Quintiles

MoneyBestPal Team
A statistical technique used to divide a huge set of data into five equal portions, each with the same number of data points.
Image: Moneybestpal.com

Main Findings

  • Quintiles are a statistical tool for dividing a data set or population into five equal parts, each containing 20% of the observations.
  • Quintiles are commonly used in finance to analyze and compare the performance of different assets, portfolios, or income distributions.
  • Quintiles can help to simplify and understand large data sets or populations by creating cut-off points or benchmarks.


Quintile is a statistical term that refers to the division of a data set into five equal parts, each containing 20% of the observations.


Quintiles are commonly used in finance to analyze and compare the performance of different assets, portfolios, or income distributions.



Why Use Quintiles in Finance?

Quintiles can help simplify and understand large data sets by creating cut-off points that define certain characteristics or ranges of values. For example, quintiles can be used to categorize companies by their market capitalization, assets by their returns, or households by their income levels.


Quintiles can also be used to measure the inequality or diversity of a data set by comparing the differences between the lower and upper quintiles.



Formula for Quintiles

The formula for calculating quintiles is based on the following steps:

  • Sort the data set in ascending order
  • Find the number of observations (n) in the data set
  • Find the rank (i) of each quintile using the formula i = n * k / 5, where k is the quintile number (1, 2, 3, 4, or 5)
  • If i is an integer, then the value of the kth quintile is the average of the ith and (i+1)th observations
  • If i is not an integer, then round it up to the nearest integer and take the value of that observation as the kth quintile



How to Calculate Quintiles

To illustrate how to calculate quintiles, let us use an example of a data set that contains the annual returns of 10 stocks:


Image: Moneybestpal.com

1. The first step is to sort the data set in ascending order:


Image: Moneybestpal.com


2. The second step is to find the number of observations (n) in the data set, which is 10.

3. The third step is to find the rank (i) of each quintile using the formula i = n * k / 5, where k is the quintile number (1, 2, 3, 4, or 5).


For the first quintile (k = 1), i = 10 * 1 / 5 = 2. Since i is an integer, then the value of the first quintile is the average of the second and third observations, which are 7% and 8%, respectively. Therefore, the first quintile is (7 + 8) / 2 = 7.5%.


For the second quintile (k = 2), i = 10 * 2 / 5 = 4. Since i is an integer, then the value of the second quintile is the average of the fourth and fifth observations, which are 9% and 10%, respectively. Therefore, the second quintile is (9 + 10) / 2 = 9.5%.


For the third quintile (k = 3), i = 10 * 3 / 5 = 6. Since i is an integer, then the value of the third quintile is the average of the sixth and seventh observations, which are 11% and 12%, respectively. Therefore, the third quintile is (11 + 12) / 2 = 11.5%.


For the fourth quintile (k = 4), i = 10 * 4 / 5 = 8. Since i is an integer, then the value of the fourth quintile is the average of the eighth and ninth observations, which are 13% and 14%, respectively. Therefore, the fourth quintile is (13 + 14) / 2 = 13.5%.


For the fifth quintile (k = 5), i = 10 * 5 / 5 = 10. Since “i” is an integer, then the value of the fifth quintile is the average of the tenth and eleventh observations, which are both equal to 15%. Therefore, the fifth quintile is (15 + 15) / 2 = 15%.


The final step is to summarize the results in a table:

Image: Moneybestpal.com

This table shows the distribution of the returns of the 10 stocks into five equal groups, each representing 20% of the data set. The lower quintile (Q1) is 7.5%, which means that 20% of the stocks have returns lower than or equal to 7.5%.


The upper quintile (Q5) is 15%, which means that 20% of the stocks have returns higher than or equal to 15%. The median (Q3) is 11.5%, which means that 50% of the stocks have returns between 7.5% and 15%.



Examples

To illustrate how quintiles work, let us consider a simple example of a data set consisting of 25 observations:


2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27 and 28.


To find the quintiles of this data set, we need to sort the observations in ascending order and then divide them into five equal groups. The first quintile will contain the lowest five values (2 to 8), the second quintile will contain the next five values (9 to 14), and so on. The table below shows the quintiles of the data set:

Image: Moneybestpal.com

The range of each quintile shows the minimum and maximum values that belong to that group. The brackets indicate whether the endpoints are included or excluded from the range. For example, [2,8] means that both 2 and 8 are included in the first quintile, while [8,14] means that 8 is excluded but 14 is included in the second quintile.


Another way to find the quintiles of a data set is to use the following formula:


Qk = L + (k(N+1)/5 - F) * W


Where:

  • Qk is the kth quintile
  • L is the lower limit of the interval that contains Qk
  • k is the quintile number (1 to 5)
  • N is the number of observations in the data set
  • F is the cumulative frequency of the observations before L
  • W is the width of the interval that contains Qk


Using this formula, we can calculate the quintiles of the same data set as follows:


Q1 = L + (k(N+1)/5 - F) * W

= 2 + (1(26)/5 - 0) * (8 - 2)

= 2 + (5.2 - 0) * 6

= 2 + (31.2)

= 33.2



Q2 = L + (k(N+1)/5 - F) * W

= 8 + (2(26)/5 - 5) * (14 - 8)

= 8 + (10.4 - 5) * 6

= 8 + (32.4)

= 40.4



Q3 = L + (k(N+1)/5 - F) * W

= 14 + (3(26)/5 -10) * (20 -14)

= 14 + (15.6 -10) *6

=14 + (33.6)

= 47.6



Q4 = L + (k(N+1)/5 - F) * W

=20 + (4(26)/5 -15) * (26 -20)

=20 + (20.8 -15) *6

=20 + (34.8)

= 54.8



Q5 = L + (k(N+1)/5 - F) * W

=26 + (5(26)/5 -20) * (28 -26)

=26 + (26 -20) *2

=26 + (12)

= 38


Note that the quintiles obtained by this formula may differ from those obtained by dividing the data into five equal groups. This is because the formula assumes that the data is uniformly distributed within each interval.



Limitations

Quintiles are useful for summarizing and comparing large data sets or populations. However, they also have some limitations that should be considered before using them for analysis or decision-making.


Some of the limitations of quintiles are:

Quintiles may not capture the variability or skewness of a data set or population. For example, if a data set has a few extreme values that are much higher or lower than the rest, dividing it into quintiles may not reflect the true distribution of the data. Similarly, if a population has a large income gap between the rich and the poor, using quintiles may not reveal the extent of inequality or poverty.


Quintiles may not be meaningful or relevant for small data sets or populations. For example, if a data set has only 10 observations, dividing it into quintiles may result in some groups having only one or two values. This may not provide enough information or insight about the data. Similarly, if a population has only 100 people, using quintiles may not be representative or accurate for generalizing or comparing with other populations.


Quintiles may not be comparable across different data sets or populations. For example, if two data sets have different ranges, scales, or units of measurement, dividing them into quintiles may not produce comparable results. Similarly, if two populations have different characteristics, such as age, gender, education, or culture, using quintiles may not account for the differences or similarities between them.



Conclusion

Quintiles are a statistical tool for dividing a data set or population into five equal parts, each containing 20% of the observations. Quintiles are commonly used in finance to analyze and compare the performance of different assets, portfolios, or income distributions.


Quintiles can help to simplify and understand large data sets or populations by creating cut-off points or benchmarks. However, quintiles also have some limitations that should be considered before using them for analysis or decision-making.


Quintiles may not capture the variability or skewness of a data set or population, may not be meaningful or relevant for small data sets or populations, and may not be comparable across different data sets or populations.



References


FAQ

A quintile is a statistical term that refers to dividing a data set into five equal parts. Each quintile represents 20% of the data. For example, the first quintile represents the lowest 20% of the data, and the fifth quintile represents the highest 20%.

While both quintiles and quantiles are methods of dividing a dataset into equal parts, a quintile specifically refers to dividing the data set into five equal parts. On the other hand, a quantile can refer to any division of a data set.

Quintiles are often used in economics and finance to analyze distributions of data. For example, income distribution in a population is often divided into quintiles to understand the disparity between different income groups.

Quintiles are calculated by sorting the data set from smallest to largest and then dividing the data into five equal parts. The cut-off points between these parts are the quintiles.

Yes, IQVIA, formerly known as Quintiles, is a Fortune 500 company that provides biopharmaceutical development and commercial outsourcing services. The name “Quintiles” was derived from the statistical term.

Tags