Math M Assignment

Introduction
A)Data description
Observed values or measurements of a variable are called data.
 Example of variable:heights of students in a class
Data divide in two:
1.Qualitative data
2.Quantitative data
Quantitative data divide in two:
1.Discrete data
2.Continuous data
Discrete data Continuous data
• can take only exact value • any value can take without
• Example: range
the number of student because • Example :
there was not half of student time was measured to fractions of
a second.
Ungrouped data Grouped data
 raw data  bundled together in categories
 data first gather from an  histograms and frequency
experiment or study table was used to show data
 not sorted into categories,
classified, or otherwise grouped
 a list of numbers
•Measures
  of tendency
 used to determine the central values of a data set
Mean,(arithmetic mean) :
sum of the values divided by the total number of observations
 it can be used with both discrete and continuous data
Median :
value at the centre of a data set after the data set is arranged in ascending or
descending order
Mode :
 value occurred the most time in a set
•Measures
  of dipersion
used to determine the spread of a data
Standard deviation ,
square root for the mean of all the squares
Variance,
square of the standard deviation.
Range
difference between the largest value and the smallest value
•Interquartile
  range (IQR)
third quartile subtracted the first quartile,
First quartile ,
known as lower quartile was a number that 25% of the data were less than
this number
Third quartile
known as upper quartile was a number that 75% of the data were less than
this number
Second quartile ,
known as median
Spread of distribution
showed by boxplots
Boxplots
draw by using smallest value ,largest value , first quartile ,third quartile
and median
non-parametric
Outliers
 may be plotted as individual points
 
 B)Correlation
determine the degree of association between two variables
 two variables are observed simultaneously ,bivariate data are obtained
 linear relation between two variables :
one where a change in one variable corresponds to a constant change in
the other variable
Scatter diagram
each pair of the bivariate data is plotted whether there is a linear
correlation between two variables
Pearson correlation coefficient , r
known as the product-moment correlation coefficient
 linear correlation coefficient is a numerical value which the degree of linear
correlation between the variables was indicated
Properties of the Pearson correlation coefficient
 correlation coefficient has values between -1 and 1,inclusive of both value.
correlation coefficient of +1
indicated a perfect positive linear correlation between the variables
correlation coefficient of -1
 indicated a perfect negative linear correlation between the variables
Other correlation coefficient values
indicated a lesser degree of liner correlation
Zero,0 correlation coefficient
 indicated no linear correlation between two variables and
uncorrelated
correlation coefficient is independent of the change of origin and
scale of measurements
• 
Spearman correlation coefficient ,
defined as the Pearson correlation coefficient between the rank variables
 the linear correlation of data was calculated by first assigning ranks to each data
take values between -1 and +1
Values of r close to -1
indicated a very strong negative linear correlation
Values of r close to +1
indicated a very strong positive linear correlation
Near the value of 0
indicated very weak or no linear correlation between the data
Methodology
•To  get mean (
all value x was added
the sum of x was divided by the total number of observation which
To get mode :
 number of time of value in a data that occurred the most time
To get median:
the data set was arranged in ascending order
the two value of the center of data set was added
the sum of the value was divided by two
•To
  get range:
the smallest value of observation was subtracted by the largest value
of observation
To get interquartile range(IQR):
 the data set was arranged in ascending order
the value of Pn was found where p was the proportion and was the
size of the data set
Pn was an integer that say r , the average of the (r+1)th ordered
value was determined
•  To get first quartile , second quartile , third quartile
P and n was multiplied
after Pn was multiplied, the (r+1) th was determined and multiplied
with
the first quartile was subtracted by third quartile
•   get standard deviation ():
To •To  get variance (:
 all the value x was added and squared all the value x was added and
the sum of the squared value x was squared
divided by the total number of the sum of the squared value x was
observation which divided by the total number of
the mean ( was squared observation which
the squared mean ( was subtracted by the mean ( was squared
the sum of the squared value x that
divided by the total number of the squared mean ( was subtracted
observation which by the sum of the squared value x
that divided by the total number of
the answer was square root
observation which
•To
  draw boxplot:
the smallest value ,largest value , first quartile , third quartile and
median was used
To determine outlier :
lower boundary and upper boundary was calculated
•To  get scatter diagram :
each pair of bivariate data was plotted which x and y
the raw data between two variables was used
To get Pearson correlation coefficient (r) :
the value x was added =
the value y was added =
the value x was squared and all the answer was added =
the value y was squared and all the answer was added =
all value x was multiplied with all value y and the answer was added =
• the value x that added was multiplied with the value y that added
and divided by ,the total number of observations
the answer was subtracted by the value x that multiplied with value
y which all product x and y was added
the answer was divided by square root of value x that squared and
added together was subtracted the value x that squared and added
that divided ,the total number of observations and square root of
value y that squared and added together was subtracted the value y
that squared and added that divided ,the total number of
observations. 
•To  get Spearman rank correlation coefficient (
the rank of x was calculated by arranged the data set ascending and
the position was not changed
if the value of two or three x was same meant it was the same rank
the rank of y was calculated by arranged the data set ascending and
the position was not changed.
 if the value of two or three y was same meant it was the same rank
 difference of rank(D) was calculated when rank of y was subtracted
by rank of x
• answer of difference of rank(D) was squared which and added
together which
value of six was multiplied with
the answer was divided by ,the total number of observations that
was multiplied with the total number of observations that squares
which and value of one was subtracted by
the answer was subtracted by value of one
Result & Conclusion
•Boxplot:
 
o distribution of the Mathematics is skewed to the right since Q3 -Q2
Q2 –Q1 and it had the biggest range between Biology and Malay
o distribution of the Biology is skewed to the right since Q3 -Q2 Q2 –Q1
and it had the second biggest range between Mathematics and Malay
o distribution of the Malay is skewed to the right since Q3 -Q2 Q2 –Q1
and it had the lowest range between Mathematics and Biology
o outlier was not exist
The school plans to give prizes to the top 5% of each subject:
o For Mathematics,the minimum marks to win the prizes:
• 95 mark
 
o For Biology,the minimum marks to win the prizes:
• 92 mark
 
o For Malay,the minimum marks to win the prizes :
• 91 mark
Scatter diagram:
o the variables which x Mathematics and the variable y which Biology
are said to have a positive correlation
o the variables which x Mathematics and the variable y which Malay
are said to have a positive correlation
o the variables which x Biology and the variable y which Malay are said
to have a positive correlation
o this meant that the variables x and y increase or decrease together
• 
Comparison between Pearson correlation coefficient ,and Spearman rank coefficient,
o Pearson correlation very sensitive to extreme values (outliers) but not Spearman rank
coefficient
o Spearman rank coefficient had one advantage over Pearson correlation coefficient is
that it can be used for non-numerical quantities since it assigns ranks to the quantities
o low value of Pearson correlation coefficient which r=0.28,0.21.0.18.So, Pearson
correlation coefficient was sensitive to extreme values
o Spearman rank coefficient was rather strong indicating a linear correlation between
x and y which =0.97,0.96,0.97
o Spearman rank coefficient is not sensitive to extreme value
• 
Conclusion on the performance of students in the examination and the relationship on
the performance between the subjects:
Performance of students in Mathematics :
o most bad compare to the other two subjects
o mean( =40.7 is the lowest compare to the other two subjects
o mode = 70 was second highest compare to the other two subjects
o median =32 was the lowest compare to the other two subjects
o standard deviation( 29.15 was the highest compare to the other two subjects
o variance ( = 849.56 was the highest compare to the other two subjects
o range = 94 was the highest compare to the other two subjects
o interquartile range(IQR) = 54.5 was the highest compare to the other two subjects
• 
Performance of students in Biology:
orather good than Mathematics but bad than Malay
omean( = 44.4 was second highest compare to the other two subjects
omode = 50 was the lowest compare to the other two subjects
omedian = 39 was the second highest compare to the other two subjects
ostandard deviation( 24.73 was second highest compare to the other two subjects.
ovariance ( = 611.69 was the second highest compare to the other two subjects.
orange = 84 was the second highest compare to the other two subjects
o interquartile range(IQR) = 40.5 was the second highest compare to the other two
subjects
 
• 
Performance of students in Malay :
o the best compare to the other two subjects
o mean( =56.13 was the highest compare to the other two subjects
o mode =80 was the highest compare to the other two subjects
o median = 55 was the highest compare to the other two subjects
o standard deviation( 22.80 was lowest compare to the other two subjects
o variance ( = 519.55 was the lowest compare to the other two subjects.
o range = 79 was the lowest compare to the other two subjects.
o interquartile range(IQR) = 39.5 was the lowest compare to the other two subjects
• 
Pearson correlation coefficient(r):
o the relationship between Mathematics and Biology was moderate positive because
r=0.28
o the relationship between Mathematics and Malay was moderate positive because r=0.21
o the relationship between Biology and Malay was moderate positive because r=0.18
Spearman rank coefficient ():
o the relationship between Mathematics and Biology was strong positive because =0.97
o the relationship between Mathematics and Malay was strong positive because =0.96
o the relationship between Biology and Malay was strong positive because =0.97