homophobia) to 100 (highest level of homophobia). The ATLG scores of the sample participating in this study ranged from 20 to 100. Seventy-eight percent of respondents had an overall ATLG score of 60 (mid-range) or less while the remainder (22%) had scores greater than 60.

Validation of the research instrument used in this study was completed with the use of confirmatory factor analysis (CFA— Figure 1). Specifically, the standardized regression weights of

each of the 20 items of the ATLG overall construct of homophobia. the indices indicated that 16 of significant. All but four of the value > .71 at p = .05.

were correlated with the Analysis of the regression of the 20 items are statistically indices had a factor loading

Thus, the regression values

indicate that the influence of

these indices on the with a regression wei and 17. In addition t item’s critical ratio validity. According t with standard normal ratios more than 1.96 item on the ATLG was critical ratio values Scale was .77; validi Cronbach’s alpha scor of the ATLG for this alpha value.

construct is relevant. The only ATLG items ght < .71 were item numbers 1, 2, 4, 13,

o

analysis of the regression weights, each

# (CR) value was also analyzed to support

o

Garson (2005), in random sample variables

distributions, estimates with critical

are significant at the .05 level. Each significant in the overall model, with

>1.96. The Cronbach’s alpha for the ATLG ty for an instrument is supported with a e > .7 (Garson, 2005). Thus, the validity study was also supported by the Cronbach’s

64