Page 142 - Contributed Paper Session (CPS) - Volume 6

CPS1850 Paula Alves de Almeida et al.
cases for films directed by a man and 95% of all cases, indicating a good
predictive power.
We also considered as response variable “the scriptwriter is a woman” and
as auxiliary variables the following characteristics of films: sex of director, sex
of cinematographer, sex of producer, sex of protagonist, and film genre. The
variables “sex of cinematographer” and “film genre” were not statistically
significant in the logistic regression and were excluded from the model. The
“sex of protagonist” was statistically significant, but the model with this
variable has a smaller value of the pseudo R and lower predictive power than
2
the chosen model. Table 2 indicates that when the director is a woman, the
odds ratio of the film has also a female scriptwriter is 115 times that for films
with male directors. In addition, the odds ratio for a film’s being written by a
woman is roughly 2 times when the producer is a woman then for male
producers.
Table 2 Estimated coefficients, corresponding standard errors and odds ratios to
“sex of writer”

The chosen model was the one with the best value for the goodness-of-
fit statistics and predictive power among the fitted models. According to the
2
value of the pseudo R , the set of variables included in the model may explain
65% of the variability of the response variable. The model correctly predicts
roughly 79% of the outcomes for films directed by a woman, 98% of the cases
for films directed by a man and 95% of all cases.
As a result of the statistical model to investigate the association between
the “sex of the director” and the other selected film characteristics, Table 3
displays the estimated probabilities of the occurrence of the event “a film is
directed by one or more women” and the event “a film is directed by one or
more men” when controlling by the explanatory variables. In addition, based
on the statistical model to investigate the association between the “sex of the
scriptwriter” and the other selected film characteristics, Table 4 presents the
estimated probabilities of the occurrence of the event “a film is written by
women” and the event “a film is written by men” according to the explanatory
variables.

131 | I S I W S C 2 0 1 9