Data Encyclopedia
HomeCharts
  • Welcome & Product Overview
  • Getting Started
  • Tutorials and Examples
    • Tutorials
      • Python API Client Walkthrough
      • Getting Started With Market Data
      • Getting Started With Futures Data
      • Aggregating Options Data
      • Examining Orderbook Depth
      • Aggregating Orderbook Depth to Create Liquidity Metrics
      • Comparing Stablecoin Prices Using Different Pricing Methods
      • Comparing Volumes of Exchanges and Assets
      • Creating Custom Network Data Metrics Using ATLAS
      • Applying Different Types of Marketcap Metrics
      • Comparing the Dominance of Mining Pools Using ATLAS
      • Using Staking Metrics to Get Yield and Staked Supply
      • Granular Insights On Chain Using Hourly Network Data Metrics
      • Exploring Options, Open Interest, and Volatility Data
      • Calculating Total Value Locked in Liquidity Pools using DEX Data
      • Calculating DEX Liquidity Pool Fees and Volumes
      • Analyzing DeFi Protocol Balance Sheets
    • How To Guides
      • How To Export Data
      • How To Migrate From Catalog to Catalog V2 and Reference Data
      • How To Use the Coin Metrics API Efficiently
    • Dashboard Examples
  • Packages
    • CM Labs
    • Coin Metrics Community Data
  • Access Our Data
    • API Reference
    • API Conventions
      • Catalog V1 to Catalog V2 Migration
    • Python API Client
    • R API Client
    • Coverage
    • Status Page
  • Data Visualization
    • Charting Tool
      • Formula Builder
      • Correlation Tool
      • Embedded Charts
      • Troubleshooting
    • Dashboard
      • Troubleshooting
    • CMTV Charts (Labs)
      • Troubleshooting
    • Atlas Explorer
  • Network Data
    • Network Data Pro Overview
      • Availability
        • Asset Completion Time
      • Addresses
        • Active Addresses
        • Address Balances
        • New Addresses
      • Economics
        • Mining
        • Valuation
      • Exchange
        • Deposits
        • Exchange Supply
        • Net Flows
        • Transaction Count
        • Withdrawals
      • Fees and Revenue
        • Fees
        • Revenue
      • Market
        • Market Capitalization
        • Price
        • Profitability
        • Returns
        • Volatility
      • Key Risk Indicator (KRI) Feed
        • Blocks
        • Block Attributes
        • Block Size
        • Block Times
        • Empty Blocks
        • Fees
        • Outputs
        • Rewards
        • Feerates
        • Hashrate
        • Transaction Feerates
        • Transaction Fees
        • Transaction Sizes
        • Transactions
      • Mining
        • Balances
        • Difficulty
        • Exchange Flows
        • Flows
        • Hardware Hash Rate
        • Hash Rate
      • Network Usage
        • Blocks
        • Contracts
        • Profitability
        • UTXOs
        • Blobs
      • Staking
        • Consensus Health
        • Flows
        • Penalty Metrics
        • Slashing Metrics
        • Validator Supply
        • Stakers
        • Yield
      • Supply
        • Active Supply
        • Addresses with Balance
        • Burnt Supply
        • Current Supply
        • Free Float Supply
        • Future Expected Supply
        • Miner Revenue
        • Profitability
        • Revived Supply
        • Shielded Supply
        • Supply Issuance
        • Staking Supply
      • Transactions
        • Blobs
        • Contracts
        • Token Transactions
        • Transactions
        • Transfer Value
        • Transfers
        • Velocity
      • Wallets
        • Active Wallets
        • Wallet Balances
    • Atlas Overview
      • Accounts
      • Account Balance
      • Blocks
        • Full Block
      • Transactions
        • Full Transaction
          • Full Transaction Info for Block
      • Balance Updates
    • Methodologies
      • Normalizing Block Times
    • DeFi Overview
      • Decentralized Exchange Data
      • DeFi Balance Sheets
      • DeFi FAQs
    • Tagging Meta Data
    • Transaction Tracker
    • CM Labs
      • Mining Pool Monitor Overview
        • Mining Pool Monitor API Fields
      • Reorg & Fork Tracker Overview
        • Reorg & Fork Tracker Tracker API Fields
    • Deprecated
      • Mempool Monitor
      • WatchTower Alerts Overview - DEPRECATED
        • WatchTower Alerts - DEPRECATED
          • Ethereum Proof-of-Stake Alerts - DEPRECATED
            • Missed Slot Alert - DEPRECATED
            • Fast Increase in Transaction Count Alert - DEPRECATED
            • Fast Decrease in Transaction Count Alert - DEPRECATED
            • Fast Decrease in Base Fees - DEPRECATED
            • Fast Increase in Base Fees - DEPRECATED
            • Fast Decrease in Priority Fees (Tips) Alert - DEPRECATED
            • Fast Increase in Priority Fees (Tips) Alert - DEPRECATED
            • Decrease in Active Addresses Alert - DEPRECATED
            • Increase in Active Addresses Alert - DEPRECATED
            • Decrease in Total Block Fees Alert - DEPRECATED
            • Increase in Total Block Fees Alert - DEPRECATED
          • DeFi Alerts - DEPRECATED
            • Smart Contract Admin Change Alert - DEPRECATED
            • Admin Change with Issuance Event Alert - DEPRECATED
            • Admin Change with Large Issuance Event Alert - DEPRECATED
          • Mining Alerts - DEPRECATED
            • Unknown Miner Predominance Alert - DEPRECATED
            • Mining Pool Conflict Alert - DEPRECATED
            • Persistent Mining Pool Conflict Alert - DEPRECATED
            • Hashrate Decrease Alert - DEPRECATED
            • 1-Block Difficulty Decrease - DEPRECATED
          • Blockchain Alerts - DEPRECATED
            • 1 Block Reorg Alert - DEPRECATED
            • 2 Block Reorg Alert - DEPRECATED
            • 3 Block Reorg Alert - DEPRECATED
            • Satoshi Coins Spent - DEPRECATED
            • Vintage Coins Spent - DEPRECATED
            • Slow Block Alert - DEPRECATED
            • 1 Consecutive Empty Block Alert - DEPRECATED
            • 2 Consecutive Empty Blocks Alert - DEPRECATED
            • 3 Consecutive Empty Blocks Alert - DEPRECATED
            • 6 Consecutive Empty Blocks Alert - DEPRECATED
          • Mempool Alerts - DEPRECATED
            • Mempool Disruption Alert - DEPRECATED
            • Mempool Size 90% Alert - DEPRECATED
            • Mempool Size 95% Alert - DEPRECATED
            • Mempool Size 99% Alert - DEPRECATED
            • Mempool Size 100% Alert - DEPRECATED
            • Mempool Congestion Alert - DEPRECATED
        • WatchTower API Fields - DEPRECATED
    • Network Data Glossary
    • Network Data FAQs
  • Market Data
    • Market Data Overview
      • Basis
      • Candles
      • Contract Prices
      • Funding Rates
        • Funding Rates
        • Predicted Funding Rates
        • Aggregated Futures Funding Rate
        • Cumulative Futures Funding Rate
      • Greeks
      • Institution Metrics
        • Grayscale
          • Shares Outstanding
          • Market Price
          • Net Asset Value
          • Coin Per Share
          • Total Assets
      • Liquidations
        • Market Level Liquidations
        • Liquidation Metrics
      • Liquidity
        • Bid-Ask Spread Percent
        • Order Book Depth
        • Slippage
      • Market Metadata
      • Open Interest
        • Market Level Open Interest
        • Reported Open Interest
      • Orderbooks
      • Quotes
      • Trades
      • Volatility
        • Market Implied Volatility
        • Implied Volatility
        • Realized Volatility
      • Volume
        • Trusted Volume
        • Reported Volume
    • CM Prices
      • Reference Rate
      • Principal Market Price (USD)
      • Principal Market (USD)
    • Methodologies
      • Coin Metrics Prices Policies
      • Coin Metrics Prices Methodology
      • Trusted Exchange Framework
    • Market Data FAQs
      • CM Prices FAQs
      • Trusted Exchange Framework FAQs
  • Index Data
    • Index Overview
      • Index Timeseries
        • Index Levels
        • Index Candles
        • Index Constituents
    • Policies & Charters
      • CMBI Index Policies
      • Governance Committees
    • Methodologies
      • Fork Legitimacy Framework
      • Adjusted Free Float Supply Methodology
      • Candidate Market Guidelines
    • Fact Sheets
      • CMBI Single Asset Series Fact Sheet
      • CMBI Multi Asset Series Fact Sheet
      • CMBI Total Market Series Fact Sheet
      • CMBI Mining Series Fact Sheet
    • Indexes Glossary
    • Index FAQs
  • Reference Data
    • datonomy Overview
      • Taxonomy for Assets
      • Taxonomy Metadata for Assets
      • datonomy FAQs
    • Profiles Overview
      • Asset Profiles
      • Network Profiles
    • Security Master Overview
      • Assets
      • Markets
    • Methodologies
      • Guiding Principles and Methodology for datonomy
  • BITTENSOR
    • Precog Methodology
      • Point Forecast Ranking
      • Interval Forecast Ranking
      • Interval Score Examples
      • Miner Weight from Rank
Powered by GitBook
On this page
  • Correlation Coefficient
  • Tool Options
  • Pearson and Spearman Correlation
  • Pearson
  • Spearman
  • Arithmetic vs Logarithmic Returns
  • Timeframe
  • Handling of Data Gaps
  • Interpretation
  • Constraints

Was this helpful?

  1. Data Visualization
  2. Charting Tool

Correlation Tool

https://charts.coinmetrics.io/correlations/

PreviousFormula BuilderNextEmbedded Charts

Last updated 10 months ago

Was this helpful?

Correlation Coefficient

A correlation coefficient is a number between -1 and 1 measuring the strength of a relationship between two variables. A positive correlation means that returns move together. If you plotted returns of two cryptoassets on a scatterplot, dots sloping upwards and right in a diagonal line would imply a positive correlation. Note that no causality is inferred. The actual derivation involves taking the covariance of two variables. Covariance tells you whether two variables move together or not, but it is unbounded and unstandardized. Finding a correlation involves standardizing those arbitrarily large figures by dividing by the sample standard deviations of both variables. This reduces covariance to a range between -1 and 1, and it is now informative as to the magnitude of moves between two assets. Put simply correlation tells you:

  1. whether two variables are related, and

  2. the magnitude of their inter-relatedness

Tool Options

The tool offers the user several options for determining the correlation coefficient:

  • Pearson vs. Spearman

  • Log vs. Arithmetic Returns

  • Timeframe: 30/60/90/180/360 days

  • Handing of Data Gaps: Linearly Interpolate or Exclude

Pearson and Spearman Correlation

Our tool presents two options for correlation: Pearson and Spearman Correlation.

The orthodox and conventional way of doing things in finance is to take the Pearson correlation of logarithmic daily asset returns, preferably over a long period. If you aren’t interested in getting into any additional complexity, you can stop there and use those settings on the charts.

(A common mistake in correlating assets is to use raw prices rather than returns. This is a mistake, as prices are often trended and non-stationary, meaning that you often get spurious positive correlations. Our tool uses the asset returns.)

Pearson

Pearson correlation basically assumes that the relationship between the two variables is linear, and it measures it on this basis. If you have nonlinear yet meaningful relationships, Pearson will report a weak correlation, when in fact there may be something interesting going on behind the scenes.

Spearman

To give our users an alternative, we introduced Spearman correlation.

Spearman correlation takes a ranking of all the data points in the sample, and then it runs a Pearson correlation on the rankings data. It then compares the two variables based on how much their rankings move together. This enables the ability to capture co-movements in datasets that are nonlinear. Spearman would find the correlation between a perfect exponential relationship as 1, whereas Pearson would declare it positive but not perfectly correlated.

Arithmetic vs Logarithmic Returns

While Arithmetic Returns are easily understood, as mentioned above, there are some good reasons for using a Logarithmic Return in certain occasions. Our took allows you to choose Arithmetic or Logarithmic returns.

Timeframe

The tool allows you to select the number of daily observations to consider when comparing returns to determine the data sets' correlation.

If, for example, you picked 180 days, the 180 daily returns prior to the point/date on the chart were considered when determining the correlation coefficient returned for the two data series at that point/date on the chart. In other words, the number you see for today refers to a sample of the previous 180 days.

Keep in mind that if you "exclude gaps" in the data set (see below), then the number of days selected will reflect only the number of days for which there are observations.

Handling of Data Gaps

On occasion, you may want to compare a continuous data series with one with gaps (such as when you compare cryptoasset returns with a traditional index like S&P500 that has no values on the weekends or holidays). The tool gives you two options for handling this:

  • Linearly interpolate the data to derive a value for the data gap prior to calculating the returns

  • Exclude the observations on the dates where one data series has a gap, but the other doesn't prior to calculating the returns (note: this results in fewer observations for the non-gapped series)

The tool will default to "excluding" data where gaps are identified. You can adjust this setting from the settings menu on the right toolbar.

Interpretation

Let’s say you select a Pearson correlation of the logarithmic returns for the previous 180 days. This number means “in the 180 days leading up to the point on the chart you’re looking at, the two assets that you have selected had co-movement in their daily returns of a magnitude corresponding to x.” If x is 1, their daily returns were perfectly positively correlated in the 180-day period leading up to the date where you observe the coefficient of 1. If x is 0.3, their returns moved together more often than not, but they weren’t particularly closely linked.

Constraints

Attempting to predict the future by looking at historical returns is always somewhat fraught. There’s no guarantee that a historical correlation will persist into the future. Because of this, we recommend looking for useful correlations over longer periods.

Things that should grab your attention:

  1. Very positive correlations between two assets, especially over longer periods of time. Consistently high correlations deserve investigation.

  2. Persistent negative correlations of any sort are tremendously interesting, albeit rare. The strength of the signal increases with the quantity of historical evidence.

Be aware that different market phases exist. Longstanding correlations can break down during certain market conditions.

Try to discern when your correlation analysis holds little explanatory power. Avoid mistaking noise for signal. And use this tool with caution.

It’s also worth reading more about the statistical underpinnings of correlation measures. \

One solution to this problem is using , which helps in processing data, and has some other useful properties if the data is normally distributed.

For more on this, we suggest reading this in the differences between the two. To put it simply: if you think your variables are linearly related, and you want to measure the strength of those co-movements, use Pearson correlation. If you want to capture variables which move together, but not at a constant rate (as with an exponential relationship), consider Spearman correlation. Spearman makes no assumptions as to linearity but simply assesses the relationship in terms of whether one variable increases when the other increases, and vice versa.

log daily returns
excellent breakdown
Find this toggle below the chart
Find this toggle below the chart
Find the timeframe options below the chart