Abstract:
We prove the validity of one-term Edgeworth expansion for Student's $t$-statistic under minimal conditions: the distribution of observations is nonlattice and has finite third moment. As a corollary we obtain the second-order correctness for the bootstrap of Student's t-statistic under these optimal conditions, thus extending classical result of Singh [Ann. Statist., 9 (1981), pp. 1187–1195] to the Studentized mean.
Citation:
M. Bloznelis, H. Putter, “Second-order and bootstrap approximation to Student's $t$-statistic”, Teor. Veroyatnost. i Primenen., 47:2 (2002), 374–381; Theory Probab. Appl., 47:2 (2003), 300–307
Wang Q., “Refined Self-normalized Large Deviations for Independent Random Variables”, J Theoret Probab, 24:2 (2011), 307–329
C&H/CRC Monographs on Statistics & Applied Probability, 20114852, Extreme Value Methods with Applications to Finance, 2011, 351
Jing B.-Y., Wang Q., “A Unified Approach to Edgeworth Expansions for a General Class of Statistics”, Stat Sin, 20:2 (2010), 613–636
Wang Qiying, Hall P., “Relative errors in central limit theorems for Student's $t$ statistic, with applications”, Statist. Sinica, 19:1 (2009), 343–354
S. Yu. Novak, “On self-normalized sums and Student's statistic”, Theory Probab. Appl., 49:2 (2005), 336–344
Hall P., Wang Qiying, “Exact convergence rate and leading term in central limit theorem for Student's $t$ statistic”, Ann. Probab., 32:2 (2004), 1419–1437