The empirical evidence on rational inattention lags the theoretical developments: micro evidence on one of the most immediate consequences of observation costs—the infrequent observation of state variables—is not available in standard datasets. We contribute to filling the gap using new household surveys. To match these data we modify existing models, shifting the focus from nondurable to durable consumption. The model features both observation and transaction costs and implies a mixture of time-dependent and state-dependent rules. Numerical simulations explain the frequencies of trading and observation of the median investor with small observation costs and larger transaction costs.