| Popis: |
Bipolar disorder and schizophrenia share some key symptoms which lead to misdiagnosis, especially on initial presentation. In this study, we have considered two categories of patients belonging to schizophrenia and bipolar disorder with (i) total duration of illness (TDI) less than or equal to 2 years and (ii) TDI greater than 2 years. We statistically test the difference between the severity of symptoms of the two groups as measured by their respective psychiatric rating scales using C(α) (or score tests), likelihood ratio and permutation tests for both categories of patients. The unknown parameters are estimated using maximum likelihood, moments by Cran and Bayesian estimation. It is observed that there exists a significant difference between the two disorders for patients in second category based on real and simulated data. Further, performance of C(α) statistic is compared on the basis of p-value and power performance with the other two methods. A new weight suggested in this paper is found to be as efficient as the previous weight based on simulation study. A retrospective data of 108 patients diagnosed with schizophrenia and bipolar disorders is collected from Lady Hardinge Medical College & Smt. S.K. Hospital, New Delhi, India for the calendar year 2013–2014. |
