R Notebook
Fox River before and after cleaning initial examination
Are the values of conductance before and after significantly different??
Load Tidyverse Import data set view data set
library(tidyverse)
library(readxl)
foxdamp <- read_excel("foxdamp.xlsx", col_types = c("numeric",
"numeric"))
View(foxdamp)print(foxdamp)spcon1 values before cleaning spcon2 values after cleaning
Summary of data Boxplot to view data
summary(foxdamp) spcon1 spcon2
Min. :0.957 Min. :1.019
1st Qu.:1.099 1st Qu.:1.136
Median :1.143 Median :1.190
Mean :1.131 Mean :1.191
3rd Qu.:1.185 3rd Qu.:1.269
Max. :1.259 Max. :1.334 boxplot(foxdamp)
In viewing the data in the summary and on a boxplot, the median appears to be larger, therefore the cleanings seem to increase the specific conductance readings.
Running some basic tests to make sure the data are normal as well meet other assumptions for a t-test like equal variance using an F-test
Shapiro Wilk test normal distribution
shapiro.test(foxdamp$spcon1)
Shapiro-Wilk normality test
data: foxdamp$spcon1
W = 0.95367, p-value = 0.7699shapiro.test(foxdamp$spcon2)
Shapiro-Wilk normality test
data: foxdamp$spcon2
W = 0.98188, p-value = 0.9605Passes pvalue above .05, Data are normal
Test of Variance
var.test(foxdamp$spcon1 , foxdamp$spcon2)
F test to compare two variances
data: foxdamp$spcon1 and foxdamp$spcon2
F = 0.83445, num df = 5, denom df = 5, p-value = 0.8474
alternative hypothesis: true ratio of variances is not equal to 1
95 percent confidence interval:
0.1167653 5.9632930
sample estimates:
ratio of variances
0.8344493 The p-value is p = 0.8 which is greater than the significance level 0.05. In conclusion, there is no significant difference between the two variances.
t.test(foxdamp$spcon1 , foxdamp$spcon2)
Welch Two Sample t-test
data: foxdamp$spcon1 and foxdamp$spcon2
t = -0.95588, df = 9.9192, p-value = 0.3619
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
-0.20013869 0.08006395
sample estimates:
mean of x mean of y
1.130872 1.190909 In further research, I found that the Wech t-test, a non- parametric t-test would be a better for our small data sets, therefore we can bypass the assumptions related to the students t-test
My conclusion from the Fox River @ Waukesha would indicate that the the p-value (p = 0.3) is greater than the significance level (0.05).
Therefore, is no significant difference in performance of the ctd between cleanings.