STA 111

Comprehensive Study Notes

Topics: Errors & Approximation | Measures of Location | Measures of Partition | Measures of
Dispersion | Skewness & Kurtosis | Index Numbers

Victoria University of Abuja

CHAPTER 1: ERRORS AND APPROXIMATION
1.1 Introduction
In measurements and statistics, we rarely obtain the exact (true) value of a quantity. The difference
between the measured (approximate) value and the true value is called an error. Errors arise from
limitations of instruments, observers, rounding of numbers, and methods of computation.

1.2 Key Definitions

True Value (T) — The exact or correct value of a quantity. This is often unknown in practice.
Approximate / Measured Value (A) — The value obtained from observation or measurement
using available instruments or methods.
Absolute Error (E) — The magnitude of the difference between the true value and the approximate
value.
Relative Error — The ratio of the absolute error to the true value — expresses error as a
proportion.
Percentage Error — The relative error expressed as a percentage of the true value.

1.3 Formulae
Absolute Error: E = T - A
Relative Error = E / T
Percentage Error = (E / T) x 100%

1.4 Types of Errors

1.4.1 Systematic Errors
These occur consistently in one direction (bias). They are predictable and reproducible. Example: an
instrument with a zero error always reads higher or lower by the same amount. Systematic errors can
often be corrected once the source is identified.

1.4.2 Random Errors

These vary unpredictably from one measurement to another. They are due to unpredictable fluctuations
in the measurement process. Random errors can be reduced (but not eliminated) by taking repeated
measurements and computing the average.
1.4.3 Gross Errors
These are large mistakes caused by carelessness — for example, misreading an instrument, recording
wrong digits, or using incorrect units. Gross errors must be avoided through careful technique and
verification.

Error Type Cause Direction Remedy

Systematic Instrument bias, zero Consistent (one Calibration, correction

error direction) factor
Random Unpredictable Both directions Repeated measurements,
fluctuations averaging
Gross Carelessness, Any Careful technique,
misreading double-checking

1.5 Significant Figures

Significant figures are the meaningful digits in a number that carry information about its precision.
• Non-zero digits are ALWAYS significant. Example: 345 has 3 significant figures.
• Zeros between non-zero digits are significant. Example: 3045 has 4 significant figures.
• Leading zeros (before non-zero digits) are NOT significant. Example: 0.0056 has 2 significant
figures.
• Trailing zeros AFTER a decimal point are significant. Example: 3.400 has 4 significant figures.
• Trailing zeros in a whole number are ambiguous unless a decimal point is shown. Example:
1200 could have 2, 3, or 4 significant figures.

1.6 Worked Examples

Example 1: Error Calculations
True value T = 50 cm; Measured value A = 47.5 cm
Absolute Error: E = 50 - 47.5 = 2.5 cm
Relative Error = 2.5 / 50 = 0.05
Percentage Error = (2.5 / 50) x 100% = 5%

Example 2: Significant Figures

Round 0.00678915 to 4 significant figures:
Answer: 0.006789
Note: Leading zeros are not significant. Counting starts from 6: 6, 7, 8, 9 are the 4 significant
figures.
1.7 Rounding Rules
• If the digit after the last significant figure is less than 5, round down (keep the last digit
unchanged).
• If the digit after the last significant figure is 5 or more, round up (increase the last digit by 1).
• Rounding 2345.678 to 3 significant figures gives 2350 (or 2.35 x 10^3).
• Rounding 0.00032582 to 4 significant figures gives 0.0003258.
CHAPTER 2: MEASURES OF LOCATION (CENTRAL
TENDENCY)
2.1 Introduction
Measures of location, also called measures of central tendency, are single values that summarize a
dataset by indicating where the centre of the distribution lies. They help us understand the typical or
representative value of a set of data.
The common measures of central tendency are:
• Arithmetic Mean (AM)
• Median
• Mode
• Geometric Mean (GM)
• Harmonic Mean (HM)
• Quadratic Mean

2.2 The Arithmetic Mean

The arithmetic mean (or simply the mean) is the sum of all observations divided by the number of
observations. It is the most commonly used measure of central tendency.

For Ungrouped Data:

x̄ = (x1 + x2 + x3 + ... + xn) / n = Σxi / n

For Grouped/Frequency Data:

x̄ = Σfx / Σf

Using Assumed Mean (for large values):

x̄ = A + Σfd / Σf
Where A = assumed mean, d = xi - A (deviation from assumed mean)
Tip: Select the class mark with the highest frequency as the assumed mean when none is
specified. The sum of deviations Σfd always equals zero when A equals the true mean.

Advantages of the Arithmetic Mean

• Simple to understand and easy to compute.
• Uses all observations — fully representative of the data.
• Mathematically well-defined; useful in advanced statistical analysis (correlation, regression,
etc.).
• Lends itself to algebraic manipulation.
Disadvantages of the Arithmetic Mean
• Greatly affected by extreme values (outliers) — even a single very large or very small value
distorts the mean.
• May give a physically impossible result (e.g., 2.3 children per family).
• Cannot be calculated for open-ended class intervals without assumptions.
• Cannot be estimated graphically.
• Meaningless for qualitative (categorical) data.

2.3 The Harmonic Mean

The harmonic mean is the reciprocal of the arithmetic mean of the reciprocals of the observations. It is
particularly useful when averaging rates (speed, efficiency, etc.).
HM = n / Σ(1/xi) [Ungrouped]
HM = Σf / Σ(f/x) [Grouped]
• Takes every value into account.
• Extreme values have the least effect compared to AM.
• Cannot be computed when any observation is zero.
• Less intuitive and harder to compute than the AM.

2.4 The Geometric Mean

The geometric mean is an analytical method for finding the average rate of growth or decline over a
period of time. It is the nth root of the product of n observations.
GM = n-th root of (x1 x x2 x x3 x ... x xn)
GM = n-th root of (x1^f1 x x2^f2 x ... x xn^fn) [with frequencies]
Key Property: AM >= GM >= HM for any set of positive numbers.
• Considers all observations in the data.
• Less affected by extreme values than the AM.
• Useful for averaging percentages, ratios, and growth rates.
• Cannot be computed when any observation is zero or negative.

2.5 The Median

The median is the value that divides a distribution into two equal halves when data is arranged in
ascending (or descending) order. Half the values lie below the median and half lie above.
• If n is ODD: Median = the middle value = ((n+1)/2)th term
• If n is EVEN: Median = average of the two middle values = [(n/2)th + (n/2 + 1)th] / 2

For Grouped Data:

Median = L1 + [(N/2 - Cfb) / fm] x w
L1 — Lower class boundary of the median class
 N — Total frequency
Cfb — Cumulative frequency before (below) the median class
fm — Frequency of the median class
w — Class width (size)
Median Class: The class whose cumulative frequency first exceeds N/2.

Advantages of the Median

• Not affected by extreme values (outliers).
• Easy to identify when data is small or already arranged.
• Can be used with open-ended distributions.
• Can be estimated graphically using an ogive.

Disadvantages of the Median

• Not representative for small data sets.
• Difficult to arrange large data sets in order.
• Only an estimate for grouped data (not exact).
• Not as algebraically useful as the mean.

2.6 The Mode

The mode is the value that occurs most frequently in a data set. It is the most popular or most common
value.
A distribution may have:
• No mode (all values occur once)
• One mode — Unimodal
• Two modes — Bimodal
• Three modes — Trimodal
• More than three modes — Multimodal

For Grouped Data:

Mode = Lmo + [Δ1 / (Δ1 + Δ2)] x w
Lmo — Lower class boundary of the modal class (class with highest frequency)
Δ1 — Difference between modal class frequency and the class BEFORE it
Δ2 — Difference between modal class frequency and the class AFTER it
w — Class width

Advantages of the Mode

• Easy to understand and determine.
 • Not affected by extreme values.
• Can be determined for qualitative data.
• Always an actual value in the dataset.

Disadvantages of the Mode

• May not be unique — datasets can have multiple modes.
• Only an approximation for continuous grouped data.
• Does not use all values in the dataset.
• May be undefined or meaningless for some datasets.

2.7 Relationship Between Mean, Median, and Mode

For a moderately skewed distribution, the empirical relationship below holds approximately:
Mode ≈ 3 x Median - 2 x Mean

Distribution Relationship Tail Direction

Symmetric (Normal) Mean = Median = Mode Both sides equal

Positively Skewed Mode < Median < Mean Right (positive) tail
Negatively Skewed Mean < Median < Mode Left (negative) tail
CHAPTER 3: MEASURES OF PARTITION
3.1 Introduction
Just as the median divides a distribution into two equal parts, partition measures divide a distribution
into multiple equal parts. The three main partition measures are Quartiles, Deciles, and Percentiles.

3.2 Quartiles
Quartiles divide an ordered distribution into four equal parts using three values: Q1 (lower/first quartile),
Q2 (second quartile = median), and Q3 (upper/third quartile).

For Ungrouped Data:

Q1 = [(n+1)/4]th term
Q2 = [2(n+1)/4]th term = [(n+1)/2]th term (the Median)
Q3 = [3(n+1)/4]th term

For Grouped Data:

Qi = LQi + [(iN/4 - CfbQi) / fQi] x w (i = 1, 2, or 3)
LQi — Lower class boundary of the quartile class
N — Total frequency
CfbQi — Cumulative frequency before the quartile class
fQi — Frequency of the quartile class
w — Class width

3.3 Deciles
Deciles divide an ordered distribution into TEN equal parts. They are denoted D1, D2, ..., D9. Note that
D5 = Q2 = Median.

For Ungrouped Data:

Di = i x [(n+1)/10]th term (i = 1, 2, ..., 9)

For Grouped Data:

Di = LDi + [(iN/10 - CfbDi) / fDi] x w (i = 1, 2, ..., 9)

3.4 Percentiles
Percentiles divide an ordered distribution into ONE HUNDRED equal parts. They are denoted P1,
P2, ..., P99.
Key Relationships:
• P25 = Q1 (Lower quartile)
• P50 = Q2 = Median
• P75 = Q3 (Upper quartile)
• P10 = D1, P20 = D2, ... P90 = D9

For Ungrouped Data:

Pi = i x [(n+1)/100]th term (i = 1, 2, ..., 99)

For Grouped Data:

Pi = LPi + [(iN/100 - CfbPi) / FPi] x w (i = 1, 2, ..., 99)

Measure Parts Created Number of Values Key Equivalences

Quartiles 4 equal parts 3 (Q1, Q2, Q3) Q2 = Median = D5 = P50
Deciles 10 equal parts 9 (D1 to D9) D5 = Q2; D2.5 = Q1; D7.5 = Q3
Percentiles 100 equal parts 99 (P1 to P99) P25=Q1; P50=Median; P75=Q3

3.5 How to Find the Partition Class (Grouped Data)

Step-by-step procedure:
1. Compute the cumulative frequency column.
2. Calculate the 'locator' value: iN/4 (quartile), iN/10 (decile), or iN/100 (percentile).
3. Find the class whose cumulative frequency first equals or exceeds the locator value.
4. Apply the appropriate formula using that class's boundaries and frequencies.
CHAPTER 4: MEASURES OF DISPERSION OR VARIATION
4.1 Introduction
A measure of central tendency alone does not fully describe a distribution. Two datasets can have the
same mean but very different spreads. Measures of dispersion describe how spread out or scattered
the values are around the central value.
If dispersion is zero, there is no variability and the mean perfectly represents all values. The greater the
dispersion, the less representative the mean becomes.

4.2 The Range

The range is the simplest measure of dispersion. It is the difference between the maximum and
minimum values in the dataset.
Range = Maximum value - Minimum value
• Easy to calculate and understand.
• Sensitive to outliers — a single extreme value drastically changes the range.
• Uses only two data points; ignores all other information.

4.3 Semi-Interquartile Range (Quartile Deviation)

The semi-interquartile range measures the spread of the middle 50% of the data. It is robust to outliers
since it is based on quartiles.
Interquartile Range (IQR) = Q3 - Q1
Semi-Interquartile Range (SIQR) = (Q3 - Q1) / 2
Coefficient of Quartile Deviation = (Q3 - Q1) / (Q3 + Q1)
• Not affected by extreme values.
• Useful for skewed distributions or when outliers are present.
• Based only on Q1 and Q3 — ignores the rest of the data.

4.4 Mean Deviation (Mean Absolute Deviation)

The mean deviation is the average of the absolute differences between each observation and the
mean. It shows, on average, how far each value is from the centre.
MD = Σ|x - x̄ | / n [Ungrouped Data]
MD = Σf|x - x̄ | / Σf [Grouped Data]
Coefficient of Mean Deviation = MD / Mean
• Takes all values into account.
• Easy to interpret (in same units as the data).
• Less mathematically tractable than variance/SD because of absolute values.
4.5 Variance and Standard Deviation
The standard deviation (SD) is the most widely used measure of dispersion. It measures the average
deviation of observations from the mean, using squared deviations to avoid cancellation of signs.

Population Standard Deviation:

σ = sqrt[ Σ(xi - μ)^2 / N ]

Sample Standard Deviation:

s = sqrt[ Σf(x - x̄ )^2 / Σf ]

Variance:
Variance = s^2 = Σf(x - x̄ )^2 / Σf

Computational shortcut formula:

s^2 = [Σfx^2 / Σf] - (x̄ )^2
Relationship: Standard Deviation = √Variance

Properties of Standard Deviation

• Uses all observations in the distribution.
• Has wider application in statistical techniques: skewness, correlation, quality control, hypothesis
testing.
• Cannot directly compare SD of datasets measured in different units.
• Sensitive to extreme values (uses squares of deviations).

4.6 Coefficient of Variation (CV)

The coefficient of variation is a relative measure of dispersion that allows comparison of variability
between datasets measured in different units or with different means.
CV = (Standard Deviation / Mean) x 100%
Interpretation: The dataset with a SMALLER CV is more consistent/less variable. A smaller CV
means the mean is a better representative of the data.

4.7 Summary Comparison of Dispersion Measures

Considers All Outlier
Measure Formula Best Used When
Data? Sensitive?

Range Max - Min No (only 2 pts) Yes (very) Quick overview

SIQR (Q3-Q1)/2 No (middle No Skewed data, outliers
50%)
 Considers All Outlier
Measure Formula Best Used When
Data? Sensitive?
Mean Deviation Σ|x-x̄ |/n Yes Moderately Intuitive spread
Variance Σf(x-x̄ )²/Σf Yes Yes Mathematical analysis
Std Deviation √Variance Yes Yes General use
Coeff. of Var. (SD/Mean)×100 Yes Yes Comparing datasets
CHAPTER 5: MEASURES OF SKEWNESS AND KURTOSIS
5.1 Introduction to Skewness
Skewness refers to the lack of symmetry in a frequency distribution. A symmetric distribution has its
values balanced equally on both sides of the centre. Skewness tells us the direction and degree of the
asymmetry.
We study skewness to understand the shape of the distribution curve and to determine whether the
mean, median, or mode best represents the data.

5.2 Types of Skewness

1. Positive Skewness (Right-Skewed)
The tail extends to the RIGHT. The mean is pulled toward the higher values by extreme observations
on the right. The distribution has more observations clustered on the left.
Relationship: Mode < Median < Mean
Analogy: Think of income distributions — most people earn moderate amounts, but a few very
wealthy individuals pull the mean upward to the right.

2. Negative Skewness (Left-Skewed)

The tail extends to the LEFT. The mean is pulled toward lower values by extreme observations on the
left. The distribution has more observations clustered on the right.
Relationship: Mean < Median < Mode

3. Symmetrical / Normal Distribution

The distribution is perfectly balanced. Neither tail is longer. The mean, median, and mode all coincide
at the centre.
Relationship: Mean = Median = Mode

Type Shape Order of Averages Skewness Value

Positive Skew Right tail longer Mode < Median < Mean Positive (> 0)
Symmetric Bell-shaped, Mean = Median = Mode Zero (= 0)
balanced
Negative Skew Left tail longer Mean < Median < Mode Negative (< 0)
5.3 Measures of Skewness
1. Karl Pearson's Coefficient of Skewness
Method A — Pearson's First Coefficient (using median):
Sk1 = 3(Mean - Median) / Standard Deviation
Method B — Pearson's Second Coefficient (using mode):
Sk2 = (Mean - Mode) / Standard Deviation
Range: Values typically fall between -3 and +3. A value of 0 indicates symmetry.

2. Bowley's Coefficient (Quartile Coefficient of Skewness)

Useful when the distribution has open-ended classes or extreme outliers, since it is based on quartiles
rather than mean and SD.
Sk(Bowley) = (Q3 + Q1 - 2Q2) / (Q3 - Q1)
Range: Values fall between -1 and +1. Zero indicates symmetry.

3. Moment-Based Measure of Skewness (β1)

Based on the statistical moments about the mean:
1st Moment (μ1) = Σ(x - x̄ ) / N = 0 [always zero]
2nd Moment (μ2) = Σ(x - x̄ )^2 / N = Variance (σ^2)
3rd Moment (μ3) = Σ(x - x̄ )^3 / N
4th Moment (μ4) = Σ(x - x̄ )^4 / N
β1 = μ3^2 / μ2^3
Interpretation: β1 = 0 means symmetric. β1 > 0 means positively skewed. The square of μ3 is
used to make β1 always non-negative; the sign of skewness is determined by the sign of μ3 itself.

4. Percentile Coefficient of Skewness

Uses the 10th, 50th, and 90th percentiles:
Sk(Percentile) = (P90 - 2P50 + P10) / (P90 - P10)

5.4 Introduction to Kurtosis

Kurtosis measures the peakedness (or flatness) of a frequency distribution relative to the normal
distribution. While skewness describes asymmetry, kurtosis describes the shape of the peak and tails.

Types of Kurtosis
Mesokurtic — Normal distribution — bell-shaped, not too peaked or flat. β2 = 3.
Leptokurtic — More peaked than normal — tall, narrow peak with heavy tails. β2 > 3.
Platykurtic — Flatter than normal — flat, wide peak with light tails. β2 < 3.
5.5 Measure of Kurtosis (β2)
β2 = μ4 / μ2^2 = 4th Moment / (2nd Moment)^2

β2 Value Type Shape Tail Weight

β2 = 3 Mesokurtic (Normal) Normal bell curve Moderate tails

β2 > 3 Leptokurtic Tall, thin peak Heavy tails
β2 < 3 Platykurtic Flat, wide peak Light tails

Excess Kurtosis: Some textbooks and software use 'excess kurtosis' = β2 - 3. Under this
convention, normal = 0, leptokurtic > 0, platykurtic < 0.
CHAPTER 6: RATES, PROPORTION, AND INDEX
NUMBERS
6.1 Proportion
Proportion is the ratio of the number of items with a certain characteristic to the total number of items in
the group. It expresses a part as a fraction of the whole.
Proportion (P) = n(X) / N
n(X) — Number of items with the characteristic of interest
N — Total number of items in the population or sample
Example: In a population of 350 males and 400 females, proportion of males = 350 / 750 = 7/15 ≈ 0.467

6.2 Rates
When a proportion refers to events occurring over a specific time period, it becomes a rate. Rates are
typically expressed per 1,000 of the population.
Rate = (Number of events / Total population) x 1000
Common types of rates include:
• Birth Rate: number of live births per 1,000 population per year
• Death Rate (Mortality Rate): number of deaths per 1,000 population per year
• Infant Mortality Rate: number of deaths of children under 1 year per 1,000 live births
• Marriage Rate: number of marriages per 1,000 population
• Migration Rate: net number of migrants per 1,000 population

6.3 Index Numbers

An index number is a statistical measure used to quantify relative changes in a variable (or group of
variables) over time, compared to a reference (base) period. The base period is always assigned an
index value of 100.
Index numbers are widely used in economics for tracking price changes, production output, and cost of
living.

6.4 Simple Index Numbers

a. Price Index
Measures the change in the price of a commodity relative to a base period.
Price Index (lt) = (Pt / P0) x 100
Pt — Price in the current (given) time period
P0 — Price in the base period
b. Quantity Index
Measures the change in the volume of goods produced or consumed.
Quantity Index = (Qt / Q0) x 100

c. Value Index
Compares total value (price × quantity) between two time periods.
Value Index = (Vt / V0) x 100 = (Pt x Qt) / (P0 x Q0) x 100

6.5 Composite Index Numbers

Composite indexes combine information from multiple commodities, usually using weights to reflect
their relative importance.

Simple Aggregate Price Index

SAPI = (ΣPt / ΣP0) x 100
Limitation: Does not account for the relative importance (quantity consumed) of different
commodities.

a. Laspeyres Price Index (LPI)

Uses BASE year quantities as weights. It measures how much the base year basket of goods would
cost at current prices.
LPI = (ΣPt·Q0 / ΣP0·Q0) x 100
Tendency: Laspeyres tends to overestimate price increases because it holds base year quantities
fixed, ignoring consumer substitution toward cheaper goods.

b. Paasche's Price Index (PPI)

Uses CURRENT year quantities as weights. It reflects the current consumption pattern.
PPI = (ΣPt·Qt / ΣP0·Qt) x 100
Tendency: Paasche tends to underestimate price increases because it uses current quantities,
which have already adjusted for price changes.

c. Fisher's Ideal Price Index (FIPI)

Fisher's index is the geometric mean of the Laspeyres and Paasche indexes. It is called 'ideal' because
it satisfies both the time reversal and factor reversal tests.
FIPI = √(LPI x PPI)
FIPI = √[(ΣPt·Q0 / ΣP0·Q0) x (ΣPt·Qt / ΣP0·Qt)] x 100
d. Bowley & Dorbish Price Index (BDPI)
The arithmetic mean of the Laspeyres and Paasche indexes.
BDPI = (LPI + PPI) / 2

e. Marshall-Edgeworth Index (MEI)

Uses the average of base and current year quantities as weights.
MEI = [ΣPt(Q0 + Qt) / ΣP0(Q0 + Qt)] x 100

Index Weights Used Formula Properties

Laspeyres (LPI) Base year quantities ΣPtQ0 / ΣP0Q0 × 100 Tends to overestimate; easy to
(Q0) compare over time
Paasche (PPI) Current year ΣPtQt / ΣP0Qt × 100 Tends to underestimate; requires
quantities (Qt) new weights each period
Fisher (FIPI) Geometric mean of √(LPI × PPI) 'Ideal' — satisfies reversal tests
both
Bowley (BDPI) Arithmetic mean of (LPI + PPI) / 2 Simple compromise between L
both and P
Marshall- Average of Q0 and ΣPt(Q0+Qt) / More balanced than L or P alone
Edgeworth Qt ΣP0(Q0+Qt) × 100

6.6 Choice of Base Period

The base period should be:
• A 'normal' period — not affected by unusual events such as wars, natural disasters, or
economic crises.
• Not too far in the past, so comparisons remain meaningful.
• Clearly defined, with reliable data available.

6.7 Uses of Index Numbers

• Measuring inflation and changes in the cost of living (Consumer Price Index / CPI).
• Comparing economic productivity across industries or nations.
• Deflating nominal values to real values (adjusting for inflation).
• Guiding government policy, wage negotiations, and business decisions.
• Tracking stock market performance (e.g., NSE Index, S&P 500).
QUICK REFERENCE: KEY FORMULAE

Topic Formula / Definition

Absolute Error E=T-A

Percentage Error (E / T) × 100%
Arithmetic Mean (ungrouped) x̄ = Σx / n
Arithmetic Mean (grouped) x̄ = Σfx / Σf
Assumed Mean Method x̄ = A + Σfd / Σf
Harmonic Mean HM = n / Σ(1/xi)
Geometric Mean GM = n-th root of (x1 × x2 × ... × xn)
Median (grouped) L1 + [(N/2 - Cfb) / fm] × w
Mode (grouped) Lmo + [Δ1 / (Δ1 + Δ2)] × w
Q1 (ungrouped) [(n+1)/4]th term
Q3 (ungrouped) [3(n+1)/4]th term
Qi (grouped) LQi + [(iN/4 - Cfb) / fQi] × w
Di (grouped) LDi + [(iN/10 - Cfb) / fDi] × w
Pi (grouped) LPi + [(iN/100 - Cfb) / FPi] × w
Range Max - Min
IQR Q3 - Q1
Semi-IQR (Q3 - Q1) / 2
Mean Deviation (ungrouped) Σ|x - x̄ | / n
Mean Deviation (grouped) Σf|x - x̄ | / Σf
Variance (grouped) Σf(x - x̄ )² / Σf
Standard Deviation √Variance
Coefficient of Variation (SD / Mean) × 100%
Pearson's 1st Skewness 3(Mean - Median) / SD
Pearson's 2nd Skewness (Mean - Mode) / SD
Bowley's Skewness (Q3 + Q1 - 2Q2) / (Q3 - Q1)
β1 (Moment Skewness) μ3² / μ2³
β2 (Kurtosis) μ4 / μ2²
Price Index (Pt / P0) × 100
 Topic Formula / Definition
Laspeyres Price Index ΣPtQ0 / ΣP0Q0 × 100
Paasche Price Index ΣPtQt / ΣP0Qt × 100
Fisher's Ideal Index √(LPI × PPI)
Proportion n(X) / N

End of STA 111 Study Notes — Good Luck!