Sie sind auf Seite 1von 21

Candidate Name:

Michael Timson

Candidate Number:

Centre Number:

ADDITIONAL MATHEMATICS

Examination Period: 2013-2014

Michael Timson

Michael Timson

PROJECT TITLE: To determine the probability of T.C.E Form 1 students obtaining a passing
grade in a multiple choice examination if he guesses the answer for each question.

PROBLEM STATEMENT:
Over the years, students have established a theory that there is a high possibility of passing a
multiple choice (Paper 1) examination by simply guessing the answers for the question. In my
curiosity to see how strong the bases of this theory stand, I have chosen to forces this project on
it. In order to do so, I wish to obtain a sample of raw data from the form one year group of
Trinity College east and from this data, analyse and interpret it through the use of graphical
representation and statistical reports. This project would be used as an analytical investigation to
determine whether guessing can enable a student to obtain a passing great in a multiple choice
examination. Hopefully Student, depending on the performance displayed in the results, will
learn to take multiple choice assessments more seriously and will take into consideration that
preparation for a multiple choice question paper is just as equally important as he preparation for
a structured paper. One of the goals of this project is to inspire student to study hard and try for
their very best in multiple choice papers. As a result of this, students are expected to perform
better now that they would have taken the importance of a multiple choice more seriously.

VARIABLES:
Controlled Variable: The multiple choice exam, Age of the student involved, length
of time used for exam.
Manipulated Variable: The degree of difficulty of the questions in the multiple
choice examination.
Responding Variables: The grades achieved on the multiple choice examination
(measure in percentage)

Michael Timson

METHOD OF DATA COLLECTION


1. A Form 5 Paper 1 Chemistry exam, consisting of 40 questions, was obtained and then
photocopied 5 times.
2. The examination was then carried around to the Form 1 year group so that they can be
assessed and data can be collected.
3. The data was then collected and analyse.

Michael Timson

PRESENTATION OF DATA:

RAW DATA

10

10

11

12

14

14

17

17

18

19

21

22

Michael Timson

TABLES:
TABLE SHOWING THE MARKS GROUPING AND ITS PERCENTAGE
Marks
0-4
5-9
10-14
15-19
20-24
25-29
30-34
35-39

Percentage
0.0 - 10.0
12.5 - 22.5
25.0 - 35.0
37.5 - 47.5
50.0 - 60.0
62.5 - 72.5
75.0 - 85.0
87.5 - 97.5
Figure 1

CUMULATIVE FREQUENCY TABLE


Marks
0-4
5-9
10-14
15-19
20-24

Frequency
63
25
6
4
2

Cumulative Frequency
63
88
94
98
100
Figure 2

TABLE SHOWING THE MIDPOINT, FREQUENCY AND THE MARK INTERVAL


Marks

Mid-Point

Frequency

Upper class limit

fx

0-4

63

126

Michael Timson

5-9

25

175

10-14

12

14

72

15-19

17

19

68

20-24

22

24

44
fx = 535
Figure 4

xx=

fx
f

=
= 5.35

Michael Timson

535
100

BOX AND WHISKERS

Michael Timson

BAR GRAPH
70

60

50

40
Frequency
30

20

10

0
0-4

5-9

10-14
Number of Marks

Michael Timson

15-19

20-24

Figure 6

HISTOGRAM:

Michael Timson

70

60

50

40
Frequency
30

20

10

Michael Timson

1
63

25

6
Marks

Figure 7

Michael Timson

PIE CHART:
PIE CHART SHOWING THE SIZE OF EACH GROUP

42
0-4
5-9

25

10-14

63

15-19
20-24

Figure 8

Michael Timson

0.02

Students Fail
Students Pass

0.98

PIE CHART SHOWING PERCENTAGE PASSED AND FAIL

Figure 9

MATHEMATICAL KNOWLEDGE/ ANALYSIS OF DATA


Figure 1 displays the way in which the raw data was grouped. As seen in the table, each grouping
had a class width of 5. The marks were then converted to its percentage and each percentage

Michael Timson

grouping had a class width of 11. Class width is found by subtracting the lower class boundary
from the upper class limit. Therefore:
Class width = The uperclassboundary thelower class boundary .
From the table we can clearly see that the scores obtained are generally far from the pass mark from the
percentages displayed.

Figure 2 is a cumulative frequency table. From this table, a best fit cumulative frequency curve
was plotted, figure 3, and used to obtain the median, the upper quartile and the lower quartile.
The median, known as Q2, is an average that is unaffected by extreme values as is known as the
middle value. With the use of a ruler, the median was found to be 3.4 marks. Therefore, from the
median from the graph, it can be said that half of the student scored marks greater or less than
3.4 marks. This also means that according to figure 1, 50 students scored less than 10%. As
mention before, the graph was also used to obtain the lower quartile, also known as Q1, and the
upper quartile, known as Q3. Q1 is the value away through the distribution and Q3 is of the
way through the distribution. Q1 and Q3 are also both unaffected by extreme values and aids in
giving an idea of the variability of the data or the spread of data. The lower quartile was obtained
with a value of 2 marks. This meant that a quarter of the students got less than 2 marks and three
quarter got over 2 marks. The graph was then further analysed to obtain the upper quartile. Q3
was found to be 5.6 marks. This means that three quarter of the total students scored below 5.6
marks and only a quarter scored above it. As reference to table 1, this means that 75 students got
less than 22.5%.
From the cumulative frequency graph, the total number of students that pass and fail the
examination can be acquired. The total number of students that passed the exam was 2 students,
therefore giving a pass rate of 2%. The total number of students failed was 98 students and thus
giving a failure rate of 98%.
Figure 4 is a tabled derived to show the mark interval, the frequency (f) which shows the number
of students that scored within the mark interval, the midpoint of the group width and the
frequency (f) multiplied by the midpoint (x). From this table the mean, or the average mark, was

Michael Timson

calculated using the formula

fx
f

. After

substituting the values, fx=535 and f = 100, the

mean was 5.35. The mean show the centre of the data set and provides a better measure of
central tendency when the sample size is large and does not include outliers. The mean mark of
5.35 is average mark0
Figure 6 is a bar chart used to show the differences between different quantities or different
groups of process data. Spaces between the bars are used to differentiate the categories. In
essence, the bar charts summarise and display the data sets. The height of each rectangular bar is
directly proportional to the frequency of students that obtained the amount of marks in that
group.
Figure 7 is a histogram. A histogram is a representation of tabulated frequencies, shown as
adjacent rectangles, erected over discrete intervals (bins), with an area equal to the frequency of
the observations in the interval.
Figure 8 is a pie chart. A pie chart is a circular diagram that is used to represent statistical data
and aids in displaying the magnitude of each group through the use of angles. Each sector angle
is directly proportional to the information that it represents. The pie chart visually gives the
viewer an idea as to how big or small a particular group is to the others.
Figure 9 is another pie chart. This pie chart is used to show the difference, in terms of size, the
amount of student that passed and failed the chemistry examination. It showed that the vast
majority student indeed fail than passed.
Probability is the measure of an event to likely occur and is a number between o which is the
impossible event, and 1 which is a certain event. From the calculation based on the cumulative
frequency curve drawn (figure 3), A was used to represent students the probability that a student
scored 0-10 percent in the exam. The probability was found to be

.This means if a student

was chosen at random the probability of that student obtaining 10% or less than 10% is
the probability of a student obtaining more than 10% is

.B was then used to represent the

probability of a student obtaining 10% - 20% and this probability was


student chosen at random getting between 20% 50% was

.The probability of a

and is represented by C. D then

represented the probability of a student passing the exam with 50% and the value found was
Michael Timson

and

Percentiles were calculated allowing a better understanding of the data. It was calculated using
the data obtained from the cumulative frequency curve.

Michael Timson

DISCUSSION OF FINDINGS
The data obtained was analysed and express through various statistical representations. The raw
data was grouped and shown in tables. These tables also showed the percentages for the mark
grouping, the cumulative frequency used to plot a cumulative frequency graph, the midpoint,
frequency, the mark interval and the frequency x the midpoint giving fx. From this table, other
forms of statistical representation were derived. These include the histogram, the bar graph, box
and whiskers and the pie chart. The mean was also calculated using the tables.
From the second pie chart, we can clearly see that the number of student that failed the chemistry
exams was superior to the amount that passed. The ratio of the amount of students that failed to
the amount that passed was
examination,

.This means that for every

students that passed the

amount failed.

The highest mark in this examination was 22 which were accomplished by 2 students. This mark
fell into the percentage group of 50% - 60%. When this mark is converted to a percentage, it was
found to be 55%. The lowest mark was 0 which was obtained by 28 students. Furthermore, 63
students obtained marks lower than 5. This means that over 63% of the student could not
achiever marks greater than 4. I can be clearly seen that the year group overall performance in
this exam was not good. The lack of preparedness for the exams was displayed through their
results thus showing us that a multiple choice paper cannot be done well through simply
guessing the answers. When guessing the answers in a multiple choice paper, the probability of a
student obtaining the right answer is . This means that that student only has a of a chance of
getting the right answer for each question for all question involved in the paper.
Student, as show cased in the data, cannot depend/rely on guessing to obtain a pass in the
multiple choice paper. Multiple choice papers need as much preparation as the structures paper in
order to achieve success. Without proper preparations, the probability of a student passing the
paper is low. However, if a student puts in the necessary preparations for the paper, the
probability of pass with a high grade is high.

Michael Timson

CONCLUSIONS
With the data collected as evidence, it can be concluded that multiple choice examinations
cannot be done properly by guessing through the paper but needs as much preparation as the
structured paper in order to obtain a successful grade.

Michael Timson

Sample Exam

Michael Timson

Answers

Michael Timson