Generate Poisson random counts

Create simulated values from a chosen probability model, with a fixed seed when you need to repeat the sample.

Guides · Worksheets and data tools · 4 min read

Example: surface defects per panel

Simulate separate surface defects on 200 independent panels, each with area 1 m². One panel may have several defects.

Download the generator parameters (reference CSV)

This is the same example used in Help. The CSV lists the generator parameters for reference. Enter them manually on Inputs; importing the CSV does not configure the generator or provide measured observations.

1. Create the generator

In the sidebar, choose Data utilities, then Create Random Data. Name the analysis, select New blank worksheet and choose Create analysis. This worksheet receives the generated columns.

2. Set the generated variable

On Inputs, under Generated variables, enter surface_defects_per_panel in Column name and 200 in Number of observations. Choose Poisson in Distribution.

Enter 2.5 in Mean (λ). This is the model’s average number of separate defects per 1 m² panel.

3. Set the seed and destination

Open Reproducibility and enter 42 in Random seed.

Check Worksheet output: the destination should be your analysis worksheet, with one new column. Generate once to reproduce this example. Each successful run appends new columns.

Create Random Data: Inputs with the example’s assignments and settings
The Poisson definition and seed 42 on Inputs. The worksheet receives one new column. View full-size image (opens in a new tab)

4. Generate data

Choose Generate data, then open Results. Open Worksheet to see the new columns.

5. Interpret results

  1. Check the generated output

    There is one new column, surface_defects_per_panel, with 200 values. These are simulated observations for practice, not measured production data.

  2. Read the model

    The model averages 2.5 separate defects per equal-area panel. That does not mean 2.5% of panels are defective. The generated sample’s average count need not be exactly 2.5.

  3. Read a generated row

    The first generated panel has 4 defects; the fifth has 0. Read each row as a nonnegative whole-number defect count for one panel. Several defects can belong to the same panel.

  4. Use the sample deliberately

    Use the generated columns to practise an analysis or explore the supplied model. Seed 42 repeats this sample with the same ordered definitions and calculation version. A blank seed requests a fresh sample. Running Generate data again appends columns; it does not replace the earlier output.

More details: read each result section

Complete result tables use six significant digits, as in Help.

Generation summary

The summary lists surface_defects_per_panel, its 200 valid values, the distribution and seed 42.

Calculated example output. Running a practice copy writes new columns to its independent worksheet.

Generation summary · 1 row
DefinitionOutput columnDistributionValid valuesSeed
surface_defects_per_panelsurface_defects_per_panelpoisson20042

Captured generator parameters

The model averages 2.5 separate defects per equal-area panel. That does not mean 2.5% of panels are defective. The generated sample’s average count need not be exactly 2.5.

Captured generator parameters · 1 row
DefinitionParameterValue
surface_defects_per_panelmean2.5

Generated values

All 200 generated rows are retained in generation order. The first generated panel has 4 defects; the fifth has 0. Read each row as a nonnegative whole-number defect count for one panel. Several defects can belong to the same panel.

Captured values in original row order. Exports retain full precision.

Generated values · 200 rows
Rowsurface_defects_per_panel
14
23
34
42
50
67
71
82
93
101
112
123
133
142
150
165
171
185
192
202
212
222
235
240
251
261
271
283
292
303
314
321
333
343
354
361
370
382
391
403
411
423
434
442
451
463
471
484
492
504
513
522
537
543
553
562
573
584
590
601
612
622
633
642
654
661
672
681
696
702
712
723
734
743
750
762
771
782
791
800
810
821
833
843
851
862
870
882
891
902
916
924
932
942
952
962
974
985
994
1001
1011
1024
1035
1042
1055
1062
1071
1084
1093
1101
1112
1125
1134
1142
1152
1163
1174
1184
1193
1201
1211
1224
1230
1240
1254
1265
1271
1284
1292
1303
1311
1323
1333
1342
1354
1362
1372
1381
1392
1403
1412
1422
1435
1444
1455
1464
1470
1481
1492
1502
1513
1521
1535
1543
1552
1563
1573
1581
1593
1602
1611
1623
1634
1641
1652
1666
1673
1681
1693
1701
1713
1720
1734
1747
1756
1763
1770
1785
1791
1804
1811
1821
1835
1843
1852
1863
1873
1882
1892
1904
1911
1926
1931
1940
1951
1963
1975
1984
1992
2001

6. Create a report

Keep Generation summary, Captured generator parameters and Generated values. Record the seed, the model and its units. Label the output as simulated practice data.

Choose Add to report from the completed run. Open Choose individual items and advanced options to select tables and charts, then choose Add to draft. Hidden items stay in the saved analysis.

Name the report and add the purpose of the study and your interpretation. Choose Save, review Preview, then use Export → Download HTML. The example below contains the full selected content, including results beyond one screen.

Complete native output for this Help example, including applicable tables, charts and run notes. Report numbers use the app’s displayed precision. Exported charts are static. On narrow screens, scroll wide charts and tables sideways.
View example report: Generate defect counts for 200 panels

We use Microsoft Clarity to understand how visitors use this website, including session recordings and heatmaps. You can use the website without accepting analytics.

Your choice is saved in this browser for six months. Privacy notice

Current choice: Not chosen.