crosstabs.
Open navigation
OpenOpen workspace

SPSS command: SPSS MULTIPLE IMPUTATION /IMPUTE METHOD=NONE

Analyze missing data patterns in your browser

Analyze Patterns is the first step of SPSS Multiple Imputation: it summarizes how much is missing at three levels and lists the patterns before anything is imputed.

Try with example dataRun on your own file

Free · No account · Files stay on your device · Updated 18 October 2026

What it tells you

Crosstabs shows the overall summary, a variable summary, the pattern chart, the ten most frequent patterns and whether the pattern is monotone.

  • What share of variables, cases and individual values is incomplete; the three numbers are often very different.
  • Which variables carry the most missing values, with their valid N, mean and standard deviation.
  • Which combinations of missing variables are most common, so you can spot a skip pattern or a block of unanswered questions.
  • Whether the pattern is monotone (once a variable is missing, every later one is too), which lets imputation use the faster monotone method.

When to use it

Use it when

  • Before Multiple Imputation, to choose the variables for the imputation model and see whether the monotone method applies.
  • Panel or longitudinal studies with drop-out, where you expect later waves to be missing for people who left.
  • Quick data-quality checks on a new survey file, including string and categorical variables.

Use something else when

  • To test whether data are missing at random: use Missing Value Analysis for separate-variance t tests and Little's MCAR test.
  • To fill in values: this step imputes nothing. Use Impute Missing Data Values or Replace Missing Values.

How to run it in Crosstabs

  1. 01

    Open your data

    Open a .sav, CSV or Excel file in the workspace and switch to Statistics mode.

  2. 02

    Choose Analyze Patterns

    In the Missing values group, pick Analyze Patterns (MULTIPLE IMPUTATION).

  3. 03

    Tick the variables to analyze

    Tick at least two variables under Variables to analyze; numeric and categorical variables are both allowed.

  4. 04

    Set the display threshold

    Show variables with at least this % missing defaults to 10, as in SPSS; lower it to list every incomplete variable in the Variable Summary.

  5. 05

    Run

    If a weight is active, declare it as a frequency or sampling weight first; pattern counts and percentages then use it. Press Run.

Run Analyze Patterns in your browser

Worked example

Computed by the Crosstabs engine from the synthetic data below when this page was built — not typed in.

Try with example data

Data

48 synthetic panel members answer the same scale question in four waves. About 45% drop out before the last wave and never return, which produces a monotone pattern. Values come from a seeded generator.

Overall Summary of Missing Values
ItemIncompleteTotalPercent incomplete
Variables3475.0%
Cases254852.1%
Values4519223.4%
Variable Summary
ItemMissing NMissing PercentValid NMeanStd. Deviation
wave42552.1%2354.237.88
wave31429.2%3452.959.45
wave2612.5%4250.128.89
Ten Most Frequent Missing Value Patterns
Number of CasesPercentwave1wave2wave3wave4
2347.9%
1122.9%X
816.7%XX
612.5%XXX

X marks a missing value.

How to read it

52.1% of cases are incomplete, but only 23.4% of all values are missing, so dropping incomplete cases would discard far more information than the gaps themselves. Only 4 patterns occur and each one is a run of missing later waves, so the engine reports the pattern as monotone (variable order wave1, wave2, wave3, wave4); Multiple Imputation can then use the faster monotone method.

Output tables explained

Overall Summary of Missing Values
Three bars for Variables, Cases and Values; the filled share is the part that is incomplete.
Variable Summary
Missing N and percent, valid N, mean and standard deviation for variables at or above the display threshold, sorted by percent missing.
Missing Value Patterns
A chart with one row per pattern and one column per variable, missing cells shaded, so blocks and monotone staircases are easy to see.
Ten Most Frequent Missing Value Patterns
The ten patterns with the most cases, with count and percent; X marks a missing value.

Assumptions and notes

  • Missing means system-missing, a blank cell, or a declared user-missing code; any other value counts as observed.
  • The monotone check orders variables by increasing missingness; a single case that breaks the staircase makes the pattern non-monotone.
  • No inference is made, so a sampling weight only changes the counts and percentages.

How the results are validated

The test suite checks that a constructed monotone pattern is reported as monotone and then imputed with the monotone method, and that a non-monotone pattern sends Multiple Imputation to FCS. The pattern counts of the companion MVA procedure are checked exactly against an independent numpy/pandas reference. Validation evidence

Questions

What does monotone mean?

Variables can be ordered so that whenever one is missing, all the variables after it are missing too, as with panel drop-out. Monotone data can be imputed one variable at a time without iterating.

Why is the percent of incomplete cases so much higher than the percent of missing values?

A case is incomplete if any one of its values is missing. Spread a few gaps across many variables and most cases become incomplete, which is why listwise deletion can discard so much data.

Why are some variables missing from the Variable Summary?

Only variables at or above the display threshold (10% by default) are listed. Set the threshold to 0 to see every variable with at least one missing value.

Can I include categorical or string variables?

Yes. Any variable with values can be analysed for patterns; means and standard deviations are shown only for numeric ones.

Related procedures

Run Analyze Patterns on your own data

Open a .sav, CSV or Excel file. Everything runs in your browser; the file never leaves your device.

Open the workspace

SPSS is a trademark of IBM Corp. Crosstabs is not affiliated with or endorsed by IBM.