Normal approximation and self-normalized moderate deviations for the minimal random walk with random step sizes

Abstract

We study the minimal random walk with independent positive random step sizes. By separating the movement count from the centered step-size noise, we obtain normal approximations and self-normalized Cramér-type moderate deviations under finite-moment assumptions. For the noise, conditioning on the movement count yields Kolmogorov, Wasserstein and Zolotarev bounds. A polynomial moderate-deviation range holds when a recalled stop can lead to movement. At the boundary where this probability is zero, we obtain a logarithmic range and construct a bounded nonsymmetric example excluding a general polynomial range. For the full position, a weighted martingale representation gives limit laws in the different regimes, nonuniform normal approximations and moment-distance bounds without logarithmic losses. Variance concentration also yields self-normalized moderate deviations in the diffusive and critical regimes.