Assessment of analytical similarity of tier 1 quality attributes is based on a set of hypotheses that tests the mean difference of reference and test products against a margin adjusted for standard deviation of the reference product. Thus, proper assessment of the biosimilarity hypothesis requires statistical tests that account for the uncertainty associated with the estimations of the mean differences and the standard deviation of the reference product. Recently, a linear reformulation of the biosimilarity hypothesis has been proposed, which facilitates development and implementation of statistical tests. These statistical tests account for the uncertainty in the estimation process of all the unknown parameters. In this paper, we survey methods for constructing confidence intervals for testing the linearized reformulation of the biosimilarity hypothesis and also compare the performance of the methods. We discuss test procedures using confidence intervals to make possible comparison among recently developed methods as well as other previously developed methods that have not been applied for demonstrating analytical similarity. A computer simulation study was conducted to compare the performance of the methods based on the ability to maintain the test size and power, as well as computational complexity. We demonstrate the methods using two example applications. At the end, we make recommendations concerning the use of the methods.
KEYWORDSbiosimilarity, confidence interval, exact-based intervals, generalized confidence intervals, Howe's method, Wald-type confidence intervals 316 317 have no clinical impact. If this information is unavailable, the Food and Drug Administration (FDA) recommends using = f × R , where the constant f is a fixed multiplier, and R is the variability of RP. The value of f = 1.5 is justified using power-based calculations as rationalized in Tsong et al 1 and Chow. 2 In this case, the set of hypotheses in Equation 1 becomes:( 2) Currently, analytical similarity is demonstrated using a two one-sided tests (TOST) of the hypotheses in Equation 2. The TOST is conducted by computing a 100(1 − 2 )% confidence interval on the difference T − R , and equivalence is demonstrated if the entire confidence interval falls within the range from −1.5 R to 1.5 R . In this setting, is the test size. However, in practice, R is unknown and is replaced in the EAC with a sample estimate. This approach does not account for the uncertainty in the estimation of R and is not recommended because it inflates the type I error and reduces the powers of the TOST. 3 Alternative approaches have been explored to address this issue.Two reformulations of the set of hypotheses in Equation 2 that facilitate development and implementation of statistical procedures to account for the uncertainty in the estimations of all the parameters, and in particular R , have been recently proposed in the literature. Burdick et al 4 reformulated the set of hypotheses in Equation 2 as effect size by dividing both sides of the inequalities by R...