STATISTICS COMPLETE STUDY NOTES
Grouped & Ungrouped Data • Quartiles • Variance • Standard Deviation • Frequency
Distributions • Graphs & Ogives
Purpose: A step-by-step revision guide with formulas, tables, worked examples, and graph-construction instructions.
How to use this book: Learn the definition → identify the type of data → choose the formula → make the calculation
table → substitute → check the answer.
Statistics Complete Study Notes Page 1
CONTENTS
1. Basic statistical ideas
2. Frequency distributions and class boundaries
3. Graphs: bar graph, histogram and frequency polygon
4. Cumulative frequency and ogives
5. Mean, median and mode
6. Quartiles, percentiles and interquartile range
7. Range and variance
8. Population variance vs sample variance
9. Standard deviation
10. Grouped-data variance and standard deviation
11. Box plots and five-number summary
12. Quick formula sheet
13. Practice questions with answers
Statistics Complete Study Notes Page 2
1. BASIC STATISTICAL IDEAS
Statistics is the collection, organization, presentation, analysis and interpretation of data.
Population: the complete group being studied. Sample: a subset selected from the population.
Parameter: a numerical measure describing a population. Statistic: a numerical measure calculated from a sample.
Discrete data: countable values such as number of students. Continuous data: measurements that can take values
within an interval, such as height or weight.
Ungrouped data: individual observations are listed. Grouped data: observations are summarized into class intervals.
Example: identify the type of data
Situation Type
Number of children in a family Discrete
Height of students Continuous
Individual test scores listed separately Ungrouped
Scores summarized as 0–9, 10–19, 20–29 Grouped
2. FREQUENCY DISTRIBUTIONS AND CLASS BOUNDARIES
Frequency (f) is the number of observations in a category or class.
Class limits are the stated lower and upper values of a class. Class boundaries remove gaps between adjacent
classes.
For whole-number classes such as 10–19 and 20–29, the boundaries are 9.5–19.5 and 19.5–29.5.
Class width = upper boundary − lower boundary.
Class midpoint = (lower limit + upper limit) / 2.
Class interval Lower boundary Upper boundary Midpoint Frequency
10–19 9.5 19.5 14.5 5
20–29 19.5 29.5 24.5 8
30–39 29.5 39.5 34.5 12
40–49 39.5 49.5 44.5 7
Notice: in a histogram, the class boundaries form the continuous horizontal scale and the bars touch. In a bar graph,
categories are separated by gaps.
3. GRAPHS: BAR GRAPH, HISTOGRAM AND FREQUENCY
POLYGON
Bar graph: categorical/discrete data; bars have gaps.
Histogram: continuous grouped data; class boundaries are on the horizontal axis and bars touch.
Frequency polygon: plot class midpoints against frequency and join the points with straight lines. Often add
zero-frequency points one class width before the first midpoint and after the last midpoint.
Example frequency polygon points
Statistics Complete Study Notes Page 3
Class Midpoint Frequency
10–19 14.5 5
20–29 24.5 8
30–39 34.5 12
40–49 44.5 7
Plot (14.5,5), (24.5,8), (34.5,12), (44.5,7), then join the points. Use the class midpoints, not the upper boundaries, for
the frequency polygon.
Exam reminder: Histogram → boundaries. Frequency polygon → midpoints. Bar graph → categories.
4. CUMULATIVE FREQUENCY AND OGIVES
Cumulative frequency (CF) is the running total of frequencies.
For a less-than cumulative frequency, add frequencies from the first class upward. For a greater-than cumulative
frequency, start with the total and subtract frequencies successively.
Class f Less-than CF Greater-than CF
10–19 5 5 32
20–29 8 13 27
30–39 12 25 19
40–49 7 32 7
Less-than ogive: plot upper class boundaries against cumulative frequency. Include the starting lower boundary with
cumulative frequency 0.
Greater-than ogive: plot lower class boundaries against greater-than cumulative frequency.
To estimate the median, Q1, Q3 or a percentile from an ogive: calculate the required cumulative-frequency position,
locate it on the vertical axis, move horizontally to the curve, then drop vertically to the horizontal axis.
5. MEAN, MEDIAN AND MODE
UNGROUPED MEAN
Mean = Σx / n
Example: 6, 7, 10, 11, 11, 13, 16, 18, 25
Σx = 117 and n = 9, so mean = 117/9 = 13.
GROUPED MEAN
For grouped data, use the class midpoint x and frequency f:
Mean = Σfx / Σf
Class f Midpoint x fx
10–19 5 14.5 72.5
20–29 8 24.5 196
30–39 12 34.5 414
40–49 7 44.5 311.5
Statistics Complete Study Notes Page 4
Class f Midpoint x fx
Total 32 994
Mean = 994/32 = 31.0625.
MEDIAN
Ungrouped: arrange the data in ascending order. If n is odd, median is the middle observation. If n is even, median is
the average of the two middle observations.
Grouped-data median formula:
Median = L + [(N/2 − CF) / f] × h
where L = lower class boundary of median class; N = total frequency; CF = cumulative frequency before median class;
f = frequency of median class; h = class width.
MODE
Ungrouped mode = the value occurring most often.
For grouped data, the modal class is the class with the highest frequency. An approximate grouped mode is:
Mode = L + [(f■ − f■)/(2f■ − f■ − f■)] × h
f■ = modal-class frequency; f■ = frequency before it; f■ = frequency after it.
6. QUARTILES, PERCENTILES AND IQR
Quartiles divide ordered data into four parts:
Q1 = 25th percentile; Q2 = 50th percentile (median); Q3 = 75th percentile.
Ungrouped-data position convention: many introductory courses use Qk position = k(n+1)/4. Some courses use
different conventions, so follow your lecturer's stated rule.
Example: data 2, 4, 5, 7, 8, 10, 12, 15 (n=8). Positions: Q1 = 2.25th, Q2 = 4.5th, Q3 = 6.75th under the (n+1) rule, with
interpolation where required.
Interquartile range: IQR = Q3 − Q1.
Quartile deviation / semi-IQR: (Q3 − Q1)/2.
GROUPED QUARTILES
Q1 = L + [(N/4 − CF)/f] × h
Q2 = L + [(N/2 − CF)/f] × h
Q3 = L + [(3N/4 − CF)/f] × h
Use the class containing the relevant cumulative-frequency position.
Percentile for grouped data: Pk = L + [(kN/100 − CF)/f] × h.
7. RANGE AND VARIANCE
Range = maximum − minimum.
Variance measures the average squared distance of observations from their mean. Because deviations are squared,
variance is expressed in squared units.
For a population:
σ² = Σ(x − µ)² / N
Statistics Complete Study Notes Page 5
For a sample:
s² = Σ(x − x■)² / (n − 1)
WORKED POPULATION EXAMPLE
Data: 6, 7, 10, 11, 11, 13, 16, 18, 25
Mean µ = 117/9 = 13.
x x − 13 (x − 13)²
6 −7 49
7 −6 36
10 −3 9
11 −2 4
11 −2 4
13 0 0
16 3 9
18 5 25
25 12 144
Total 280
Population variance = 280/9 = 31.11.
Population standard deviation = √31.11 ≈ 5.58.
SHORTCUT FORMULA
Population variance = Σx²/N − µ²
For the same data, Σx² = 1801. Therefore σ² = 1801/9 − 13² = 31.11.
8. POPULATION VARIANCE VS SAMPLE VARIANCE
This distinction is very important in examinations.
Population Sample
Mean µ x■
Number of values N n
Variance σ² = Σ(x−µ)²/N s² = Σ(x−x■)²/(n−1)
SD σ = √σ² s = √s²
Use when data are the entire population data are a sample from a population
Using the same nine values as a sample, the sum of squared deviations is 280. Sample variance = 280/(9−1) = 35.
Sample standard deviation = √35 ≈ 5.92.
Why n−1? Dividing by n−1 gives an unbiased estimator of population variance when a sample is used to estimate the
population variance.
9. STANDARD DEVIATION
Standard deviation is the square root of variance and is therefore expressed in the original units of the data.
Statistics Complete Study Notes Page 6
Population: σ = √[Σ(x−µ)²/N]
Sample: s = √[Σ(x−x■)²/(n−1)]
Interpretation: a smaller standard deviation means observations are generally closer to the mean; a larger standard
deviation means they are more spread out.
Coefficient of variation: CV = (standard deviation / mean) × 100%. It is useful for comparing relative variability
between datasets with different means or units.
10. GROUPED-DATA VARIANCE AND STANDARD DEVIATION
For grouped data, use the class midpoint x as the representative value for every observation in that class.
Population grouped variance:
σ² = Σf(x − µ)² / N
Shortcut:
σ² = Σfx²/N − µ²
Sample grouped variance (using midpoint approximation):
s² = [Σf(x − x■)²]/(N − 1)
WORKED EXAMPLE
Class f x fx x² fx²
10–19 5 14.5 72.5 210.25 1051.25
20–29 8 24.5 196 600.25 4802
30–39 12 34.5 414 1190.25 14283
40–49 7 44.5 311.5 1980.25 13861.75
Total 32 994 33998
Mean µ = Σfx/N = 994/32 = 31.0625.
Population variance = Σfx²/N − µ² = 33998/32 − (31.0625)² ≈ 91.31.
Population standard deviation ≈ √91.31 = 9.56.
Because grouped data replace each class by its midpoint, this is an approximation to the variance of the original
observations.
ASSUMED-MEAN / STEP-DEVIATION METHOD
When numbers are large, choose an assumed mean A and define d = x − A. If class width is h, define u = (x − A)/h.
These methods reduce arithmetic. Your lecturer may provide a specific shortcut formula; always use the exact
convention taught in class.
11. BOX PLOTS AND FIVE-NUMBER SUMMARY
A five-number summary contains: minimum, Q1, median (Q2), Q3, maximum.
A box-and-whisker plot displays Q1 to Q3 as a box, the median inside the box, and whiskers extending toward the
minimum and maximum (depending on the convention used).
IQR = Q3 − Q1. A common outlier rule is: lower fence = Q1 − 1.5(IQR); upper fence = Q3 + 1.5(IQR). Values beyond
the fences are potential outliers.
Box plots are useful for comparing the center, spread and skewness of several datasets.
Statistics Complete Study Notes Page 7
12. QUICK FORMULA SHEET
Quantity Formula
Ungrouped mean x■ = Σx/n
Grouped mean x■ = Σfx/Σf
Population variance σ² = Σ(x−µ)²/N
Sample variance s² = Σ(x−x■)²/(n−1)
Population shortcut σ² = Σx²/N − µ²
Sample SD s = √s²
Population SD σ = √σ²
Range maximum − minimum
IQR Q3 − Q1
Quartile deviation (Q3 − Q1)/2
Grouped Q1 L + [(N/4−CF)/f]h
Grouped median L + [(N/2−CF)/f]h
Grouped Q3 L + [(3N/4−CF)/f]h
Grouped percentile Pk L + [(kN/100−CF)/f]h
Class midpoint (lower limit + upper limit)/2
Class width upper boundary − lower boundary
CV (SD/mean) × 100%
GRAPH MEMORY RULE
Bar graph → categories + gaps. Histogram → class boundaries + touching bars. Frequency polygon → class
midpoints. Less-than ogive → upper boundaries + cumulative frequency. Greater-than ogive → lower boundaries +
cumulative frequency.
13. PRACTICE QUESTIONS WITH ANSWERS
Question 1: For 4, 6, 7, 9, 9, 10, 12, find the mean, median, mode and range.
Answer: Mean = 57/7 = 8.14; median = 9; mode = 9; range = 12−4 = 8.
Question 2: A population is 2, 4, 6, 8, 10. Find the population variance and standard deviation.
Mean = 6. Squared deviations = 16, 4, 0, 4, 16; sum = 40. Variance = 40/5 = 8. SD = √8 ≈ 2.83.
Question 3: The same five values are treated as a sample. Find sample variance and sample SD.
Sample variance = 40/(5−1) = 10. Sample SD = √10 ≈ 3.16.
Question 4: Classes 0–9, 10–19, 20–29 have frequencies 4, 7, 9. Find midpoints and total frequency.
Midpoints = 4.5, 14.5, 24.5. Total frequency = 20.
Question 5: State which horizontal values are used for each graph.
Graph Horizontal values
Bar graph Categories
Statistics Complete Study Notes Page 8
Graph Horizontal values
Histogram Class boundaries
Frequency polygon Class midpoints
Less-than ogive Upper class boundaries
Greater-than ogive Lower class boundaries
FINAL EXAM CHECKLIST
• Always sort ungrouped observations before finding median or quartiles.
• Check whether the question says population or sample before calculating variance.
• For a sample variance, the denominator is n−1, not n.
• For grouped mean/variance, calculate class midpoints carefully.
• Check that the frequencies add to the total N.
• Use class boundaries for a histogram and upper boundaries for a less-than ogive.
• Use midpoints for a frequency polygon.
• Include units for variance (squared units) and standard deviation (original units).
• Round only at the final step unless the question instructs otherwise.
END OF NOTES
Use these notes together with your lecturer's formula conventions, especially for quartile-position rules, because different textbooks can use
different conventions.
Statistics Complete Study Notes Page 9