We introduce noisy information in the determination of stock prices. Agents receive a noisy signal about the structural shock driving future dividend variations. The resulting equilibrium stock price includes a transitory component { the \noise bubble" { which can be responsible for boom and bust episodes unrelated to economic fundamentals. We propose a non-standard VAR procedure to estimate the structural shock and the \noise" shock, their impulse response functions and the bubble component of stock prices. We apply such procedure to US data and _nd that noise explains a large fraction of stock price volatility. In particular the dot-com bubble is entirely explained by noise. On the contrary the stock price boom peaking in 2007 is not a bubble, whereas the following stock market crisis is largely due to negative noise shocks.