If T(x) be an estimator of 0, then bias term can be defined as, a) 0-E [T(x)] b) E[T(x)]-0 c) E[T(x)]-0² d) T(x)-0 In which case, an estimator T (x) is called as bias estimator of 0? E[T(x)]=0 E[T(x)] +0 a) b) c) d) Either E[T(x)] or E[T(x)]>0 E[T(x)]>0 If T(x) be an estimator of 0, then the mean square error can be defined as, a) Var [T(x)] + Bias² [T(x)] b) Var[T(x)] + Bias [T(x)] c) Var [T(x)]-Bias [T(x)] d) Var[T(x)] If X₁, X2,..., X, be independent and identically distributed sample taken from N(μ, 1), 器 our estimate is T(X)=-x, then a) T(X)~ N(u, 1) b) T(X)~N(nu, n) c) T (X) ~ N (1) d) T(X)~x²(n)