Research Scenario 3: Employee Training and Skill Development
The CEO of a company evaluated the communication skills (multiple-item rating scale) of all employees and found that, on average, their performance was below the company’s desired standard. To address this gap, all employees participated in a professional communication training program. The CEO now wants to determine whether the training has led to measurable improvements in employees’ communication abilities. Is there an improvement in the employees’ communication skills?
Hypotheses
H₀: There is no difference in the employees’ communication skills between scores before and after training.
H₁: There is a difference in the employees’ communication skills between scores before and after training.
Load Required Library
library(readxl)
Read dataset
A6R3 <- read_excel("C:/Users/saisa/Downloads/A6R3.xlsx")
Variables
Before <- A6R3$PreTraining
Before
## [1] 64 42 60 61 57 56 55 59 52 66 57 52 59 56 67 54 63 55 62 54 54 65 53 63 49
## [26] 56 58 58 67 59 57 51 65 65 54 52 49 58 55 65 59 74 73 66 70 64 35 64 65 68
## [51] 60 48 66 59 54 65 69 54 69 70 57 66 58 79 63 57 53 57 52 66 64 68 70 57 52
## [76] 58 72 66 63 47 75 64 52 62 49 61 63 56 48 71 56 68 53 51 39 68 62 55 64 72
## [101] 56 57 65 61 61 65 66 51 65 59 62 44 36 66 57 67 63 54 63 71 54 63 63 68 58
## [126] 65 63 60 59 62 50 64 48 62 60 44 54 65 59 84 51 45 59 65 58 54 64 70 75 55
After <- A6R3$PostTraining
After
## [1] 71 50 71 78 63 67 63 66 62 80 72 60 65 66 83 57 65 62 80 64 57 73 64 83 65
## [26] 62 69 57 68 72 75 61 78 68 66 70 59 65 65 74 64 79 76 84 85 79 40 74 64 76
## [51] 54 50 70 79 62 71 78 69 71 81 66 76 72 88 72 71 68 59 61 76 71 83 76 59 60
## [76] 70 74 83 70 58 85 81 59 78 56 72 77 69 55 75 58 81 61 57 50 85 76 66 73 86
## [101] 63 68 75 65 64 79 71 57 76 62 61 57 46 74 63 80 66 66 75 81 67 74 70 80 60
## [126] 74 76 61 74 82 63 77 48 75 69 58 62 75 69 96 57 61 69 80 69 72 68 76 90 70
Differences <- After - Before
Differences
## [1] 7 8 11 17 6 11 8 7 10 14 15 8 6 10 16 3 2 7 18 10 3 8 11 20 16
## [26] 6 11 -1 1 13 18 10 13 3 12 18 10 7 10 9 5 5 3 18 15 15 5 10 -1 8
## [51] -6 2 4 20 8 6 9 15 2 11 9 10 14 9 9 14 15 2 9 10 7 15 6 2 8
## [76] 12 2 17 7 11 10 17 7 16 7 11 14 13 7 4 2 13 8 6 11 17 14 11 9 14
## [101] 7 11 10 4 3 14 5 6 11 3 -1 13 10 8 6 13 3 12 12 10 13 11 7 12 2
## [126] 9 13 1 15 20 13 13 0 13 9 14 8 10 10 12 6 16 10 15 11 18 4 6 15 15
Descriptive Statistics
# Install and load the package
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
Calculate the Descriptive Statistics
#Descriptive Statistics for Before Scores
mean(Before, na.rm = TRUE)
## [1] 59.73333
median(Before, na.rm = TRUE)
## [1] 60
sd(Before, na.rm = TRUE)
## [1] 7.966091
length(Before)
## [1] 150
#Descriptive Statistics for After Scores
mean(After, na.rm = TRUE)
## [1] 69.24
median(After, na.rm = TRUE)
## [1] 69.5
sd(After, na.rm = TRUE)
## [1] 9.481653
length(After)
## [1] 150
Histograms
hist(Differences,
main = "Histogram of Difference Scores",
xlab = "Value",
ylab = "Frequency",
col = "light blue",
border = "black",
breaks = 20)
Is the histograms symmetrical, positively skewed, or negatively skewed? Positive
Did the histogram look too flat, too tall, or did it have a proper bell curve? Proper Bell curve
Shapiro-wilk Test
shapiro.test(Differences)
##
## Shapiro-Wilk normality test
##
## data: Differences
## W = 0.98773, p-value = 0.21
Normality Test Results: Differences: W = 0.98773, p-value = 0.21 → normally distributed
Decision: Since it is normally distributed, we will use Dependent t test.
BOXPLOT
boxplot(Differences,
main = "Distribution of Score Differences (After - Before)",
ylab = "Difference in Scores",
col = "blue",
border = "darkblue")
How many dots are in your boxplot? One
Where are the dots in your boxplot? close to the whiskers
Based on the dots and there location, is the data normal? The dots are CLOSE to the whiskers,so the data is normal
Determine Statistical Significance
t.test(Before, After, paired = TRUE)
##
## Paired t-test
##
## data: Before and After
## t = -23.285, df = 149, p-value < 2.2e-16
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -10.313424 -8.699909
## sample estimates:
## mean difference
## -9.506667
p < 0.01 - Statistically significant
Effect size
# Install and load the package
library(effectsize)
Calculate the effect size
cohens_d(Before, After, paired = TRUE)
## For paired samples, 'repeated_measures_d()' provides more options.
## Cohen's d | 95% CI
## --------------------------
## -1.90 | [-2.17, -1.63]
What is the size of the effect? -1.90 Very Large
Which group had the higher average score? PostTraining group has the highest score
FINAL REPORT
A dependent t-test was conducted to compare communication skills before and after the professional training program among 150 employees. Results showed that post-training communication scores (M = 69.31, SD = 9.86) were significantly higher than pre-training scores (M = 59.80, SD = 7.76), t(149) = -23.29, p < .001. The effect size was Cohen’s d = -1.90, indicating a very large effect. These results suggest that the professional communication training program significantly improved employees’ communication skills.