Skip to content

Split-half reliability ​

Open this method

Purpose ​

Assess consistency among items intended to measure the same construct.

Data and assumptions ​

Reverse-score relevant items first. Each scale uses cases complete on its items. High reliability alone does not establish construct validity.

Configure this method ​

Split by odd/even or first/last selected-item positions. Results include the half-score correlation, Spearman–Brown and Guttman coefficients; unequal halves use the unequal-length correction.

Variables ​

ControlInput
Analysis variablesSelect variables
Dimensions and itemsAdd named dimensions and their items

Analysis settings ​

ParameterChoicesDefault
Also analyze the total scaleSet as neededDisabled
Split methodOdd and even items, First and second halvesodd_even

Analysis parameters remain visible in the main configuration area. Advanced formatting contains only the table title and numeric decimals. Methods that calculate intervals also show the significance level; 0.05 corresponds to 95% intervals.

Read the results ​

Consider coefficients together with item count and content. Negative coefficients call for checking coding and item direction. Item-deleted estimates inform judgment rather than automatic deletion.

Workflow and exports ​

  1. Upload the dataset and choose the method from the sidebar or search.
  2. Select the variables above, set the design-specific options, then run the analysis.
  3. Inspect the paper-style result. Reconfigure from the result area, or open raw output for diagnostics and sample details.
  4. Rename and keep result tabs as needed. Export Word, Excel, CSV or TXT; batch export can include the selected AI interpretation. Word retains figures. AI text should be checked against the estimates.

Algorithm and references ​