Analysis of data from the International Outcome Inventory for Hearing Aids (IOI-HA) using Bayesian Item Response Theory

Abstract

Objective: IOI-HA response data are conventionally analysed assuming that the ordinal responses have interval-scale properties. This study critically considers this assumption and compares the conventional approach with a method using Item Response Theory (IRT). Design: A Bayesian IRT analysis model was implemented and applied to several IOI-HA data sets. Study sample: Anonymised IOI-HA responses from 13273 adult users of one or two hearing aids in 11 data sets using the Australian English, Dutch, German and Swedish versions of the IOI-HA. Results: The raw ordinal responses to IOI-HA items do not represent values on interval scales. Using the conventional rating sum as an overall score introduces a scale error corresponding to about 10 À 15% of the true standard deviation in the population. Some interesting and statistically credible differences were demonstrated among the included data sets. Conclusions: It is questionable to apply conventional statistical measures like mean, variance, t-tests, etc., on the raw IOI-HA ratings. It is recommended to apply only nonparametric statistical test methods for comparisons of IOI-HA results between groups. The scale error can sometimes cause incorrect conclusions when individual results are compared. The IRT approach is recommended for analysis of individual results.

Prediction of successful hearing aid treatment in first-time and experienced hearing aid users: Using the International Outcome Inventory for Hearing Aids

“…As it has recently been pointed out (Leijon et al 2020) that IOI-HA does not behave well when handled as a metric scale, we, therefore, applied the item specific category weights suggested in Leijon et al (2020) as a supplementary analysis and repeated the main analysis on the resulting IOI-HA scores. Moreover, as an additional sensitivity analysis, we applied ordinal logistic regression to the raw IOI-HA scores to investigate if this resulted in consistent estimates.…”

“…The results from the regression analyses are presented in Table 4. For comparison, results from the corresponding regression models on the IOI-HA with the weights suggested by Leijon et al (2020) are reported in Supplementary Table 1. This sensitivity analysis and the analysis applying ordinal logistic regression instead (results not shown), resulted in estimates consistent with the main analysis.…”

Community-based adult hearing care provided by community healthcare workers using mHealth technologies

“…Researchers have generally used the mean scores to interpret the results of IOI-HA. However, as the IOI-HA results in ordinal data, the use of median scores of each item and total scores for the overall scores may be more appropriate [ 42 ]. To ensure backward compatibility of the data with previous literature, we also report the mean IOI-HA scores.…”

Psychometric properties of the Kannada version of the International Outcome Inventory for Hearing Aids (IOI-HA)

“…IOI-HA was developed over 20 years ago without the use of ITI, and all previous studies (Br€ annstr€ om and Wennerstr€ om 2010; Chu et al 2012;Cox and Alexander 2002;Jespersen, Bille, and Legarth 2014;Kramer et al 2002;Pavia et al 2017) that examined the psychometric properties of IOI-HA except the recent international study (Leijon et al 2020) have applied parametric methods such as PCA. Considering this, to allow maximum inter-study compatibility, the statistical analysis in this study falls generally in line with the procedure applied by Cox and Alexander (2002) in the original IOI-HA study.…”