot2)
library(tidyr)##
## Attaching package: 'tidyr'## The following object is masked from 'package:magrittr':
##
## extractFigure <- as.data.frame(Centroids)
Figure$id <- 1:nrow(Figure)
Figure <- pivot_longer(Figure, cols = c(Q12f, Q12a, Q10a, Q10f, Q10g))
Figure$Groups <- factor(Figure$id,
levels = c(1, 2, 3, 4),
labels = c("1", "2", "3", "4"))
Figure$nameFactor <- factor(Figure$name,
levels = c("Q12f", "Q12a", "Q10a", "Q10f","Q10g"),
labels = c("Transparency", "Reputation", "B_Consultant", "Bank_website", "Literature"))
ggplot(Figure, aes(x = nameFactor, y = value)) +
geom_hline(yintercept = 0) +
theme_bw() +
geom_point(aes(shape = Groups, col = Groups), size = 3) +
geom_line(aes(group = id), linewidth = 1) +
ylab("Averages") +
xlab("Cluster variables")+
ylim(-2.0, 1.5)
#Checking if clustering variables successfully differentiate between groups
fit <- aov(cbind(Q12f, Q12a, Q10a, Q10f, Q10g) ~ as.factor(ClusterK_Means),
data = mydata1)
summary(fit)## Response Q12f :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(ClusterK_Means) 3 54.805 18.2685 22.006 6.302e-13 ***
## Residuals 305 253.195 0.8301
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Q12a :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(ClusterK_Means) 3 155.66 51.887 103.88 < 2.2e-16 ***
## Residuals 305 152.34 0.499
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Q10a :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(ClusterK_Means) 3 167.89 55.963 121.82 < 2.2e-16 ***
## Residuals 305 140.11 0.459
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Q10f :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(ClusterK_Means) 3 120.31 40.105 65.173 < 2.2e-16 ***
## Residuals 305 187.69 0.615
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Q10g :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(ClusterK_Means) 3 102.36 34.121 50.608 < 2.2e-16 ***
## Residuals 305 205.64 0.674
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1aggregate(mydata_dropNA$Q28,
by = list(mydata1$ClusterK_Means),
FUN = "mean")## Group.1 x
## 1 1 2.190476
## 2 2 1.634146
## 3 3 2.453704
## 4 4 1.890909fit <- aov(mydata_dropNA$Q28 ~ as.factor(ClusterK_Means),
data = mydata1)
summary(fit)## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(ClusterK_Means) 3 24.7 8.242 4.205 0.00618 **
## Residuals 305 597.8 1.960
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1aggregate(mydata_dropNA$Q24b,
by = list(mydata1$ClusterK_Means),
FUN = "mean")## Group.1 x
## 1 1 0.3809524
## 2 2 0.4390244
## 3 3 0.4722222
## 4 4 0.4909091aggregate(mydata_dropNA$Q25,
by = list(mydata1$ClusterK_Means),
FUN = "mean")## Group.1 x
## 1 1 3.476190
## 2 2 3.097561
## 3 3 3.129630
## 4 4 3.472727aggregate(mydata_dropNA$Q9a,
by = list(mydata1$ClusterK_Means),
FUN = "mean")## Group.1 x
## 1 1 4.600000
## 2 2 3.707317
## 3 3 4.296296
## 4 4 4.436364aggregate(mydata_dropNA$Q22,
by = list(mydata1$ClusterK_Means),
FUN = "mean")## Group.1 x
## 1 1 1.495238
## 2 2 1.658537
## 3 3 1.537037
## 4 4 1.563636aggregate(mydata_dropNA$Q26,
by = list(mydata1$ClusterK_Means),
FUN = "mean")## Group.1 x
## 1 1 1.580952
## 2 2 1.560976
## 3 3 1.620370
## 4 4 1.618182aggregate(mydata_dropNA$Q23,
by = list(mydata1$ClusterK_Means),
FUN = "mean")## Group.1 x
## 1 1 1.971429
## 2 2 1.975610
## 3 3 1.981481
## 4 4 1.945455