Course - Math 206 - Data Analysis

Author - Brad Hartlaub

Reading in a data set

library(Stat2Data)
data("WeightLossIncentive4")

Looking at the structure of a data set

str(WeightLossIncentive4)
## 'data.frame':    36 obs. of  2 variables:
##  $ WeightLoss: num  12.5 12 1 -5 3 -5 7.5 -2.5 20 -1 ...
##  $ Group     : Factor w/ 2 levels "Control","Incentive": 1 1 1 1 1 1 1 1 1 1 ...

Basic Plots

hist(WeightLossIncentive4$WeightLoss)

boxplot(WeightLoss~Group, data=WeightLossIncentive4)

Basic Descriptive Statistics

summary(WeightLossIncentive4)
##    WeightLoss            Group   
##  Min.   :-17.000   Control  :19  
##  1st Qu.:  1.750   Incentive:17  
##  Median :  7.750                 
##  Mean   :  9.472                 
##  3rd Qu.: 18.625                 
##  Max.   : 30.000

Summary Statistics by Group

library(psych)
describe(WeightLossIncentive4$WeightLoss)
##    vars  n mean    sd median trimmed  mad min max range  skew kurtosis
## X1    1 36 9.47 10.89   7.75    9.52 12.6 -17  30    47 -0.03    -0.66
##      se
## X1 1.82
describeBy(WeightLossIncentive4$WeightLoss, WeightLossIncentive4$Group)
## $Control
##    vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 19 3.92 9.11      3    4.21 8.15 -17  20    37 -0.13    -0.37 2.09
## 
## $Incentive
##    vars  n  mean   sd median trimmed   mad  min max range  skew kurtosis
## X1    1 17 15.68 9.41     18    15.8 11.86 -0.5  30  30.5 -0.12    -1.51
##      se
## X1 2.28
## 
## attr(,"call")
## by.default(data = x, INDICES = group, FUN = describe, type = type)

Two sample t test

t.test(WeightLoss~Group, data=WeightLossIncentive4)
## 
##  Welch Two Sample t-test
## 
## data:  WeightLoss by Group
## t = -3.7982, df = 33.276, p-value = 0.0005889
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -18.05026  -5.46058
## sample estimates:
##   mean in group Control mean in group Incentive 
##                3.921053               15.676471
t.test(WeightLoss~Group, data=WeightLossIncentive4, var.equal=TRUE)
## 
##  Two Sample t-test
## 
## data:  WeightLoss by Group
## t = -3.8054, df = 34, p-value = 0.0005635
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -18.033330  -5.477506
## sample estimates:
##   mean in group Control mean in group Incentive 
##                3.921053               15.676471

    Two Sample t-test

data:  WeightLoss by Group
t = -3.8054, df = 34, p-value = 0.0005635
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -18.033330  -5.477506
sample estimates:
  mean in group Control mean in group Incentive 
               3.921053               15.676471