This section investigates the reliability and validity of the ONI. First, reliability scores are obtained for all sub-factors and factors in ONI. Then, factor structure is sought for ONI. In the adaptation study of the ONI, the validity analysis was analyzed with the confirmatory factor analysis (CFA). The final scale was obtained with three sub-factors. CFA was used to verify this structure. The reason for this is that the dimensions in the original scale were analyzed by exploratory factor analysis (EFA) and the relevant structure was specified. In addition, outlier control was made for all items in the scale. First of all, among the factors related to the three sub-factors structure obtained, the regression path coefficients for the items were obtained statistically significant. The t values for the standard regression coefficients of each item were examined and obtained outside the critical value of ± 1.96 at 0.05 significance level. Regression coefficients were obtained in the range of 0.29 - 0.58 (Figure 1). Factor_1, factor_2 and factor_3 show the sub-factors which are behaviors, emotions and impairiments, respectively.
There are many model data fit indexes in the literature for model data fit. In this study, among these fit indices, the most frequently used fit indices are given. In this study, fit indices which are Relative Chi-square (x2 / df), the Root Mean Square Error of Approximation (RMSEA), Normed Fit Index (NFI), Comparative Fit Index (CFI), Standardized Root Mean Square Residual (SRMR), Goodness of Fit Index (GFI), Adjusted Goodness of Fit Index (AGFI) and Incremental Fit Index (IFI) are given. (Table 2).
Table 2. Model Fit Indexes
Index
|
Perfect Fit Measure
|
Good fit measure
|
Research finding
|
Conclusion
|
CMIN / df
|
0-3
|
3-5
|
5.65
|
Acceptable
|
RMSEA
|
0.00 ≤ RMSEA ≤ .05
|
0.05 < RMSEA ≤ .10
|
0.081
|
Good
|
CFI
|
0.95 ≤ CFI ≤ 1.00
|
0.90 ≤ CFI < 0.95
|
0.94
|
Good
|
NFI
|
0.95 ≤ NNFI ≤ 1.00
|
0.90 ≤ NNFI < 0.95
|
0.93
|
Good
|
SRMR
|
0.00 ≤ SRMR ≤0.05
|
0.05 < SRMR ≤ 0.08
|
0.066
|
Good
|
GFI
|
0.80 ≤ CFI
|
0.90 ≤ CFI
|
0.86
|
Good
|
AGFI
|
0.80 ≤ AGFI
|
0.90 ≤ AGFI
|
0.83
|
Good
|
IFI
|
0.85 ≤ IFI
|
0.95 ≤ IFI
|
0.94
|
Good
|
CMIN / df = Relative Chi-square, RMSEA = Root Mean Square Error of Approximation, NFI = Normed Fit Index, CFI = Comparative Fit Index, SRMR = Standardized Root Mean Square Residual, GFI = Goodness of Fit Index, AGFI = Adjusted Goodness of Fit Index, IFI = Incremental Fit Index
A ratio of Chi-square (X2) to degrees of freedom below 3 indicates perfect fit, and a value below 5 indicates a good fit [28]. In this study, the CMIN / df result was obtained as 5.65, indicating an acceptable fit. According to the statistics related to the other model data fit indices, the model generally fits well to the structure (RMSEA = 0.081, CFI = 0.94, NFI = 0.91, IFI = 0.94, SRMR = 0.066, GFI = 0.86, AGFI = 0.83, IFI = 0.94) [29]. Although the first CMIN / df result was out of the specified range, no modification was required as the other fit indices fit well. Therefore ON of three sub-factors compared to the CFE adaptation of the inventory analysis work sample structure it was also confirmed in Turkey.
Reliability coefficient for each factor and the whole scale was examined with Cronbach’s alpha coefficient. The Cronbach’s alpha coefficient was over 0.80 in sub-factors and total factor scores for ONI. The Cronbach’s alpha coefficient was 0.906 for ONI total factor scores and Cronbach’s alpha values for “behaviours”, “impairements”, and “emotions” were found to be 0.821, 0.842, and 0.809, respectively. Cronbach alpha reliability coefficient is expected to be above 0.70 [30]. Accordingly, the whole scale and its sub-factors were obtained reliably.
There is a statistically significant relationship between the total scores of ONI and the total scores of EAT-26 (p < 0.01). A positive and moderate relationship (r = 0.418) was found between ONI and EAT-26. In addition, the correlation coefficient between ONI and BMI was found to be statistically significant (p < 0.01). A positive and low level (r = 0.160) correlation was found between ONI and BMI. In other words, as ONI scores increase, both BMI and YTT-26 scores increase or vice versa.
Table 3. ONI relationships with EAT-26 and BMI
|
ONI Total
|
ONI Behaviors
|
ONI Impairments
|
ONI Emotions
|
EAT-26
|
0,418**
|
0.311**
|
0.374**
|
0.401**
|
BMI
|
0,160**
|
0.62
|
0.221**
|
0.150**
|
EAT-26 = Aating Attitue Test-26, BMI = Body Mass Index, ** Correlation is significant at the 0.01 level, * Correlation is significant at the 0.05 level
Skewness and kurtosis are statistics that provide information about the normality of the data distribution, and when it is between -2 and +2, the data distribution is normal [31]. Accordingly, the skewness and kurtosis value for women and men was 1.050 / 0.059, and 0.808 / 0.725 respectively. So the data distribution is normal. Whether there is a difference according to gender is shown in Table 4.
Table 4. ONI relationships with gender
Gender
|
n
|
Mean
|
|
SD
|
t
|
df
|
p
|
Women
|
503
|
39.03
|
±
|
9.99
|
-1.227
|
708
|
0.22
|
Men
|
207
|
40.04
|
±
|
10.04
|
|
|
|
Values are expressed as n or mean±SD
There is no statistically significant difference between ONI scores according to gender (t(708)=-1.227, p = 0.22, p < 0.05). The average ONI of female and male are similar. In other words, female and male of ONI scores are at similar levels.