STATISTICS
Σ
Complete Study Notes
Frequency Distribution | Central Tendency | Dispersion
Graphical Representation | Standard Deviation
Prepared for Karnataka Competitive Examinations
STATISTICS — STUDY NOTES Page 1
TABLE OF CONTENTS
a. Frequency Distribution Table
b. Graphical Representation — Tabular, Pie Chart, Bar Chart, Sector Graph
c. Mean — Measures of Central Tendency (Overview)
d. Arithmetic of Ungrouped Data — Mean and Median
e. Mean, Median and Mode for Grouped Data
f. Range, Quartiles, Deviation and Mean Deviation
g. Statistical Measures — Summary
h. Histogram and Frequency Polygon
i. Collection of Data
j. Calculation of Mean, Median, Mode (Ungrouped Data) — Worked Examples
k. Preparation of Bar Chart and Sector Graph
l. Standard Deviation — Concept
m. Standard Deviation of Ungrouped Data
n. Standard Deviation of Grouped Data
o. Coefficient of Variation
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 2
a. Frequency Distribution Table
A frequency distribution is a systematic arrangement of data (raw scores) into classes or categories along
with the number of times each value or class occurs, called the frequency (f). It converts a large,
disorganised set of raw data into a compact, readable table.
Key Terms
● Class interval: the range into which data is grouped, e.g. 10–20.
● Class limits: the lowest (lower limit) and highest (upper limit) values of a class.
● Class boundaries: true limits obtained by adjusting for gaps between classes (used for continuous data).
● Class width / size (h): difference between the upper and lower boundary of a class.
● Class mark / mid-value: average of the lower and upper limit of a class.
● Frequency (f): number of observations falling in a class.
● Cumulative frequency (c.f.): running total of frequencies up to a class (less-than or more-than type).
Class mark = (Lower limit + Upper limit) ÷ 2
Types of Frequency Distribution
● Discrete (ungrouped): each distinct value listed separately with its frequency.
● Continuous (grouped): data grouped into class intervals, used when the range of values is large.
● Exclusive series: upper limit of one class = lower limit of next (e.g. 10–20, 20–30) — no gap.
● Inclusive series: classes do not overlap (e.g. 10–19, 20–29) — gap between classes; converted to
exclusive form for calculations.
Example — Grouped Frequency Table
Class Interval Tally Frequency (f) Cumulative Frequency
0 – 10 |||| 4 4
10 – 20 |||| | 6 10
20 – 30 |||| |||| 9 19
30 – 40 |||| | 6 25
40 – 50 ||| 3 28
Total 28
★ Exam Tip
Always check that the sum of frequencies in the last column equals the total number of observations
(n).
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 3
b. Graphical Representation — Table, Pie Chart
Graphical representation converts numerical data into visual form, making patterns and comparisons easier to
grasp at a glance.
1. Tabular Representation
Data arranged in rows and columns with clear headings, units and totals. It is the basis for all other graphical
forms and must show the title, column headings, and the source of data.
2. Pie Chart (Sector Diagram)
A circular chart divided into sectors, where each sector's angle is proportional to the value it represents. Total
angle of a circle = 360°.
Angle of a sector = (Value of item ÷ Total value) × 360°
Example: If total sales = 500 units and a product's share = 125 units, its sector angle = (125/500) × 360° = 90°.
3. Bar Chart
Rectangular bars of equal width, with heights (or lengths) proportional to the values represented; bars are
separated by equal gaps. Can be simple, multiple, or sub-divided (stacked).
4. Sector Graph
Another name for the pie chart / pie diagram — used interchangeably in Karnataka exam syllabi.
★ Exam Tip
Pie chart questions almost always test the angle formula — memorise it and practice converting
percentages to degrees quickly.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 4
c. Mean — Measures of Central Tendency
A measure of central tendency is a single value that represents the whole set of data by locating its centre
or typical value. The three main measures are Mean, Median, and Mode.
Measure Definition Best Used When
Mean Sum of all values ÷ number of values Data has no extreme outliers
Median Middle value when data is arranged in order Data has outliers/skewed distribution
Mode Most frequently occurring value Categorical or most-common-value data
The Arithmetic Mean is the most widely used measure and is the sum of all observations divided by their
count.
Mean (x■) = Σx ÷ n
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 5
d. Arithmetic of Ungrouped Data, Median
Mean of Ungrouped Data
x■ = Σx / n
where Σx is the sum of all observations and n is the total number of observations.
Example: Data: 4, 8, 6, 10, 2. Sum = 30, n = 5, so Mean = 30/5 = 6.
Median of Ungrouped Data
The median is the middle-most value when the data is arranged in ascending (or descending) order. It divides
the distribution into two equal halves.
If n is odd: Median = value at position (n+1)/2
If n is even: Median = average of values at positions n/2 and (n/2 + 1)
Example (odd n): Data: 3, 7, 9, 12, 15 (n=5). Median = 3rd value = 9.
Example (even n): Data: 4, 8, 10, 14 (n=4). Median = average of 2nd & 3rd values = (8+10)/2 = 9.
★ Exam Tip
Always arrange data in ascending order first — a common mistake is finding the middle position of
unsorted data.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 6
e. Mean, Median and Mode for Grouped Data
Mean of Grouped Data (Direct Method)
x■ = Σfx / Σf
where x is the class mark (mid-value) of each class and f is its frequency.
Mean of Grouped Data (Assumed Mean / Shortcut Method)
x■ = A + (Σfd / Σf)
where A = assumed mean, d = x − A (deviation of class mark from assumed mean).
Mean of Grouped Data (Step-Deviation Method)
x■ = A + (Σfu / Σf) × h, where u = (x − A) / h
h = class width. This method simplifies calculation when class widths are equal.
Median of Grouped Data
Median = l + [ ((n/2 − cf) / f) × h ]
where: l = lower boundary of the median class; n = total frequency; cf = cumulative frequency before the
median class; f = frequency of the median class; h = class width. The median class is the class where the
cumulative frequency first equals or exceeds n/2.
Mode of Grouped Data
Mode = l + [ (f1 − f0) / (2f1 − f0 − f2) ] × h
where: l = lower boundary of the modal class (class with highest frequency); f1 = frequency of modal class; f0
= frequency of class preceding modal class; f2 = frequency of class following modal class; h = class width.
★ Exam Tip
Remember the empirical relationship: Mode = 3 Median − 2 Mean. It's a quick way to verify your
calculated values or find one measure if the other two are known.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 7
f. Range, Quartile, Deviation and Mean Deviation
Range
The simplest measure of dispersion — the difference between the highest and lowest values in the data.
Range = Maximum value − Minimum value
Quartiles
Quartiles divide an ordered dataset into four equal parts. Q1 (lower quartile) marks the 25% point, Q2
(median) marks 50%, and Q3 (upper quartile) marks 75%.
Q1 = value at (n+1)/4 position; Q3 = value at 3(n+1)/4 position
Interquartile Range (IQR) = Q3 − Q1; Quartile Deviation (QD) = (Q3 − Q1) / 2
Mean Deviation
The average of the absolute deviations of all observations from a central value (usually the mean or median).
Mean Deviation (from mean) = Σ|x − x■| / n
For grouped data: M.D. = Σf|x − x■| / Σf
★ Exam Tip
Mean deviation always uses the absolute (modulus) value of deviations — negative deviations are
treated as positive so they don't cancel out.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 8
g. Statistical Measures — Summary
Statistical measures are broadly grouped into three families, each answering a different question about the
data.
Family Purpose Examples
Measures of Central Tendency Locate the 'centre' of data Mean, Median, Mode
Range, Quartile Deviation,
Measures of Dispersion Show spread / variability
Mean Deviation, Standard Deviation
Measures of Relative Standing Compare variability across datasets Coefficient of Variation
A complete statistical analysis reports both a measure of central tendency (where the data is centred) and a
measure of dispersion (how spread out it is) — the mean alone can be misleading if the spread is not known.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 9
h. Histogram and Frequency Polygons
Histogram
A histogram is a graphical representation of a continuous frequency distribution using adjoining rectangles
(no gaps between bars). Class boundaries are marked on the x-axis and frequencies on the y-axis; the area
of each rectangle is proportional to the class frequency.
● Bars touch each other (unlike a bar chart) because the data is continuous.
● If class widths are unequal, the height must be adjusted: Height = Frequency ÷ Class width.
● Used to visualise the shape of the distribution (symmetric, skewed, etc.).
Frequency Polygon
A frequency polygon is obtained by plotting the class marks (mid-values) against their frequencies and joining
the points with straight lines. It can be drawn directly, or by joining the midpoints of the tops of histogram bars.
● To close the polygon, it is extended to touch the x-axis at one class-width before the first class and one
class-width after the last class (using zero-frequency classes).
● Useful for comparing two or more frequency distributions on the same graph.
★ Exam Tip
Histogram bars are drawn on class boundaries (true limits); if the given data is 'inclusive', convert it to
'exclusive' form first, or the histogram will show gaps.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 10
i. Collection of Data
Statistical data can be collected in two broad ways, and understanding the distinction is a common conceptual
question in exams.
Primary Data
Data collected first-hand by the investigator for a specific purpose. It is original but time-consuming and costly
to gather.
● Direct personal interviews
● Questionnaires and schedules
● Direct observation / experiments
● Telephone or online surveys
Secondary Data
Data that has already been collected by someone else and is being reused. Faster and cheaper, but must be
checked for reliability, suitability, and relevance.
● Government publications and reports (e.g. Census, RBI, NSSO)
● Journals, newspapers, and research papers
● Records of organisations, banks, and institutions
★ Exam Tip
Key distinction: Primary data is original and collected for the current purpose; secondary data is
borrowed from data already gathered for some other purpose.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 11
j. Mean, Median, Mode for Ungrouped Data — Worked
Examples
Worked Example: Data set = 5, 8, 3, 9, 8, 6, 8, 4
Step 1 — Mean:
Sum = 5+8+3+9+8+6+8+4 = 51; n = 8
Mean = 51 ÷ 8 = 6.375
Step 2 — Median:
Arrange in order: 3, 4, 5, 6, 8, 8, 8, 9 (n = 8, even)
Median = average of 4th and 5th values = (6 + 8) / 2 = 7
Step 3 — Mode:
The value 8 occurs three times, more than any other value.
Mode = 8
Measure Value
Mean 6.375
Median 7
Mode 8
★ Exam Tip
A dataset can have one mode (unimodal), two modes (bimodal), or no clear mode at all — check
carefully before answering.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 12
k. Preparation of Bar Chart and Sector Graph
Steps to Draw a Bar Chart
1 Draw two perpendicular axes: categories on the x-axis, values/frequency on the y-axis.
2 Choose a suitable scale for the y-axis based on the range of values.
3 Draw bars of equal width for each category, with equal gaps between bars.
4 Height of each bar must be proportional to the value it represents.
5 Label the axes, give a title, and add a legend if multiple bars are shown per category.
Steps to Draw a Sector Graph (Pie Chart)
1 Find the total of all values in the data.
2 Convert each value's share into a degree measure using: (Value ÷ Total) × 360°.
3 Draw a circle and, using a protractor, mark off each sector's angle starting from a single reference radius.
4 Label each sector with its category name and percentage/value.
5 Shade or colour sectors differently and add a title/legend.
Worked Example — Sector Angles
Category Value Angle (Value/Total × 360°)
Food 200 72°
Rent 300 108°
Savings 150 54°
Others 350 126°
Total 1000 360°
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 13
l. Standard Deviation — Concept
Standard Deviation (SD or σ) is the most widely used and most reliable measure of dispersion. It measures
the average distance of each observation from the mean, using squared deviations to avoid the cancellation
problem seen in mean deviation.
Why Standard Deviation?
● Unlike mean deviation, it uses squares of deviations (not absolute values), making it mathematically easier
to work with in further analysis.
● It gives more weight to larger deviations, making it sensitive to outliers.
● It is the basis for further statistical concepts like variance, correlation, and the normal distribution.
Variance (σ²) = Σ(x − x■)² / n
Standard Deviation (σ) = √[ Σ(x − x■)² / n ]
Standard deviation is simply the positive square root of the variance, and is expressed in the same units as
the original data (unlike variance, which is in squared units).
★ Exam Tip
A smaller standard deviation means the data is more tightly clustered around the mean; a larger SD
means greater spread/variability.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 14
m. Standard Deviation of Ungrouped Data
Direct Method
σ = √[ Σ(x − x■)² / n ]
Shortcut (Actual Mean not needed) Method
σ = √[ (Σx² / n) − (Σx / n)² ]
Worked Example: Data = 2, 4, 6, 8, 10
x x − mean (x − mean)²
2 -4 16
4 -2 4
6 0 0
8 2 4
10 4 16
Total 0 40
Mean = 30/5 = 6; Σ(x−x■)² = 40; n = 5
σ = √(40/5) = √8 = 2.83 (approx.)
★ Exam Tip
If the mean is not a whole number, prefer the shortcut method (using Σx² and Σx) to avoid messy
decimal subtraction at every step.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 15
n. Standard Deviation of Grouped Data
Direct Method
σ = √[ Σf(x − x■)² / Σf ]
Shortcut Method (Assumed Mean)
σ = √[ (Σfd² / Σf) − (Σfd / Σf)² ], where d = x − A
Step-Deviation Method
σ = h × √[ (Σfu² / Σf) − (Σfu / Σf)² ], where u = (x − A)/h
Here x is the class mark, f is the class frequency, A is the assumed mean, and h is the class width. The
step-deviation method is preferred in exams when class widths are equal, since it keeps numbers small and
easy to compute.
★ Exam Tip
Always double check whether the question wants variance or standard deviation — variance is the
squared value and is a very common trap in objective-type exams.
Karnataka Competitive Exams — Mathematics Syllabus
STATISTICS — STUDY NOTES Page 16
o. Coefficient of Variation
The Coefficient of Variation (C.V.) is a relative measure of dispersion, expressed as a percentage. It is used
to compare the variability of two or more datasets that may have different units or very different means.
C.V. = (σ / x■) × 100%
A higher C.V. indicates greater relative variability (less consistency), while a lower C.V. indicates the data is
more consistent/uniform relative to its mean.
Worked Example
Dataset Mean Standard Deviation C.V. (%)
A 50 5 10%
B 60 9 15%
Since Dataset B has a higher C.V. (15%) than Dataset A (10%), Dataset B is relatively more variable (less
consistent), even though its absolute standard deviation and mean are both larger.
★ Exam Tip
C.V. is unit-less (a percentage), which is exactly why it can compare two datasets measured in
completely different units (e.g. marks vs. heights).
— End of Statistics Notes —
Karnataka Competitive Exams — Mathematics Syllabus