# Article

Full entry | PDF   (0.2 MB)
Keywords:
locally most powerful rank tests; randomness; symmetry
Summary:
Let $X_i$, $1\le i \le N$, be $N$ independent random variables (i.r.v.) with distribution functions (d.f.) $F_i (x,\Theta )$, $1\le i \le N$, respectively, where $\Theta$ is a real parameter. Assume furthermore that $F_i(\cdot ,0)=F(\cdot )$ for $1\le i \le N$. Let $R=(R_1,\ldots ,R_N)$ and $R^+=(R_1^+,\ldots ,R_N^+)$ be the rank vectors of $X = (X_1,\ldots ,X_N)$ and $|X| = (|X_1|,\ldots ,|X_N|)$, respectively, and let $V = (V_1,\ldots ,V_N)$ be the sign vector of $X$. The locally most powerful rank tests (LMPRT) $S=S(R)$ and the locally most powerful signed rank tests (LMPSRT) $S=S(R^+,V)$ will be found for testing $\Theta = 0$ against $\Theta >0$ or $\Theta <0$ with $F$ being arbitrary and with $F$ symmetric, respectively.
References:
[1] Gibbons, J.D.: On the power of two-sample rank tests on the quality of two distribution functions. J. Royal Stat. Soc., Series B 26 (1964), 293–304. MR 0174120
[2] Hájek, J.: A course in nonparametric statistics. Holden-Day, New York, 1969. MR 0246467
[3] Hájek, J., Šidák, Z.: Theory of Rank Tests. Academia, Praha, 1967. MR 0229351
[4] Nguyen Van Ho: The locally most powerful rank tests. Acta Mathematica Vietnamica, T3, N1 (1978), 14–23.
[5] Lehmann, E.L.: The power of rank tests. AMS 24 (1953), 23–43. MR 0054208 | Zbl 0050.14702
[6] Scheffé, H.: A useful convergence theorem for probability distributions. AMS 18 (1947), 434–438. MR 0021585

Partner of