Data Analysis Data Description

Task 4
Data Analysis
Data Description
Here a dataset is provided showing information about influence of coffee intake on test
score among University students.
Data Pre-processing
In this stage, a subset of the data is created by omitting the missing values.
Research Objectives
The main motive of this study is to find out whether consumption of coffee influences the
test scores of students. For this, two research questions are built up. Firstly, it is required to
check whether there is any significant difference in scores after coffee intake or not. Another
goal is to find out whether age is associated with the test score_after.
Descriptive Study
At first some descriptive studies are performed to understand the variables. Here Gender
is a categorical variable taking 1=Male and 2=Female. The summary statistics for the numerical
variables are shown below.

From table 1, it can be seen that on average, the age of a student is 25.62=26 years
(approx.). The median shows that 50% students have age less than 26 years. Maximum number
of students are 20 years old. Moreover, the percentiles show that 25% student are below 22 years
(25th percentile) and above 29 years (75th percentile). The skewness indicates that the distribution
of age is positively skewed (Hinton, McMurray and Brownlow 2014).

Before consuming coffee, the average mark was 55.37=55(approx.) whereas after coffee
intake the test score is 70.32=70 (approx.) on average. The medians show that 50% students
scored less than 60 before coffee intake and less than 73 after coffee intake. Maximum number
of students scored 62 before and 75 after. Both the skewness are negative. Hence, it can be
concluded that the distribution of the test scores are negatively skewed.
Normality Test
Here normality assumption is tested graphically using histogram and normal Q-Q plot
(Das and Imon 2016).

The histograms show that the test1 scores are approximately normally distributed for both
male and female students.