When considering binary generalized linear models, it. is also interesting to represent the relationship between covariates X and Y via a continuous unobserved intent variable, '1' and the linear model representation, %which are modelled such as a linear model: \":131f'pizui 1 Y;=0,if'1';<. with e marks we now consider that the noise component is a standard annel distribution : n in this case using latent variable write down expression for ph>