It is generally accepted that agricultural production is characterized by increasing returns to scale. In this paper we examine the evidence allegedly supporting this assertation and come to the conclusion that the hypothesis of increasing returns is not warranted. The essence of our argument is that if increasing returns were important we would have seen huge "food factories" dominating the industry. Instead, the dominating form of organization is the family unit and farms come in a multitude of sizes--as can be expected in a constant cost industry.