Contents - Index

Four-way data - parallel

This type of data has the following features:

• It should have 4 + N columns, with the first 4 columns representing Year, Tester (e.g, location), Block (i.e., replication), Entry (e.g., genotype), and followed by N columns of the traits.

• The first row is the header, containing the names of the columns, i.e., Year, "location name", "Block name", "Entry name", and names for each of the N traits. You could put "End" after the trait name, but this is not required if it is an Excel or Access file; it is required only if the data file is in csv data format.

• Each subsequent row contains an observation or entry, wiht values for year, location name, block (replication) name, entry name, and measured value for each of the traits, respectively.

• The data do not have to be balanced in terms of entry by location combinations. The number of blocks can differ for different testers. 

• Missing cells can be indicated by anything except that it cannot be left empty for text files.

Below is an example data file: