Suitability of Attitude Scaling Methods for Large Statement Sets

The choice of an attitude scaling method depends on various factors, including the number of attitude statements to be scaled. Some methods become operationally complex and time-consuming as the number of statements increases significantly.

Method Analysis

• Paired Comparison: This method requires judges to compare every statement with every other statement. The number of comparisons grows quadratically with the number of statements ($n$), making it highly impractical for a large set.
• Equal Appearing Intervals (Thurstone): Judges sort statements into a fixed number of scale categories. While effective, managing a large number of statements and ensuring consistent sorting across judges becomes challenging.
• Summated Ratings (Likert): Respondents rate their agreement with each statement. This method is relatively straightforward to administer and score, making it suitable for scaling a large number of statements.
• Successive Intervals: This Thurstone-type method requires judges to rate statements on a continuum and involves complex statistical calculations to derive scale values. The extensive judging process and intricate computational steps make it particularly unsuitable for scaling a very large number of attitude statements compared to simpler methods like Summated Ratings.

Conclusion on Suitability

While Paired Comparison is extremely difficult with many statements due to the sheer number of comparisons, Successive Intervals presents significant operational and computational challenges during the scaling process itself when dealing with a large quantity of statements. This complexity makes it less practical than methods like Summated Ratings for such scenarios.