Su_Yizhan_Homework_3”
Yizhan Su
2024-03-12
# List of packages
packages <- c("tidyverse", "infer", "fst") # add any you need here
# Install packages if they aren't installed already
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
# Load the packages
lapply(packages, library, character.only = TRUE)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors## Warning: package 'infer' was built under R version 4.3.3## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "infer" "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [7] "readr" "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [13] "graphics" "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "fst" "infer" "lubridate" "forcats" "stringr" "dplyr"
## [7] "purrr" "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"ess <- read_fst("All-ESS-Data.fst")france_data <- read.fst("france_data.fst")Task 1
Based on the recoding of lrscale for “left” and “right” and omitting “moderates” (see Tutorial 4), and educ.ba from this tutorial, do the long form coding for Chi-Square. Using the steps outlined in the tutorial, first generate the tables of expected proportions and frequencies. Determine and interpret the critical value for independence. Finally, determine and interpret both the Pearson’s chi-squared statistic and the p-value. Discuss main takeaways.
france_data <- ess %>%
# Filter for France
filter(cntry == "FR") %>%
# Recoding clsprty and cleaning trstplt (will use later)
mutate(
ID = case_when(
lrscale %in% 0:3 ~ "Left", # Values 0 to 3 in 'lrscale' are categorized as "Left"
lrscale %in% 7:10 ~ "Right", # Values 7 to 10 in 'lrscale' are categorized as "Right"
lrscale %in% c(4,5,6,77, 88, 99) ~ NA_character_ # Values 77, 88, 99 in 'lrscale' are set as NA
),
# Recoding education with case_when for consistency
educ.ba = case_when(
essround < 5 & edulvla == 5 ~ "BA or more",
essround >= 5 & edulvlb > 600 ~ "BA or more",
TRUE ~ "No BA"
)
) %>%
# Ensure all NAs are handled uniformly
mutate(
edulvla = ifelse(edulvla %in% c(77, 88), NA_integer_, edulvla),
edulvlb = ifelse(edulvlb %in% c(5555, 7777, 8888), NA_integer_, edulvlb),
educ.ba = as.character(educ.ba) # Force educ.ba to be treated as character
)tab_dat <- france_data
# Create a crosstable and save it into the object mytab
mytab <- table(tab_dat$clsprty,tab_dat$educ.ba)
# Calculate row-wise sums of counts in table
rsums <- rowSums(mytab)
# Calculate column-wise sums of counts in table
csums <- colSums(mytab)
# Get the total count of the table (N)
N <- sum(mytab)
# Generate table of expected proportions
ptab <- tcrossprod(rsums/N, csums/N)
cat("Table of Expected Proportions:\n")## Table of Expected Proportions:print(ptab)## [,1] [,2]
## [1,] 0.111530617 0.387839065
## [2,] 0.107858682 0.375070197
## [3,] 0.001184873 0.004120306
## [4,] 0.002768615 0.009627645ftab <- N * ptab
cat("Table of Expected Frequencies:\n")## Table of Expected Frequencies:print(ftab)## [,1] [,2]
## [1,] 2123.31989 7383.68011
## [2,] 2053.41359 7140.58641
## [3,] 22.55762 78.44238
## [4,] 52.70890 183.29110alpha <- 0.05 # significance level
c_val <- qchisq(alpha, df = 1, lower.tail = FALSE)
cat("Critical Value:", round(c_val, 3), "\n")## Critical Value: 3.841# Pearson's chi-squared statistic:
test_stat <- sum((mytab - ftab)^2 / ftab)
cat("Pearson's X^2:", round(test_stat, 4), "\n")## Pearson's X^2: 169.5185p_val <- pchisq(test_stat, df = 1, lower.tail = F)
# p-value:
p_val <- pchisq(test_stat, df = 1, lower.tail = F)
cat("p-value:", round(p_val, 4), "\n")## p-value: 0# Using chisq.test for validation:
cat("Chi-squared test result:\n")## Chi-squared test result:print(chisq.test(mytab, correct = F))##
## Pearson's Chi-squared test
##
## data: mytab
## X-squared = 169.52, df = 3, p-value < 2.2e-16The Pearson’s chi-squared test statistic is 169.52 with 3 degrees of freedom, and the p-value is less than 2.2e-16, indicating that there is likely a relationship or association between the variables.
Task 2
Do Steps 1 to 3 using the infer package (as we did in the tutorial), for the variables sbbsntx (recoded to the corresponding 5 categories) as the response and domicil (recoded to urban and rural, setting 2 to urban instead of peri-urban) as the explanatory variable for the country of France.
france_data <- ess %>%
# Filter for France
filter(cntry == "FR") %>%
mutate(
sbbsntx = case_when(
sbbsntx == 1 ~ "Agree strongly",
sbbsntx == 2 ~ "Agree",
sbbsntx == 3 ~ "Neither agree nor disagree",
sbbsntx == 4 ~ "Disagree",
sbbsntx == 5 ~ "Disagree strongly",
TRUE ~ NA_character_
),
domicil = case_when(
domicil == "1" ~ "Urban",
domicil == "2" ~ "Urban",
domicil == "3" ~ "Rural",
domicil == "4" ~ "Rural",
domicil == "5" ~ "Rural",
TRUE ~ NA_character_
)
)
france_data<-france_data%>%
filter(!is.na(sbbsntx),!is.na(domicil))test_stat <- france_data %>%
specify(explanatory = domicil, # change variable name for explanatory variable
response = sbbsntx) %>% # change variable name for outcome of interest
hypothesize(null = "independence") %>%
calculate(stat = "Chisq") # replace in between quotation marks appropriate test statistic
print(test_stat$stat)## X-squared
## 19.97187null_distribution <- france_data %>%
specify(explanatory = domicil,
response = sbbsntx) %>%
hypothesize(null = "independence") %>%
generate(reps = 1000, type = "permute") %>% # only line we are adding, use reps = 1000 as standard but change if too computationally demanding
calculate(stat = "Chisq")p_val <- null_distribution %>% # replace name here if you assigned something other than null_distribution above
get_pvalue(obs_stat = test_stat, direction = "two-sided") # would only replace test_stat if assigned another name in Step 1
p_val## # A tibble: 1 × 1
## p_value
## <dbl>
## 1 0.002See variable info here: https://ess.sikt.no/en/datafile/ffc43f48-e15a-4a1c-8813-47eda377c355/92?tab=1&elements=[%22874a86e2-a0f6-40b4-aef7-51c8eed98a7d/1%22])
Provide interpretations of the output (consider the variable info).
from above we could know that there is strong evidence to reject null. ## Task 3
Now do Step 4 (i.e., the null distribution visualization with confidence intervals) for the same variables and country as Task 2, and interpret the output.
null_distribution %>%
visualize() +
shade_p_value(obs_stat = test_stat, direction = "two-sided")## Warning: Chi-Square usually corresponds to right-tailed tests. Proceed with
## caution.
null_distribution## Response: sbbsntx (factor)
## Explanatory: domicil (factor)
## Null Hypothesis: independence
## # A tibble: 1,000 × 2
## replicate stat
## <int> <dbl>
## 1 1 4.17
## 2 2 3.71
## 3 3 2.96
## 4 4 0.547
## 5 5 1.52
## 6 6 1.38
## 7 7 2.49
## 8 8 2.21
## 9 9 6.39
## 10 10 3.94
## # ℹ 990 more rowsobserved result is highly unlikely to have occurred under the null hypothesis. Consequently, there is strong evidence to reject the null hypothesis in favor of the alternative hypothesis.
Task 4
Conduct Steps 1 to 3 using the infer package (as we did in the tutorial), for the variables ccrdprs (leaving it on the 0-10 numeric scale) as the response (or outcome) variable and lrscale (recoded as left and right, omitting “moderates” as we did in Task 1) as the explanatory variable.
Variable info here: https://ess.sikt.no/en/datafile/ffc43f48-e15a-4a1c-8813-47eda377c355/92?tab=1&elements=[%2283b08cf2-508e-49a0-9fc8-c3cc281290ec/4%22]
Provide interpretations of the output (consider the variable info).
france_data <- ess %>%
# Filter for France
filter(cntry == "FR") %>%
mutate(
ccrdprs = case_when(
ccrdprs == 1 ~ "1",
ccrdprs == 2 ~ "2",
ccrdprs == 3 ~ "3",
ccrdprs == 4 ~ "4",
ccrdprs == 5 ~ "5",
ccrdprs == 6 ~ "6",
ccrdprs == 7 ~ "7",
ccrdprs == 8 ~ "8",
ccrdprs == 9 ~ "9",
ccrdprs == 10 ~ "10",
TRUE ~ NA_character_
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left",
lrscale %in% 7:10 ~ "Right",
lrscale %in% c(77,88,99)~NA_character_
),
)
france_data<-france_data%>%
filter(!is.na(ccrdprs),!is.na(lrscale))test_stat <- france_data %>%
specify(explanatory = lrscale, # change variable name for explanatory variable
response = ccrdprs) %>% # change variable name for outcome of interest
hypothesize(null = "independence") %>%
calculate(stat = "Chisq") # replace in between quotation marks appropriate test statistic
print(test_stat$stat)## X-squared
## 32.31967null_distribution <- france_data %>%
specify(explanatory = lrscale,
response = ccrdprs) %>%
hypothesize(null = "independence") %>%
generate(reps = 1000, type = "permute") %>% # only line we are adding, use reps = 1000 as standard but change if too computationally demanding
calculate(stat = "Chisq")p_val <- null_distribution %>% # replace name here if you assigned something other than null_distribution above
get_pvalue(obs_stat = test_stat, direction = "two-sided") # would only replace test_stat if assigned another name in Step 1## Warning: Please be cautious in reporting a p-value of 0. This result is an approximation
## based on the number of `reps` chosen in the `generate()` step.
## ℹ See `get_p_value()` (`?infer::get_p_value()`) for more information.p_val## # A tibble: 1 × 1
## p_value
## <dbl>
## 1 0from above we could know that there is strong evidence to reject null. ## Task 5
Now do Step 4 (i.e., the null distribution visualization with confidence intervals) for the same variables and country as Task 4, and interpret the output.
null_distribution %>%
visualize() +
shade_p_value(obs_stat = test_stat, direction = "two-sided")## Warning: Chi-Square usually corresponds to right-tailed tests. Proceed with
## caution.
```
Since the observed statistic falls far outside the range of the simulated null distribution, this suggests that there is strong evidence to reject the null hypothesis under frequentist hypothesis testing principles.