What it means
Raw numbers are hard to compare when they sit on different scales. A company with $50 million in sales and a profit margin of 8% cannot easily be compared to another on the basis of the two figures alone, because dollars and percentages mean different things.
Standardising puts each measure on a common footing. The statistical method is called a z-score.
You take a value, subtract the average of the group and divide by the standard deviation, which is the typical distance of values from the average. A score of 0 means the value is exactly average, a score of 1 means it is one standard deviation above average, and a score of -1 means one below.
Analysts use z-scores in many places. They compare a fund's return with its peers, flag unusual transactions in an audit, build credit scoring models and prepare data before running regression or machine learning tools.
Standardised inputs stop a variable with large numbers, such as revenue in dollars, from swamping one with small numbers, such as a ratio. The same word applies to business operations.
Standardising a chart of accounts, a month-end checklist or a pricing policy across subsidiaries makes reports easier to consolidate and reduces errors. Group finance teams often standardise accounting policies so that results from different countries can be added together on a like-for-like basis.
The nuance is that standardisation depends on the data used. A z-score is only meaningful if the average and spread are calculated from a suitable comparison group, and extreme values can distort both.
It also does not fix problems such as skewed data or missing information. It is also different from normalisation in the narrow data sense, which rescales values to a fixed range such as 0 to 1.
People sometimes use the two words loosely, so say which method you mean. When writing a report, state the formula so readers can reproduce it.
In practice
Real-world examples.
Example
An investment analyst standardises the revenue growth, margin and debt ratio of 50 companies so they can be combined into a single quality score. Without standardisation, the debt figure measured in billions would dominate. The resulting ranking is easy to explain to clients.
Example
An internal auditor standardises the sizes of payments to suppliers and flags those with a z-score above 3. A payment of $95,000 stands out against a typical range of $5,000 to $20,000. The auditor investigates and finds a duplicate invoice.
Example
A group controller introduces a standard chart of accounts and month-end calendar across six subsidiaries. Reports now arrive in the same format on the same day. The consolidation takes two days less each month, and the audit team spends less time reconciling differences between entities.
Formula
Calculation
Z-score = (Value - Mean) / Standard deviation
Suppose the average sales growth in an industry is 8% with a standard deviation of 4%, and a company reports sales growth of 14%. The z-score is (14% - 8%) / 4% = 6% / 4% = 1.5. The company's growth is one and a half standard deviations above the industry average. A company growing at 2% would score (2% - 8%) / 4% = -1.5, which is equally far below average.Case study
Seen in the real world.
Pinecrest Retail is a fictional chain with stores in five regions, and its finance team wanted to rank store performance fairly. This illustrative company had measures in different units, including sales per square metre, staff turnover and customer satisfaction scores. This is a fictional scenario, not a real company.
The analyst standardised each measure into a z-score and averaged them into a single index. She discovered that a small store previously ranked mid-table was consistently strong once size effects were removed, while a large flagship was only average. The regional managers agreed to use the index for bonuses and to review it every quarter. They also agreed to publish the formula and the weights so that store managers could see exactly how their score was built.
Watch out
Common mistakes.
- Standardising against the wrong comparison group. A z-score only means something when the average and spread come from a relevant set of peers.
- Letting outliers distort the result. A few extreme values can inflate the standard deviation and hide real differences.
- Confusing standardisation with normalisation. One uses the mean and standard deviation, and the other usually scales to a fixed range.
Questions
People also ask.
What does a z-score of 2 mean?
The value is two standard deviations above the average, which is unusually high in most datasets.
Why standardise data before analysis?
It puts different measures on the same scale, so no single variable dominates the results only because of its units.
Does standardisation also apply to accounting policies?
Yes, businesses standardise policies and processes across units so reports can be combined and compared consistently.
From the founder's library
Take it further with the book.
Build your financial confidence beyond this definition. Shihan's full-length guide, Accounting Fundamentals, takes the same plain-English approach and turns it into a complete, practical playbook for non-finance managers, business owners and students - with chapter-end quiz answers and presentation slides included.
25% off with code MMHQ25, applied at checkout. Priced in USD - checkout may show the equivalent in your local currency.
View the book and save 25%Related