Missing value

As explained in Everyday Data Visualization

A missing data point is an expected observation or value that is absent from a dataset or visualization.

A missing value is an expected observation that is absent. In a visualization, the important part is not to quietly smooth it away: an unseen gap can make people infer a trend or continuity that the data does not support. section 9.1.1

Missingness can appear at two scales. A series may have an occasional hole, such as a day with no recorded value. Or it may be sparse because collection has only just begun, leaving more gaps than observations. Both deserve an honest visual treatment, even if the result is less tidy. section 9.1.1

Make gaps legible rather than accidental-looking:

• In a line chart, mark observed points with dots so viewers can distinguish actual values from the connecting stroke. section 9.1.1
• Break a line where data is missing; a continuous line otherwise implies a connection across the gap. section 9.1.1
• In a time-based bar chart, retain empty positions for missing days, weeks, or months instead of closing ranks around them. section 9.1.1
• If point markers make a chart too busy, reconsider the chart, reduce the displayed data, or make the markers smaller rather than concealing the gaps. section 9.1.1
• When data is still arriving, allow room for the display to grow rather than optimizing only for its thin early state; this anticipatory planning is future-proofing. section 9.1.1

A daily series with a hole

Suppose a daily line has values on Monday, Tuesday, Thursday, and Friday, but none on Wednesday. Dots identify the four observations, and a break between Tuesday and Thursday makes Wednesday’s absence visible. A daily bar chart should likewise leave Wednesday’s slot empty. The gap is information, not a formatting defect. section 9.1.1

Figure 9.1 When trending data in a line chart, I like to make it more obvious where the data points are by adding a dot at each point. Not only is it easier to understand, but it’s also more apparent when there’s data missing. Breaking the line on missing data points further drives the point home.

Point markers and a broken segment make both the observed values and the missing interval easy to see at a glance. section 9.1.1

A null is related but not identical language: in JSON, null represents nothing, an unassigned value, or an empty value. Whether it should be treated as a missing observation depends on what that field and row are meant to represent. section 3.5.2 section 3.6

How Everyday Data Visualization covers it

How deep it goes

Explains visual treatments for isolated and very sparse gaps, while deferring detailed data-cleaning or imputation methods.

Examples

Uses daily line and bar trends, including point dots, broken lines, and empty positions for missing periods.

What it assumes

Assumes familiarity with line and bar charts while defining sparse data and future-proofing conversationally.

What you can do after

Apply it to make absent observations visible and reduce misleading conclusions from trend charts.

How it connects

Connects missing values with line charts, bar charts, sparse data, future-proofing, JSON, and null.

liveBookmanning.com

Read Everyday Data Visualization on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  The Well-Grounded Data AnalystA missing value is an absent or unavailable value for a field that is expected to contain data.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIMissing data is the absence of recorded or available values or cases in a dataset, often represented explicitly by a special marker.
• 

  liveBookmanning.com
  Starting Data Analytics with Generative AI and PythonA missing value is an absent or unavailable data value in a record or variable.
• 

  liveBookmanning.com
  Statistics Slam DunkA missing value or missing data item is an observation whose value is unavailable, unrecorded, or not applicable in a dataset.
• 

  liveBookmanning.com
  API Design PatternsA missing value is a value that is absent because its field is omitted rather than explicitly assigned.
• 

  liveBookmanning.com
  Pandas Workout: 200 exercises to make you a stronger data analystA missing or null value is an absent or unavailable observation or field in a dataset.
• 

  liveBookmanning.com
  Outlier Detection in PythonThe absence of an expected value or observation in a dataset.
• 

  liveBookmanning.com
  The Well-Grounded Rubyist, Fourth Editionnil is Ruby’s singleton object representing the absence of a meaningful value.
• 

  liveBookmanning.com
  100 Go Mistakes and How to Avoid ThemA null value is a database value representing the absence of a value rather than a value of the column's declared type.
• 

  liveBookmanning.com
  Fast Python: High performance techniques for large datasets
• 

  liveBookmanning.com
  PostgreSQL Mistakes and How to Avoid ThemA SQL NULL is a marker representing an absent, unknown, or inapplicable value that participates in three-valued logic rather than ordinary equality.
• 

  liveBookmanning.com
  The Art of CodeIn Java, null is the literal value denoting that a reference does not refer to an object.
• 

  liveBookmanning.com
  Financial AI in PracticeData values that are absent from a dataset for some records or fields.
• 

  liveBookmanning.com
  100 Java Mistakes and How to Avoid ThemThe null value is Java's special reference value denoting the absence of an object reference.
• 

  liveBookmanning.com
  Clojure: The Essential Referencenil is Clojure's null value, representing the absence of a value or a null reference.
• 

  liveBookmanning.com
  .NET in Action, Second EditionA null value indicates that a reference or nullable value does not refer to an object or contain a non-null value.
• 

  liveBookmanning.com
  F# in Action: A Revised Edition of Get Programming with F#Missing data is information that is absent, unavailable, or not provided for an expected field or value.
• 

  liveBookmanning.com
  Learn Go with Pocket-Sized Projectsnil is Go's predeclared zero-like value representing the absence of a valid reference, interface value, or other applicable value.
• 

  liveBookmanning.com
  Data Storytelling with Altair and AIA missing value is an absent or unrecorded value for an observation and variable in a dataset.
• 

  liveBookmanning.com
  Machine Learning System DesignMissing data consists of absent values, records, or fields that are expected in a dataset or input.
• 

  liveBookmanning.com
  Graph Algorithms for Data ScienceMissing data is information that should be present for an entity or observation but is absent from the dataset.
• 

  liveBookmanning.com
  Modern CA null pointer is a pointer value that represents no valid object or function address.
• 

  liveBookmanning.com
  Statistics Every Programmer NeedsA null value is a missing or undefined data value represented as having no usable value.
• 

  liveBookmanning.com
  Modern C, Third Editionnullptr is the C23 null pointer constant used to represent a null pointer value.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionA missing value is an absent or unrecorded value for an attribute in a data record.
• 

  liveBookmanning.com
  Pro ASP.NET Core 7, Tenth EditionA null value represents the absence of an object reference or other value in a context where null is permitted.
• 

  liveBookmanning.com
  Delivering Machine Learning Projects: From design to deploymentA null value is a database value representing the absence of a recorded value rather than a measured numeric value.
• 

  liveBookmanning.com
  Grokking Machine LearningA missing value is an absent, unreadable, or otherwise unavailable entry in a dataset.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA missing value is an absent or unavailable data entry for an expected attribute of an instance.
• 

  liveBookmanning.com
  Julia as a Second LanguageMissing data is information absent from a collected dataset because it was not recorded, was lost, or is otherwise unavailable.
• 

  liveBookmanning.com
  Grokking StatisticsMissing data consists of observations or variable values that are absent from a dataset when they are expected or needed.
• 

  liveBookmanning.com
  Kotlin in Action, 2EA null value represents the absence of an object or reference value in a program.
• 

  liveBookmanning.com
  The Quick Python Book, Fourth EditionA missing value is a data item for which the intended observation is unavailable, inapplicable, or not reported.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionAn absent data field in a sample that must be handled explicitly during preprocessing.

Compare how 35 books explain missing value →

Related concepts

• left outer joinproduced by · A left outer join returns every row from the left relation and matching rows from the right relation, representing unmatched right-side values as nulls.
• primitive data typekind of · A primitive data type is a fundamental, language-provided type for representing a basic value, rather than a composite of multiple values.
• imputationuses · Imputation is the replacement of missing or incomplete data with estimated, inferred, representative, or otherwise selected values.
• atomkind of · An atom is an Elixir named constant whose text is stored in the runtime atom table and whose value is a reference to that text.
• findproduced by · A find operation searches a collection for the first element or entry matching a value or predicate and returns it, or indicates that no match exists.

This explainer was generated by Manning's knowledge graph from the text of Everyday Data Visualization. The section links point to the parts of the book it draws on.