Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

Academic Honesty and Psychology Data Skills Project

Arshya Pooladi-Darvish

2022-07-08

AHSdata<-read.csv("/Users/arshyapooladi-darvish/Desktop/University/Stats 2244/Data Skills Project/datase


#Importing the Academic Honesty and Psychology Dataset

Description: This a a study on psychological traits and academic honesty/dishonesty in university students
from Poland.
Variables:
participant: the person being observed for the study. categorical and nominal variable
sex: determines which sex the participant identifies with. categorical and nominal variable
age: determines age of participant. quantitative and ratio variable
field: determines which academic background each participant has. categorical and nominal
efficacy: a score from 0-40 measuring the degree to which an individual believes they can achieve their goals.
quantitative and interval variable
dishonesty: level of academic dishonesty, from 0-65, displayed by each participant was determined by the
Academic Dishonesty Scale determined from. quantitative and ratio variable
Three Research Questions:
1. How does a participant’s age and field affect their efficacy
2. What is the difference in mean dishonesty rating across men and women
3. Is there a significant difference in academic dishonesty across participants fields

Question 1: How does a participant’s age and field affect their efficacy?

library(ggplot2)
table(AHSdata$age)

##
## 19 20 21 22 23 24 25 26 27 28 56
## 6 22 66 84 71 66 41 21 9 3 1

#as portrayed above, the one individual with the age of 56 is clearly an outlier and
#I will exclude them for the sake of making interpreting the graph easier
ggplot(subset(AHSdata,AHSdata$age < 30), aes(x=age, y=efficacy, shape=field, color=field)) +
geom_point(size=4, shape=20) + geom_smooth(method=lm, se=FALSE, size=1) +
ggtitle("Comparing efficacy against age in participants from different fields")

1
## ‘geom_smooth()‘ using formula ’y ~ x’

Comparing efficacy against age in participants from different fields


40

field
30

H
efficacy

LA
MS

20 SS
ST

10

20 22 24 26 28
age
From the graph above I can conclude that on average individuals in Humanities and Medical Science saw
a decrease in their efficacy as they got older, while those individuals in undeclared fields, Law, Science and
Technology and Social Sciences saw an increase in their efficacy as they got older. ### Question 2: What
is the difference in mean dishonesty rating across men and women?

attach(AHSdata)
t.test(dishonesty ~ sex)

##
## Welch Two Sample t-test
##
## data: dishonesty by sex
## t = -1.151, df = 133.17, p-value = 0.2518
## alternative hypothesis: true difference in means between group female and group male is not equal to
## 95 percent confidence interval:
## -4.403985 1.163985
## sample estimates:
## mean in group female mean in group male
## 12.70 14.32

Since the p value is greater than the alpha value (p>0.05), this confidence interval for the difference of mean
illustrates (with 95% confidence) that there is no true difference in academic dishonesty between men and
women.

2
Question 3: Is there a significant difference in academic dishonesty across participants fields?

H0 : There is no significant difference in academic dishonesty across participants fields


Ha : There is a significant difference in academic dishonesty across participant fields
The best inference procedure in this case is an ANOVA, analysis of variance. ANOVA is a test which tests
how a quantitative responding variable is affected by multiple categorical explanatory variables. An ANOVA
tests for a difference in means like a regular t-test but for more than just two independent variables.

udog<-aov(dishonesty ~ field, data = AHSdata)


summary(udog)

## Df Sum Sq Mean Sq F value Pr(>F)


## field 5 2007 401.5 3.997 0.00151 **
## Residuals 384 38564 100.4
## ---
## Signif. codes: 0 ’***’ 0.001 ’**’ 0.01 ’*’ 0.05 ’.’ 0.1 ’ ’ 1

Since our p-value is very low (p<0.005), we reject the null hypothesis and accept the alternate hypothesis and
conclude that there is a significant difference in academic dishonesty across participant fields.

You might also like