The hypothesis test that will determine if there are significant differences between year cohorts for mean days of care/admitted baby. The Ho (null hypothesis) will state: there is no association between the year cohorts for mean days of care/admitted baby, and the association is by chance. In contrast, H1 will state: there is an association between the year cohorts for mean days of care/ admitted baby. The type of hypothesis test may be the t-test. With the t-test, we can compare continuous data (means days of care/admitted baby) of both cohorts (group differences)(Bruce, Pope, & Stanistreet, 2008). In comparison, a chi-squared test would not determine the strength of the association, only that there may be evidence of an association ( Bruce, Pope, & Stanistreet, 2008). Also, categorical data is required for chi-squared tests (Bruce, Pope, & Stanistreet, 2008). Furthermore, logistic regression statistical analysis may be applied to account for confounding variables (Pourhoseingholi, Baghestani, & Vahedi,
The hypothesis test that will determine if there are significant differences between year cohorts for mean days of care/admitted baby. The Ho (null hypothesis) will state: there is no association between the year cohorts for mean days of care/admitted baby, and the association is by chance. In contrast, H1 will state: there is an association between the year cohorts for mean days of care/ admitted baby. The type of hypothesis test may be the t-test. With the t-test, we can compare continuous data (means days of care/admitted baby) of both cohorts (group differences)(Bruce, Pope, & Stanistreet, 2008). In comparison, a chi-squared test would not determine the strength of the association, only that there may be evidence of an association ( Bruce, Pope, & Stanistreet, 2008). Also, categorical data is required for chi-squared tests (Bruce, Pope, & Stanistreet, 2008). Furthermore, logistic regression statistical analysis may be applied to account for confounding variables (Pourhoseingholi, Baghestani, & Vahedi,