A positive relation between overconfidence and investment provision has been theoretically justified and practically assumed in the literature, but has not been thoroughly investigated. We test and confirm this positive relation between direct measures of overconfidence in one's financial knowledge and choice of investment. More precisely, strong overconfidence results in excess investment, underconfidence induces underinvestment, whereas moderate overconfidence leads to accurate investments. Our experimental results are based on different subject pools, financial professionals and students, and different media: computer-, paper-, and web-based. The degree of one's overestimation of one's individual financial knowledge relative to one's actual knowledge as well as relative to the knowledge of peers explains investment decisions better than one's actual knowledge. The relation between overconfidence and investment is robust to the degree of individual risk aversion, the riskiness of the investment projects, and to the changes in incentives structure.