Application of The Rasch Model in The Development of Dimension of The in The Development of Dimension of The Measurement of Tax Fairness Perception Measurement of Tax Fairness Perception

Abstract

This study aims to investigate the measurement instrument of the perception dimension of tax fairness using the Rasch model method. The dimensions of the perception of tax fairness are divided into seven dimensions, namely general fairness, exchange fairness, horizontal fairness, vertical fairness, retributive fairness, policy fairness, and administrative fairness. The sampling technique employed purposive sampling by classifying several criteria for respondents. The distribution of data used Google docs to as many as 122 individuals. The results of this study indicate that the Cronbach alpha value (KR-20) is 0.71. The question item with code PF2 which is included in the personal fairness dimension with a logit value of +0.91 is the most difficult item for respondents to answer. There are three question items that are considered misfit because the logit value of the item is greater than the sum of the mean and standard deviation (1.27). The three items are VF 1 (1.72), RF1 (1.48), and EF2 (1.29). The contributions of this study are: (1) to enrich the literature on tax fairness perceptions by using the Rasch model as a data analysis tool, and (2) empirically, to validate the measurement instrument in the perception of tax fairness dimensions which will be useful for further research.

The Use of The Rasch Model on The Instruments of Accounting Students' Attitude and Interest in The Accounting Profession

“…The fit and misfit criteria can be used infit MNSQ values of each element in the table with a summation value between the mean value and the standard deviation. The larger logit value proves that the article is in a mismatched state [33].…”

“…Participants were asked to evaluate questionnaire questions on five likert ratings (1= strongly disagree, 2= disagree, 3= neutral, 4= agree, and 5= strongly agree) and the demographic information of the participants. The study's scoring outcomes are polytomy [33].…”

“…The first is to interpret the results of the analysis of the respondent (person) and the second to describe the item. The table of respondents describes whether or not a measurement item is fit [33]. Table 2.…”

“…Shows an alpha cronbach (KR-20) value of 0.95. This value is included in the very good category (α > 0.8) which means that there is a compatibility between the respondents and the instruments used in this study [33]. Then the realibility value for the item of 0.97 indicates that the value is special (α > 0.94) and the realibility value for the respondent (person) of 0.94 indicates that the value is special (α > 0.94).…”

“…The logit element values are sorted from the most difficult element to agree with, namely the highest score to the easiest to agree element, which is the lowest score [29]. In this table provides information about the logit of each entry [33].…”