Trimmed Mean: Definition, Calculation, Examples & Real-World Applications

Table of Contents#

What Is a Trimmed Mean? (Definition & Core Concept)
Key Benefits of Using a Trimmed Mean
How to Calculate a Trimmed Mean: Step-by-Step Guide
Trimmed Mean Example: Rent Prices in a City
Common Uses of Trimmed Mean Across Industries
Trimmed Mean vs. Other Central Tendency Measures
Conclusion
References

1. What Is a Trimmed Mean? (Definition & Core Concept)#

A trimmed mean (also called a truncated mean) is a robust measure of central tendency that adjusts the arithmetic mean by removing a fixed percentage of extreme values from both ends of a sorted dataset. Unlike the traditional mean, which includes all data points, the trimmed mean focuses on the “middle” portion of the data to avoid skewing from outliers.

For context:

A 5% trimmed mean removes the lowest 5% and highest 5% of values, using the middle 90% of the dataset to calculate the average.
A 10% trimmed mean cuts 10% from each tail, retaining the middle 80% of data.

The core idea is to strike a balance between the precision of the arithmetic mean and the robustness of the median, making it ideal for datasets with skewed distributions or extreme outliers.

2. Key Benefits of Using a Trimmed Mean#

Trimmed means are favored by analysts, economists, and statisticians for several critical reasons:

Mitigates Outlier Impact: Eliminates skewing caused by one-time anomalies (e.g., a sudden oil price spike or an unusually high executive salary) that distort the traditional mean.
Balances Precision & Robustness: Unlike the median, which only uses the middle value(s), the trimmed mean leverages most of the dataset, making it more precise than the median while still being resistant to outliers.
Ideal for Skewed Datasets: For non-symmetric data (e.g., income levels, rent prices, stock returns), it provides a more accurate central tendency measure than the arithmetic mean.
Stabilizes Volatile Data: In fields like economics or finance, trimmed means smooth short-term volatility to reveal long-term trends.

3. How to Calculate a Trimmed Mean: Step-by-Step Guide#

Calculating a trimmed mean is straightforward with these five steps:

Step 1: Choose Your Trimming Percentage#

Select a percentage of data to trim from each end. Common choices are 5% (for large datasets of 100+ observations) or 10% (for smaller, more volatile datasets). Adjust based on your data’s size and skew.

Step 2: Sort the Dataset#

Arrange all data points in ascending order (lowest to highest). This makes it easy to identify and remove extreme tails.

Step 3: Calculate Values to Trim Per Tail#

Multiply the total number of observations (n) by the trimming percentage to find how many values to remove from each end: Number of values to trim per tail = n × Trimming Percentage If the result is a decimal, round to the nearest integer for practical applications.

Step 4: Remove Extreme Values#

Delete the calculated number of values from both the bottom (lowest) and top (highest) of the sorted dataset.

Step 5: Compute the Mean of Remaining Data#

Sum the remaining values and divide by the count of remaining observations: Trimmed Mean = (Sum of Remaining Values) / (Total Observations - 2 × Values Trimmed Per Tail)

4. Trimmed Mean Example: Rent Prices in a City#

Let’s apply these steps to a real-world scenario: monthly rent prices for 12 apartments in a mid-sized city.

Full Dataset (Unsorted):#

$800,$ 2500, $900,$ 920, $950,$ 980, $1000,$ 1050, $1100,$ 1200, $1500,$ 850

Step 1: Choose Trimming Percentage#

We’ll use a 16.67% trim (16.67% of 12 = 2 values per tail, a clean integer).

Step 2: Sorted Dataset:#

$800,$ 850, $900,$ 920, $950,$ 980, $1000,$ 1050, $1100,$ 1200, $1500,$ 2500

Step 3-4: Trim Values#

Remove the 2 lowest ( $800,$ 850) and 2 highest ( $1500,$ 2500) values. Remaining data: $900,$ 920, $950,$ 980, $1000,$ 1050, $1100,$ 1200

Step 5: Compute Trimmed Mean#

Sum of remaining values = $8100 Remaining count = 8 Trimmed Mean = 8100 / 8 = **$ 1012.50**

Comparison to Traditional Mean#

The full dataset’s mean is $1145.83, skewed upward by the$ 2500 apartment. The trimmed mean is far more representative of typical rent prices in the city.

5. Common Uses of Trimmed Mean Across Industries#

Trimmed means are widely used in fields where outlier skewing is a frequent issue:

Economics & Government#

The U.S. Bureau of Economic Analysis (BEA) uses a 16% trimmed mean to calculate the Personal Consumption Expenditures (PCE) price index, a key inflation metric. This removes extreme price changes (e.g., sudden food or energy spikes) to reveal stable, long-term inflation trends.
Central banks use trimmed means to analyze wage growth and GDP components, avoiding distortions from one-time events like natural disasters.

Sports & Entertainment#

In figure skating, gymnastics, and diving, judges’ scores use a trimmed mean: the highest and lowest scores are discarded, and the average of remaining scores determines the final mark. This prevents biased judges from unfairly affecting results.

Finance & Investing#

Analysts use trimmed means to calculate average stock returns over time. A 5% trim removes extreme one-day gains/losses (caused by breaking news) to reveal a stock’s typical performance.

Education#

Teachers may use trimmed means for class test averages, removing the highest and lowest scores to avoid skewing from students who missed the test or scored perfectly, giving a more accurate measure of class performance.

6. Trimmed Mean vs. Other Central Tendency Measures#

To understand its value, compare the trimmed mean to the arithmetic mean and median:

Measure	Sensitivity to Outliers	Best For	Data Utilization
Arithmetic Mean	High	Symmetric, outlier-free datasets	100% of data
Trimmed Mean	Low	Skewed or volatile datasets	80-95% of data
Median	None	Highly skewed datasets with extreme outliers	~1 data point (middle value)

Trimmed Mean vs. Mean: The trimmed mean retains most data but filters outliers, making it more robust for skewed data.
Trimmed Mean vs. Median: The median is the most robust but discards most data, making it less precise. The trimmed mean strikes a balance between the two.

7. Conclusion#

The trimmed mean is a powerful tool for anyone working with skewed or volatile data. By balancing precision and robustness, it provides a more accurate central tendency measure than both the arithmetic mean and median in many real-world scenarios. Whether analyzing inflation data, calculating test averages, or evaluating stock performance, it helps avoid outlier skewing and supports informed decision-making.

8. References#

Investopedia. (2024). "Trimmed Mean." Retrieved from https://www.investopedia.com/terms/t/trimmedmean.asp
U.S. Bureau of Economic Analysis. (2024). "Trimmed Mean PCE Price Index." Retrieved from https://www.bea.gov/data/prices-inflation/pce-price-indexes
Statistics LibreTexts. (2024). "Trimmed Means." Retrieved from https://stats.libretexts.org/Bookshelves/Introductory_Statistics/Introductory_Statistics_(Shafer_and_Zhang)/03%3A_Descriptive_Statistics/3.02%3A_Measures_of_Central_Tendency/3.2.07%3A_Trimmed_Means