Homework6
2025-02-19
Question 1-3
We are using a data set collected from an annual survey provided to the Vermont Beekeepers Association to better understand the social demographic of the organization and member satisfaction with aspects of the organization. We aim to better support minority demographics by understanding the satisfaction rating among these groups.
ds <- read.csv("Annual Survey Results - 2025 Winter meeting.csv")
head(ds)## Annual_meetings Mentorship_program Access_resources
## 1 Satisfied No prior experience Neutral
## 2 Satisfied No prior experience Very satisfied
## 3 Very satisfied Satisfied
## 4 Very satisfied No prior experience No prior experience
## 5 No prior experience No prior experience Very satisfied
## 6 No prior experience No prior experience No prior experience
## Educational_workshops Industry_policy_insights Networking_opportunities
## 1 Neutral Satisfied Satisfied
## 2 Very satisfied Satisfied Satisfied
## 3 Satisfied Satisfied Very satisfied
## 4 No prior experience No prior experience Very satisfied
## 5 Very satisfied Very satisfied No prior experience
## 6 No prior experience No prior experience No prior experience
## News_updates Marketing_social
## 1 Satisfied Satisfied
## 2 Satisfied Satisfied
## 3 Satisfied Satisfied
## 4 Very satisfied Very satisfied
## 5 Very satisfied No prior experience
## 6 No prior experience No prior experience
## Option_to_explain Speaker.Name.s..
## 1 NA
## 2 NA
## 3 NA
## 4 Cant sign onto website as a member to renew membership NA
## 5 NA
## 6 NA
## Topic.s.. Speaker.Category
## 1
## 2
## 3
## 4 Types of hives pros & cons Hive management techniques
## 5
## 6
## Workshop.Topic.s..
## 1
## 2
## 3 Making nucs, overwinter splits
## 4 Types of hives pros & cons
## 5 Beginner beekeeping, treating for mites
## 6 First time beekeeping
## Workshop.Category Age Gender Race
## 1 55-64 Male White
## 2 35-54 Male White
## 3 Preparing for winter, Hive management techniques 65+ Male White
## 4 Hive management techniques 55-64 Male White
## 5 Pests and pathogens 65+ Female White
## 6 Hive management techniques
## Location Scale Beekeeping_experience
## 1 Southern Vermont Hobbyist Beekeeper (<25 colonies) 10+
## 2 Northwest Vermont Hobbyist Beekeeper (<25 colonies) 4-6
## 3 Western Vermont Hobbyist Beekeeper (<25 colonies) 4-6
## 4 Other Sideliner Beekeeper (25-300 colonies) 4-6
## 5 Central Vermont Hobbyist Beekeeper (<25 colonies) 0-3
## 6Question 4 & 5: Analyzing the data multiple times/ Graphing the data
Instead of changing parameters, we analyzed several questions using different aspects of the data set.
library(ggplot2)
ggplot(data = ds, aes(x = factor(Mentorship_program), fill = Gender)) +
geom_bar(position = "dodge")
We used chi-squared tests to calculate the significance of our categorical data.
- Are the proportion of women that are unsatisfied with the mentorship program significantly different from men?
# Create a new column that indicates whether a person is unsatisfied or not
ds$Mentorship_programClean <- ifelse(ds$Mentorship_program %in% c("Unsatisfied", "Very Unsatisfied", "Neutral"), "Unsatisfied", "Satisfied")
# Create a contingency table for gender vs unsatisfaction status
contingency_table <- table(ds$Gender, ds$Mentorship_programClean)
# Perform the Chi-squared test
chi_squared_test <- chisq.test(contingency_table)## Warning in chisq.test(contingency_table): Chi-squared approximation may be
## incorrect# Print the results of the test
print(chi_squared_test)##
## Pearson's Chi-squared test
##
## data: contingency_table
## X-squared = 6.3283, df = 2, p-value = 0.04225# Get the standardized residuals
standardized_residuals <- chi_squared_test$stdres
#Priint residuals
print(standardized_residuals)##
## Satisfied Unsatisfied
## -2.36098808 2.36098808
## Female 0.08511831 -0.08511831
## Male 2.06772205 -2.06772205print(contingency_table)##
## Satisfied Unsatisfied
## 7 5
## Female 9 2
## Male 18 1- Are beekeepers with more years of beekeeping experience more likely to be satisfied with networking activities?
# Create a new column that indicates whether a person is unsatisfied or not
ds$Networking_opportunitiesClean <- ifelse(ds$Networking_opportunities %in% c("Unsatisfied", "Very Unsatisfied", "Neutral"), "Unsatisfied", "Satisfied")
# Create a contingency table for gender vs unsatisfaction status
contingency_table2 <- table(ds$Beekeeping_experience, ds$Networking_opportunitiesClean)
print(contingency_table2)##
## Satisfied Unsatisfied
## 9 3
## 0-3 7 1
## 10+ 6 1
## 4-6 10 1
## 7-10 4 0# Perform the Chi-squared test
chi_squared_test2 <- chisq.test(contingency_table2)## Warning in chisq.test(contingency_table2): Chi-squared approximation may be
## incorrect# Print the results of the test
print(chi_squared_test2)##
## Pearson's Chi-squared test
##
## data: contingency_table2
## X-squared = 2.0549, df = 4, p-value = 0.7257# Get the standardized residuals
standardized_residuals2 <- chi_squared_test2$stdres
#Priint residuals
print(standardized_residuals2)##
## Satisfied Unsatisfied
## -1.2549900 1.2549900
## 0-3 0.1604222 -0.1604222
## 10+ 0.0000000 0.0000000
## 4-6 0.5731019 -0.5731019
## 7-10 0.8583951 -0.8583951Question 6-9: For loops
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union# list to store results
proportion_results <- list()
# Loop through each gender
for (gender in c("Male", "Female")) {
# Subset the data for this gender group
gender_data <- ds[ds$Gender == gender, ]
# list to store proportions for this gender
gender_proportions <- list()
# Loop through each column
for (column in c("Annual_meetings", "Mentorship_program", "Access_resources", "Educational_workshops", "Industry_policy_insights", "Networking_opportunities", "News_updates", "Marketing_social")) {
# Calculate the proportion of each category for this column
prop_very_satisfied <- mean(gender_data[[column]] == "Very satisfied") * 100
prop_satisfied <- mean(gender_data[[column]] == "Satisfied") * 100
prop_unsatisfied <- mean(gender_data[[column]] == "Unsatisfied") * 100
prop_very_unsatisfied <- mean(gender_data[[column]] == "Very unsatisfied") * 100
prop_neutral <- mean(gender_data[[column]] == "Neutral") * 100
prop_noexperience <- mean(gender_data[[column]] == "No prior experience") * 100
# Store the results in the list
gender_proportions[[column]] <- c("Very satisfied" = prop_very_satisfied,
"Satisfied" = prop_satisfied,
"Unsatisfied" = prop_unsatisfied,
"Very unsatisfied" = prop_very_unsatisfied,
"Neutral" = prop_neutral,
"No prior expreience" = prop_noexperience)
}
# Store the results for this gender
proportion_results[[gender]] <- gender_proportions
}
# Print the results
print(proportion_results)## $Male
## $Male$Annual_meetings
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 36.842105 31.578947 0.000000 0.000000
## Neutral No prior expreience
## 5.263158 26.315789
##
## $Male$Mentorship_program
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 15.789474 5.263158 5.263158 0.000000
## Neutral No prior expreience
## 0.000000 63.157895
##
## $Male$Access_resources
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 31.578947 36.842105 0.000000 0.000000
## Neutral No prior expreience
## 5.263158 21.052632
##
## $Male$Educational_workshops
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 52.631579 21.052632 0.000000 0.000000
## Neutral No prior expreience
## 5.263158 15.789474
##
## $Male$Industry_policy_insights
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 42.10526 26.31579 0.00000 0.00000
## Neutral No prior expreience
## 10.52632 15.78947
##
## $Male$Networking_opportunities
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 47.368421 26.315789 0.000000 0.000000
## Neutral No prior expreience
## 5.263158 15.789474
##
## $Male$News_updates
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 31.57895 47.36842 0.00000 0.00000
## Neutral No prior expreience
## 0.00000 15.78947
##
## $Male$Marketing_social
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 31.57895 36.84211 0.00000 0.00000
## Neutral No prior expreience
## 15.78947 10.52632
##
##
## $Female
## $Female$Annual_meetings
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 9.090909 27.272727 0.000000 0.000000
## Neutral No prior expreience
## 9.090909 45.454545
##
## $Female$Mentorship_program
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 27.272727 0.000000 9.090909 9.090909
## Neutral No prior expreience
## 9.090909 27.272727
##
## $Female$Access_resources
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 27.272727 36.363636 0.000000 9.090909
## Neutral No prior expreience
## 9.090909 9.090909
##
## $Female$Educational_workshops
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 54.545455 27.272727 0.000000 9.090909
## Neutral No prior expreience
## 0.000000 0.000000
##
## $Female$Industry_policy_insights
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 36.363636 0.000000 0.000000 9.090909
## Neutral No prior expreience
## 18.181818 18.181818
##
## $Female$Networking_opportunities
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 27.272727 18.181818 9.090909 9.090909
## Neutral No prior expreience
## 9.090909 9.090909
##
## $Female$News_updates
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 63.636364 0.000000 9.090909 9.090909
## Neutral No prior expreience
## 0.000000 0.000000
##
## $Female$Marketing_social
## Very satisfied Satisfied Unsatisfied Very unsatisfied
## 27.272727 18.181818 0.000000 9.090909
## Neutral No prior expreience
## 18.181818 18.181818