# Making a new variable from existing variables

#### Duki

##### New Member
Hi everyone! I have this paragraph from an article
'We next created a scalar variable that incorporated participants’ confidence ratings into their match judgments, which we analyzed using a 2 x 2 (crime type x suspect characteristics) ANOVA. Specifically, we multiplied participants’ match judgments (coded as -1 for no match and +1 for match) by their confidence (1–10) and applied a -/+.5 correction to account for the absence of zero values.' - Smalarz, L., Madon, S., Yang, Y., Guyll, M., & Buck, S. (2016). The perfect match: Do criminal stereotypes bias forensic evidence analysis? Law and Human Behavior, 40(4), 420–429.

Can someone explain to me why it was necessary to create that new variable like that?
Thanks!

#### katxt

##### Active Member
I'm guessing here. It looks as if they wanted a scale of the "strongly disagree" "no opinion" "strongly agree" type.
The new scale goes from -9.5 to 9.5 where -9.5 means "very confident there is no match", through -0.5 and 0.5 which means "I'm really not sure if there is a match or not" through to +9.5 which means "very confident there is a match" (although I would have described the correction as +/- 0.5). It's hardly likely to be normal.

#### Duki

##### New Member
I'm guessing here. It looks as if they wanted a scale of the "strongly disagree" "no opinion" "strongly agree" type.
The new scale goes from -9.5 to 9.5 where -9.5 means "very confident there is no match", through -0.5 and 0.5 which means "I'm really not sure if there is a match or not" through to +9.5 which means "very confident there is a match" (although I would have described the correction as +/- 0.5). It's hardly likely to be normal.
Thank you for your response. It really helped!