STATISTICS AND DATA Examples:

Lesson 4: Symmetric and Asymmetric Distributions • Right-skewed distribution

• The scores of students who did not study for a
Symmetric Distribution major examination
• Property of a distribution that has the mean as • The household income of Filipinos in a certain
the center, acting as a mirror image of the two area in the National Capital Region
sides of the distribution • Left-skewed distribution
• Most of the data values are found near the • The number of people buying Christmas presents
mean, tapering off on both sides of the mean. during December.
• The mean is equal to the median. • The hours that children spend playing with their
gadgets
Asymmetric Distribution
• Lack of symmetry STATISTICS AND DATA
• Can be right-skewed distribution or left-skewed Lesson 5: Presentation and Interpretation of Data
distribution
Frequency Distribution Table
• Right-skewed distribution • Arrangement of raw data into class intervals and
frequency
Kinds of Frequency Distribution Table
• Categorical Frequency Distribution Table
• Grouped Frequency Distribution Table

Categorical Frequency Distribution Table

• Qualitative Data – either nominal or ordinal level
of measurement
• Count how many observations are in each
category
 Left-skewed distribution • Table below shows an example of the
distribution of students in MC College

Bar Graph and Pie Chart

• Qualitative Data – either nominal or ordinal level
of measurement
Pearson Coefficient of Skewness • Used to describe frequency (bar graphs) and
(𝑥̅ − 𝑚𝑒𝑑𝑖𝑎𝑛) relative frequency (pie charts)
𝑆𝑘 = 3
𝑠
Calculate for the coefficient of skewness if the mean is
76 and the median is 75 with standard deviation is 0.75.

(𝑥̅ − 𝑚𝑒𝑑𝑖𝑎𝑛) 76 − 75
𝑆𝑘 = 3 = 3[ ]=4
𝑠 0.75
Grouped Frequency Distribution
IMPORTANT NOTES (FOR ASYMMETRIC DISTRIBUTION
• Quantitative data – interval or ratio level of
ONLY):
measurement
1. If the Sk is less than -1 or greater than 1, then the
• There are steps involved in constructing a
distribution is highly skewed.
grouped frequency distribution table
2. If the Sk is between -1 or -1/2 or between ½ and 1, then
the distribution is moderately skewed.
Constructing a Grouped Frequency Distribution Table
3. If the Sk is between -1/2 and 1, then the distribution
1. Determine the lowest and highest values and
is approximately normal.
calculate the range. The range is the difference
4. If the Sk is 0, then the distribution is normally
between these two values.
distributed.
2. Calculate the class width by dividing the range and the
number of class intervals. Round –up the obtained
*If the mean is greater than the median, it is a RIGHT
value.
SKEWED DISTRIBUTION.
3. Start the table with the lowest value and add the class
*Ifthe median is greater than the mean, it is a LEFT
width to obtain the lower limits of the class intervals.
SKEWED DISTRIBUTION.
Obtain the upper limits by subtracting 1 from the

1|Ma thema tics in the Mode rn World

second lower limit and add the class width
successively.
4. Count how many observations are within the
intervals. This is the frequency column

Example:
The data below shows the grades of twenty students
who took the 50-item test in Integral Calculus:
Make a grouped frequency distribution table with 4 class
intervals .

• By the histogram, it can be noted that the students

got high scores. The scores that the students got
follow an asymmetric distribution, particularly left-
skewed distribution.
• This may be interpreted as:
1. Determine the lowest and highest values and • The exam was very easy
calculate the range. The range is the difference • The students were able to study well.
between these two values. • The teacher taught the subject matter very
Highest value = 45 efficiently.
lowest value = 10
Range = 45 – 10 = 35 Stem-and-Leaf Plot
2. Calculate the class width by dividing the range and • Raw data are plotted
the number of class intervals. Round –up the obtained • The first digits form the “stem” and the second
value. digits form the “leaf”
𝟑𝟓
class width = = 𝟖. 𝟕𝟓 ≈ 𝟗
𝟒
3. Start the table with the lowest value and add the class
width to obtain the lower limits of the class intervals.
Obtain the upper limits by subtracting 1 from the second
lower limit, writing it beside the lowest value and add the Box-and-Whisker Plot
class width successively. • Five-number summary
• Minimum, lower quartile, median, upper quartile,
maximum
• Used when there are extreme values in the
dataset, that is, outliers are present
• Outliers lie beyond the ranges of values and can be
determined by using:
lower quartile – 1.5IQR
upper quartile + 1.5IQR

Example:
4. Count how many observations are within the • Minimum = 10; Maximum = 45; Median = 34.5
intervals. This is the frequency column. • Lower quartile = 24.5; upper quartile = 40
• Interquartile range = 40 – 24.5 = 15.5
• Outliers should lie beyond lower quartile – 1.5IQR
and upper quartile + 1.5IQR.
• 24.5 – 1.5(15.5) = 1.25 and 40 + 1.5(15.5) =
63.25
• There are no outliers since there are no values
Histogram outside 1.25 and 63.25.
• Vertical bars that have no gaps because of class
boundaries
• Upper class boundaries: upper limit + 0.5
Lower class boundaries: lower limit – 0.5

2|Ma thema tics in the Mode rn World

Example (2): • Solve using the Table of Areas under the
• Below is the box-and-whisker plot for the dataset Normal Curve

Finding Areas – Examples

1. 𝑷(𝟎 ≤ 𝒛 ≤ 𝟎. 𝟓𝟔) ; 𝑷(𝟎 ≤ 𝒛 ≤ 𝟎. 𝟓𝟔) = 𝟎. 𝟐𝟏𝟐𝟑

• The box-and-whisker plot shows that the data is

not symmetric

DATA MANAGEMENT TOOLS

Lesson 1: Normal Distribution

Normal Distribution (z-distribution)

• Continuous probability distribution 2. 𝑷(−𝟏. 𝟐𝟓 ≤ 𝒛 ≤ 𝟎) ; 𝑷(−𝟏. 𝟐𝟓 ≤ 𝒛 ≤ 𝟎) = 𝟎. 𝟑𝟗𝟒𝟒
• Uses interval or ratio level of measurement

Properties of the Normal Distribution

• It is a bell-shaped curve 𝟑. 𝑷(𝒛 ≤ 𝟎. 𝟓𝟔) ; 𝑷(𝒛 ≤ 𝟎. 𝟓𝟔) = 𝟎. 𝟕𝟏𝟐𝟑
• The total area under the normal curve is 1.
• The tails of the normal curve are asymptotic to
the horizontal axis
• The curve is symmetrical to the mean
• It is determined by two parameters, µ and 
• The mean, median and mode have equal values

The Standard Normal Distribution 4. 𝑷(𝒛 < −𝟐. 𝟏𝟔) ; 𝑷(𝒛 < −𝟐. 𝟏𝟔) = 𝟎. 𝟎𝟏𝟓𝟒
• Same as the Normal distribution, including the
properties EXCEPT
𝝁 = 𝟎 and 𝝈 = 𝟏

5. 𝑷(|𝒛| ≤ 𝒛𝟎 ) = 𝟎. 𝟖𝟒 is the same as 𝑷(−𝒛𝟎 ≤ 𝒛 ≤

𝒛𝟎 ) = 𝟎. 𝟖𝟒

z-value of 0.4200 is 1.41 (0.4207)

Finding Areas under the Normal Curve 𝒛 = ±𝟏. 𝟒𝟏

• Concept of probability will be used: 0 ≤ 𝑃 ≤ 1
• Table of Areas under the Normal Curve will be
used
• Three things to remember when using the z-
distribution
• Draw the bell-shaped curve
• Shade the appropriate area
3|Ma thema tics in the Mode rn World
6. The area to the right of z is 0.6664. What is the z-
value?
z-value of 0.1664 is – 0.43

If the mean is 100 with a standard deviation of 15, what

Transformation to the z-score: value marks the upper 10% of the data?
𝑥−𝜇 The z-value of 0.4000 is – 1.28(0.3997)
𝑧=
𝜎 𝑥 = (15)(−1.28) + 100 = 80.8
If the area is given, 𝑥 = 𝑧𝜎 + 𝜇

Application of the Normal Distribution – Example

• The grocery store at the corner of a busy street has an
average petty cash of Php3,500 and a standard
deviation of Php500. Assuming that the petty cash
are normally distributed.
a. Find the probability that the petty cash is over
Php3,550
b. Find the probability that the petty cash is less
than Php4,000. DATA MANAGEMENT TOOLS
c. What is the probability that the petty cash is Lesson 2: Linear Correlation Analysis
between Php3,000 and Php3,700?
Linear Correlation Analysis
a. find the probability that the petty cash is over • Study of the relationship between independent
Php3,550 and dependent variables
𝟑𝟓𝟓𝟎 − 𝟑𝟓𝟎𝟎 • Measures the strength and direction of
𝒛= = 𝟎. 𝟏(𝟎. 𝟎𝟑𝟗𝟖) continuous bivariate data
𝟓𝟎𝟎

Correlation Coefficient, r
• Determines if there is a linear relationship
between two variables

Scatterplot
• Graph that shows the linear relationship
b. find the probability that the petty cash is less than between the two variables
Php4,000.
𝟒𝟎𝟎𝟎 − 𝟑𝟓𝟎𝟎
𝒛= = 𝟏(𝟎. 𝟑𝟒𝟏𝟑)
𝟓𝟎𝟎

Pearson Product Moment Correlation Coefficient

[𝑛 ∑ 𝑋𝑌 − ∑ 𝑋 ∑ 𝑌]
𝑟=
c. What is the probability that the petty cash is between √[𝑛 ∑ 𝑋2 − (∑ 𝑋)2 ][𝑛 ∑ 𝑌 2 − (∑ 𝑌)2 ]
Php3,000 and Php3,700? where
𝟑𝟎𝟎𝟎 − 𝟑𝟓𝟎𝟎 X = values of the independent variable
𝒛𝟏 = = −𝟏(𝟎. 𝟑𝟒𝟏𝟑)
𝟓𝟎𝟎 Y = values of the dependent variable
𝟑𝟕𝟎𝟎 − 𝟑𝟓𝟎𝟎
𝒛𝟐 = = 𝟎. 𝟒(𝟎. 𝟏𝟓𝟓𝟒)
𝟓𝟎𝟎

4|Ma thema tics in the Mode rn World

• Tells how much of the variance in the values of
Pearson Product Moment Correlation Coefficient – one variable can be explained by the values on
Example another variable
• A medical researcher wants to know if there is a linear • Square of the correlation coefficient, r
relationship between toddler’s age (months) and
their height (cm). Data are shown below: Regression Line – Example
Toddler’s age and Height have a linear relationship.
Determine the regression line and explain the
coefficient of determination

6(7866) − (102)(458)
𝑟=
√[6(1838) − (102)2 ][6(35070) − (458)2 ]
47196−46716
=
√[624][656]

= 0.75
6(7866) − (102)(458)
𝑟=
√[6(1838) − (102)2 ][6(35070) − (458)2 ]

47196−46716
=
√[624][656]

= 0.75

DATA MANAGEMENT TOOLS

Lesson 3: Simple Linear Regression Analysis If the toddler is 21 months old, then its height is
̂ = 𝟔𝟑. 𝟑𝟔 + 𝟎. 𝟕𝟕(𝟐𝟏) = 𝟕𝟗. 𝟒𝟑 𝒄𝒎
𝒚
Simple Linear Regression Analysis
• Analyzes the linear relationship between the Regression Line – Example(2)
independent and dependent variables Toddler’s age and Height have a linear relationship.
• Before linear regression analyses, linear Determine the regression line and explain the
relationship must be guaranteed coefficient of determination

Regression Line Coefficient of Determination: 𝑟 2 = (0.75)2 = 0.5625

𝑦̂ = 𝑎 + 𝑏𝑥 Interpretation:
where 56.25% of the height of toddler’s is explained by their
̂ = predicted value of the dependent variable y
𝒚 age. There are other factors which are needed to explain
a = intercept of the regression line their height.
b = slope of the regression line
x = value of the independent variable
LINEAR PROGRAMMING
∑ 𝑌 ∑ 𝑋 2 −∑ 𝑋 ∑ 𝑋𝑌 Lesson 1: Linear Programming
𝑎=
𝑛 ∑ 𝑋 2 −(∑ 𝑋)2

Linear Programming Problem

𝑛 ∑ 𝑋𝑌−∑ 𝑋 ∑ 𝑌
𝑏=
𝑛 ∑ 𝑋 2 −(∑ 𝑋)2
• A linear programming problem has either of the
two objectives:
Coefficient of Determination, 𝒓𝟐 • Maximize profit
• Percent variation in the dependent variable • Minimize cost
which is explained by all the independent
variables put together

5|Ma thema tics in the Mode rn World

Terms to consider in LPP
• Objective function: either to maximize profit or
to minimize cost
• Structural constraints (explicit): are the
limitations on the availability of resources
• Non-negativity constraints (implicit): set the
variables to non-negative solutions

Steps in Solving Linear Programming Problems Using

Graphical Method
• Change the inequality to equality and graph
• Change the equality to inequality again and Substituting the corner points in the
apply the origin test to determine if the result objective function:
will give a true or false statement. If the result (2,0): 5(2) +7(0) = 10
gives a true statement, then shade the area (5,0): 5(5) + 7(0) = 25
where the origin lies. Otherwise, shade the (5/7, 45/7): 5(5/7) + 7(45/7) = 48.57
other half-plane. Hence, maximum value is 48.57 at (5/7, 45/7).
• Determine the corner points of the feasible
region. Substitute them to the objective 3. Min: P  5x  7y
function: if the problem involves maximization, Subject to: 5x  y  10 (0,10), (2,0)
get the highest value and if the problem involves
3x  2 y  15 (0,7.5), (5,0)
minimization, get the lowest value.
x  0, y  0
Maximization LPP Graphical Method Substituting the corner points in the
1. Max: P  5x  7y objective function:
(2,0): 5(2) +7(0) = 10
Subject to: 5x  y  10 (0,10), (2,0)
(5,0): 5(5) + 7(0) = 25
3x  2 y  15 (0,7.5), (5,0) (5/7, 45/7): 5(5/7) + 7(45/7) = 48.57
x  0, y  0 Hence, the minimum value is 10 at (2,0).
Substituting the corner points in the
objective function:
(2,0): 5(2) +7(0) = 10
(5,0): 5(5) + 7(0) = 25
(5/7, 45/7): 5(5/7) + 7(45/7) = 48.57

2. Max: P  5x  7y
Subject to: 5x  y  10 (0,10), (2,0)
3x  2 y  15 (0,7.5), (5,0)
x  0, y  0

6|Ma thema tics in the Mode rn World