week 5 lecture
Jessica Taylor-Sepulveda
2024-09-25
library(tidyverse)## ── 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 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ 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 errorslibrary(readxl)
district_3_<-read_excel("district (3).xls")pastecs::stat.desc(district_3_$DA0AT21R,norm=T)## nbr.val nbr.null nbr.na min max
## 1.203000e+03 0.000000e+00 4.000000e+00 -1.000000e+00 1.000000e+02
## range sum median mean SE.mean
## 1.010000e+02 1.139929e+05 9.540000e+01 9.475719e+01 1.402861e-01
## CI.mean.0.95 var std.dev coef.var skewness
## 2.752329e-01 2.367528e+01 4.865725e+00 5.134940e-02 -1.349334e+01
## skew.2SE kurtosis kurt.2SE normtest.W normtest.p
## -9.565050e+01 2.503308e+02 8.879953e+02 3.600778e-01 9.455757e-54#Mean: 9.475719e+01
#Median: 9.540000e+01
#Skewed to the left
qqnorm(district_3_$DA0AT21R)
qqline(district_3_$DA0AT21R,col="red")
shapiro.test(district_3_$DA0AT21R)##
## Shapiro-Wilk normality test
##
## data: district_3_$DA0AT21R
## W = 0.36008, p-value < 2.2e-16P-value is greater than .05 so data is plausibly normal.
qqnorm(district_3_$DA0AT21R)
qqline(district_3_$DA0AT21R,col="red")
ks.test(district_3_$DA0AT21R,"pnorm",mean=mean(district_3_$DA0AT21R),sd=sd(district_3_$DA0AT21R))## Warning in ks.test.default(district_3_$DA0AT21R, "pnorm", mean =
## mean(district_3_$DA0AT21R), : ties should not be present for the one-sample
## Kolmogorov-Smirnov test##
## Asymptotic one-sample Kolmogorov-Smirnov test
##
## data: district_3_$DA0AT21R
## D = NA, p-value = NA
## alternative hypothesis: two-sideddistrict_3_cleaned<-district_3_%>%filter(DA0AT21R>0)ks.test(district_3_$DA0AT21R,"pnorm",mean=mean(district_3_$DA0AT21R),sd=sd(district_3_$DA0AT21R))## Warning in ks.test.default(district_3_$DA0AT21R, "pnorm", mean =
## mean(district_3_$DA0AT21R), : ties should not be present for the one-sample
## Kolmogorov-Smirnov test##
## Asymptotic one-sample Kolmogorov-Smirnov test
##
## data: district_3_$DA0AT21R
## D = NA, p-value = NA
## alternative hypothesis: two-sideddistrict_3_cleaned<-district_3_cleaned%>%filter(DA0AT21R>0)mean(district_3_cleaned$DA0AT21R)## [1] 94.91665hist(district_3_cleaned$DA0AT21R, breaks = 10,probability = T)
lines(density(district_3_cleaned$DA0AT21R),col='red',lwd=2)
qqnorm(district_3_cleaned$DA0AT21R)
qqline(district_3_cleaned$DA0AT21R,col='red')
district_3_cleanedsqrt<-district_3_cleaned%>%mutate(DA0AT21R_SQRT=sqrt(DA0AT21R))%>%select(DA0AT21R,DA0AT21R_SQRT)
head(district_3_cleaned)## # A tibble: 6 × 137
## DISTNAME DISTRICT DZCNTYNM REGION DZRATING DZCAMPUS DPETALLC DPETBLAP DPETHISP
## <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 CAYUGA … 001902 001 AND… 07 A 3 574 4.4 11.5
## 2 ELKHART… 001903 001 AND… 07 A 4 1150 4 11.8
## 3 FRANKST… 001904 001 AND… 07 A 3 808 8.5 11.3
## 4 NECHES … 001906 001 AND… 07 A 2 342 8.2 13.5
## 5 PALESTI… 001907 001 AND… 07 B 6 3360 25.1 42.9
## 6 WESTWOO… 001908 001 AND… 07 B 4 1332 19.7 26.2
## # ℹ 128 more variables: DPETWHIP <dbl>, DPETINDP <dbl>, DPETASIP <dbl>,
## # DPETPCIP <dbl>, DPETTWOP <dbl>, DPETECOP <dbl>, DPETLEPP <dbl>,
## # DPETSPEP <dbl>, DPETBILP <dbl>, DPETVOCP <dbl>, DPETGIFP <dbl>,
## # DA0AT21R <dbl>, DA0912DR21R <dbl>, DAGC4X21R <dbl>, DAGC5X20R <dbl>,
## # DAGC6X19R <dbl>, DA0GR21N <dbl>, DA0GS21N <dbl>, DDA00A001S22R <dbl>,
## # DDA00A001222R <dbl>, DDA00A001322R <dbl>, DDA00AR01S22R <dbl>,
## # DDA00AR01222R <dbl>, DDA00AR01322R <dbl>, DDA00AM01S22R <dbl>, …library(ggplot2)ggplot(district_3_cleaned,aes(x=log(DA0AT21R),y=DPETECOP)) + geom_point() + ggtitle("Log-Transformed Data")