TCP throughput is one of the major communication quality metrics. In order to grasp this metric by active measurement while imposing a lower load, various estimation techniques have been proposed. These techniques are categorized as either equation-based or history-based; here we focus on the latter. Conventional history-based estimation techniques target a wired environment and estimate temporally. By contrast, we target a wireless environment and estimate spatially. For TCP throughput estimation using lightweight probing, we propose a new modeling whereby TCP throughput is determined by capacity and delay fluctuation. We evaluate our proposed modeling by conducting experiments in a commercial CDMA2000 1x EV-DO network. This evaluation empirically verified the validity of our model to estimate TCP throughput in a wireless environment with lightweight probing.