Analysis Of Students Marks By Demographics

Abstracts
PART A

167 participants were tested and observed to determine whether their sex or age or whether they were full time or part time students would affect their marks in this given course. by deriving the needed data from the existing data and utilizing several different analysis tools, such as pivot tables, graphs, scatter charts, histograms and boxplots, we must determine the difference in pass rates between males and females; the difference in pass rates based on the age of the students; the difference in the average total module mark between full-time and part-time students; the relationship between the coursework mark and exam mark; the distribution of total marks achieved as shown in a histogram; the relevant information and produce a pair of boxplots of the coursework marks and the exam marks. While some of the outcomes were inconclusive, others yeilded unexpected results.
PART B
I am to relay my personal experience and views as to what I have learned from the project in Part-A and what practical learnings I can use to my benefit in the future.
An Analysis of Student Coursework and Exam Marks based on Given Demographic
In a recently conducted module, 167 participants, 97 of which were males and 70 of them females, I will attempt to determine if and how the participants’ sex or age or whether they were full time or part time students would affect their marks in this given course or subject. Here are what was derived from the study the pass and fail marks of  the participants of this module:
Pass and Fail Rates between Male and Female Participants
Based on the total marks of each participant, I have surmised that of the 97 male participants of this module, 88 passed the course; and, consequently, of the 70 females who participated, 62 passed the course. This means that (as shown in Figure 1) 91% of males and 89% of females passed the course. As far as this particular module is concerned, males faired slightly better than females, leading them by only 2%; however, this difference is considered negligible. This may led us to conclude that for this particular course, the participants’ sex does not affect their pass and fail rates.
Figure 1
 Pass and Fail rates Based on the Participants’ Age
We divided the participants into 3 age groups; from ages 19 to 23, 24 to 28, and 30 to 39 years. As indicated in Table 1, the largest group of participants, 122, came from the 19 to 23 age group; while there were 38 and 7 participants from the 24 to 28 and 30 to 39 age groups respectively.
All but 2 of those who failed the course came from the 19 to 23 age group; however, when this data is translated into percentages (as shown in Figure 2), we can see that it is the 30 to 39 age group that has the highest fail rate (at 14%). We will also notice that the highest pass rate belongs to the 24 to 28 age group.

19 to 23
24 to 28
30 to 39

Pass
107
37
6

Fail
15
1
1

Total
122
38
7

Table 1
Figure2
These results seem inconclusive. Though percentages show that the 24 to 28 age group has the highest “per ratio” pass rate, the number of participants in that age group (38) is far lower than that of the 19 to 23 age group (122). Furthermore, we cannot accurately determine if the percentage results for the 30 to 39 age group is accurate since there are only 7 participants from this age group. For this to be accurate, we will need to have more participants coming from both the 24 to 28 and 30 to 39 age groups.
Average Total Module Marks for Full-time and Part-time Participants
According to the data given there are 145 participants who undertook this module full-time; and 22 participants who undertook this module part-time. The average “Total Module” marks (as shown in Figure 3) of the full-time participant at 55.4 points, which is only 2.4 points higher than the part-timers, at 53.0 points.
This result may, again, seem inconclusive at first glance; however, if we are to view the histogram below (Figure 5) we notice that full-timers fall slightly above the mean (55.1 points), while the part-timers fall far below the mean. This may lead us to conclude that part-time participants, perhaps because they are not that dedicated to the course, fall below “average” performance.
Figure3
Relationship between Coursework marks and Exam marks
As we can see from the scatter chart (Figure 4), and assuming that 40 is the passing mark, I have determined that there are 32 participants who failed the exam and 3 participants who failed their coursework. Of the 32 who failed the exam, 31 actually had passing marks in their coursework; whereas, there were 2 participants who passed the exam after having failed their coursework.
Figure4
The high number of participants who failed the exams may suggest that different methods were used in the implementation of the exam and coursework. I theorize that the students who failed the exam after passing their coursework may have been expecting the same methodology from the implementation of the exam and the coursework.
Distribution of Total Marks Achieved using a Histogram
Figure 5
From the histogram (Figure 5) I have derived a mean mark of 55.1. We can also see, from the histogram, that marks from 55 to 60 had the highest frequency or number of participants hitting that mark.
Comparison of Coursework and Exam Marks using Notched Skeletal Boxplot
The relevant information I used to construct the 2 boxplots below were the Coursework and Exam marks, their respective frequencies (number of time those marks were hit), and the total number of participants of this course.
What I learned from this Module
I enjoy learning from experience. It’s exhilirating and I learn a lot more by doing than by memorizing. Solving a problem or trying to make sense of raw data or radom figures always hastens the learning process for me. And yes, I believe that what I have learned here, in this module, is both relevant and beneficial for me; not only in my career and studies, but in my life in general.
The most obvious skill involved in this module is the ability to analyze raw data and determine the relationship each data group had to the questions given to me. However, my analysis would be flawed if not for the other two skills I discovered through this module. One of them was the skill of observation. Analysis can be easy, when I have the right processed information before hand; but if, like in this module, I have to determine which data to use  to answer the given questions, I need to be keen and patient in observing how each data group behaves in relation with the other data groups.
But a keen observing eye cannot stand alone; it needs another important skill; communication ( and not just the talking kind). After I determined what data I needed to get the desired results, I had to have a way to present this data; to know what charts or graphs to use; so that those I am presenting to will be able to understand where I am coming from. I may be wrong in my analysis, but you cannot deny that I got my message through clearly. I belive that analysis, observation and communication skills are not only skills one needs in school, they are, more importantly, life skills, or skills I will use throughout my life.
For obvious reasons, these skills are very important in school. All the subjects I take have problems that need observation, to gather information on the many itnricacies of a given problem; analysis, that I may understand and find solutions to the problem;  and communication, so that I may be able to explain my answers and why I chose the solution I chose.
However, these three skills are also very important in everyday life, and are, thus, very valuable skills to have indeed. In life, I will need to be able to observe, analyze and communicate in every aspect of life; from buying goods from a store to to becoming an enterpreneur someday. In fact, even in the simple act of talking to a classmate or teacher, we need to use all these skills. And, by asking us to solve modules like this, we train ourselves in the use of these skills.
Basically, I am an audial and kinestenic learner. I learn by listening and by experiencing. I am particularly weak at visual learning, especially when it comes to reading long novels or essays. I also work better in a group than I do alone; which tells me that I need the support of a group to get me out of my many procrastination phases. That being said, I need to set a quota for how many books I intend to read this year (maybe I’ll start with 12 easy ones first) in order to train my dormant visual learning skills.
Also, procrastination is either a problem with the “stimulus” or the “response” phase of learning; so, I’m quite sure I have to try to find the proper stimulus or goal in my life so that what I do in school will have some meaning. If I can find that goal, I’m sure that procrstination will be a thing of the past. But it isn’t all bad; because once I get started on something I don’t leave it until it’s done. Which means that if and when I find the proper stimulus, it take very little “reinforcement” for me to get the job done.
In all, this module has taught me quite a lot… and I hope to learn much, much more!