setwd("C:/StatQuiz")
getwd()
## [1] "C:/StatQuiz"
library(ggplot2)
library(dplyr)
###Load Data
load("brfss2013.RData")
1.1 number of observations that are “NA” in the variable “sleptim1”; 1.2 number of observations having at most 5 hours of sleep; 1.3 number of observations having more than 5 hours of sleep but less than 11 hours of sleep; 1.4 number of observations having at least 11 hours of sleep and 1.5 number of observations having at most 5 hours of sleep that are married.
str(select(brfss2013,sleptim1))
## 'data.frame': 491775 obs. of 1 variable:
## $ sleptim1: int NA 6 9 8 6 8 7 6 8 8 ...
brfss2013 %>%
filter(is.na(sleptim1)) %>%
group_by(sleptim1) %>%
summarise(count = n())
## # A tibble: 1 × 2
## sleptim1 count
## <int> <int>
## 1 NA 7387
str(select(brfss2013,sleptim1))
## 'data.frame': 491775 obs. of 1 variable:
## $ sleptim1: int NA 6 9 8 6 8 7 6 8 8 ...
brfss2013 %>%
filter(sleptim1 <= c(5)) %>%
group_by(sleptim1) %>%
summarise(frequency = n())
## # A tibble: 6 × 2
## sleptim1 frequency
## <int> <int>
## 1 0 1
## 2 1 228
## 3 2 1076
## 4 3 3496
## 5 4 14261
## 6 5 33436
str(select(brfss2013,sleptim1))
## 'data.frame': 491775 obs. of 1 variable:
## $ sleptim1: int NA 6 9 8 6 8 7 6 8 8 ...
A <- brfss2013 %>%
filter(sleptim1 > c(5), sleptim1 < c(11)) %>%
group_by(sleptim1) %>%
summarise(frequency = n())
B <- brfss2013 %>%
filter(sleptim1 > c(5), sleptim1 < c(11)) %>%
group_by(sleptim1) %>%
summarise(frequency = n())
sum(B$frequency)
## [1] 425670
str(select(brfss2013,sleptim1))
## 'data.frame': 491775 obs. of 1 variable:
## $ sleptim1: int NA 6 9 8 6 8 7 6 8 8 ...
brfss2013 %>%
filter(sleptim1 > c(11)) %>%
group_by(sleptim1) %>%
summarise(frequency = n())
## # A tibble: 15 × 2
## sleptim1 frequency
## <int> <int>
## 1 12 3675
## 2 13 199
## 3 14 447
## 4 15 367
## 5 16 369
## 6 17 35
## 7 18 164
## 8 19 13
## 9 20 64
## 10 21 3
## 11 22 10
## 12 23 4
## 13 24 35
## 14 103 1
## 15 450 1
C <- brfss2013 %>%
filter(sleptim1 > c(11)) %>%
group_by(sleptim1) %>%
summarise(frequency = n())
sum(C$frequency)
## [1] 5387
str(select(brfss2013,sleptim1,marital))
## 'data.frame': 491775 obs. of 2 variables:
## $ sleptim1: int NA 6 9 8 6 8 7 6 8 8 ...
## $ marital : Factor w/ 6 levels "Married","Divorced",..: 2 1 1 1 1 2 1 3 1 1 ...
brfss2013 %>%
filter(sleptim1 > c(5), marital == "Married") %>%
group_by(sleptim1) %>%
summarise(frequency = n())
## # A tibble: 18 × 2
## sleptim1 frequency
## <int> <int>
## 1 6 53700
## 2 7 81653
## 3 8 75534
## 4 9 11791
## 5 10 4831
## 6 11 306
## 7 12 1259
## 8 13 55
## 9 14 168
## 10 15 125
## 11 16 138
## 12 17 14
## 13 18 52
## 14 19 5
## 15 20 18
## 16 22 3
## 17 23 2
## 18 24 6
D <- brfss2013 %>%
filter(sleptim1 > c(5), marital == "Married") %>%
group_by(sleptim1) %>%
summarise(frequency = n())
sum(D$frequency)
## [1] 229660