Leveling the playing field: evaluating measurement equivalence in MMIs between genders
Jaclyn Michele Szkwara1, Amy Jean Bannatyne1, Mustafa Asil1
1Medical Program, Faculty of Health Sciences and Medicine, Bond University, Gold Coast, QLD, Australia.
Frontiers in Medicine
|September 15, 2025
Summary
Multiple Mini-Interviews (MMI) show factorial validity and measurement fairness across genders. However, female applicants consistently outperform males, necessitating further research into selection equity in medical school admissions.
Area of Science:
- Medical Education
- Psychometrics
- Health Professions Education
Background:
- Medical school selection is crucial for identifying suitable candidates.
- Multiple Mini-Interviews (MMI) assess non-cognitive skills like empathy and judgment.
- Ensuring fairness and validity of MMIs across diverse applicant groups is essential for equitable admissions.
Purpose of the Study:
- To investigate the factorial validity of the Multiple Mini-Interview (MMI) structure.
- To determine if non-cognitive attributes assessed by MMIs are interpreted consistently across gender groups.
- To examine potential gender-related disparities in MMI performance.
Main Methods:
- Confirmatory Factor Analysis (CFA) was used to assess MMI structure dimensionality.
- Multi-Group CFA tested for measurement invariance across gender groups.
- Latent mean comparisons examined gender-related differences in MMI performance.
Main Results:
- A higher-order model demonstrated a well-fitting structure for MMIs.
- Scalar invariance confirmed equivalent interpretation of non-cognitive attributes by males and females.
- Female applicants consistently outperformed male applicants in MMI performance over three selection cycles.
Conclusions:
- The study provides empirical support for the factorial validity and measurement fairness of MMIs across gender.
- Consistent gender-based performance differences in MMIs warrant further investigation into sources of disparity.
- Findings are relevant for medical educators and policymakers aiming for evidence-based and equitable selection processes.
Related Concept Videos
One-Way ANOVA: Equal Sample Sizes
4.0K
One-Way ANOVA can be performed on three or more samples with equal or unequal sample sizes. When one-way ANOVA is performed on two datasets with samples of equal sizes, it can be easily observed that the computed F statistic is highly sensitive to the sample mean.
Different sample means can result in different values for the variance estimate: variance between samples. This is because the variance between samples is calculated as the product of the sample size and the variance between the...
Different sample means can result in different values for the variance estimate: variance between samples. This is because the variance between samples is calculated as the product of the sample size and the variance between the...
4.0K
Interval Level of Measurement
18.0K
For effective statistical analysis, data are classified into four levels of measurement—nominal, ordinal, interval, and ratio.
Data measured using the interval scale are similar to ordinal level data because they have a definite arrangement. However, in the interval level of measurement, the differences between data values are meaningful even though the data does not have a starting point.
Temperature is measured using the interval scale. It is measurable data, and the difference between...
Data measured using the interval scale are similar to ordinal level data because they have a definite arrangement. However, in the interval level of measurement, the differences between data values are meaningful even though the data does not have a starting point.
Temperature is measured using the interval scale. It is measurable data, and the difference between...
18.0K
Ratio Level of Measurement
20.6K
The way a set of data is measured is called its level of measurement. Correct statistical procedures depend on a researcher being familiar with levels of measurement. For analysis, data are classified into four levels of measurement—nominal, ordinal, interval, and ratio.
A set of data measured using the ratio scale takes care of the ratio problem and provides complete information. Ratio scale data are like interval scale data, except they have a zero point and ratios can be calculated....
A set of data measured using the ratio scale takes care of the ratio problem and provides complete information. Ratio scale data are like interval scale data, except they have a zero point and ratios can be calculated....
20.6K
One-Way ANOVA: Unequal Sample Sizes
6.6K
One-way ANOVA can be performed on three or more samples of unequal sizes. However, calculations get complicated when sample sizes are not always the same. So, while performing ANOVA with unequal samples size, the following equation is used:
6.6K
Two-Way ANOVA
3.3K
The two-way ANOVA is an extension of the one-way ANOVA. It is a statistical test performed on three or more samples categorized by two factors - a row factor and a column factor. Ronald Fischer mentioned it in 1925 in his book 'Statistical Methods for Researchers.'
The two-way ANOVA analysis initially begins by stating the null hypothesis that there is an interaction effect between the two factors of a dataset. This effect can be visualized using line segments formed by joining the...
The two-way ANOVA analysis initially begins by stating the null hypothesis that there is an interaction effect between the two factors of a dataset. This effect can be visualized using line segments formed by joining the...
3.3K
Multiple Comparison Tests
4.4K
Multiple comparison test, abbreviated as MCT, is a post hoc analysis generally performed after comparing multiple samples with one or more tests. An MCT will help identify a significantly different sample among multiple samples or a factor among multiple factors.
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...
4.4K


