Journal Article The Friedman-Savage Hypothesis and Convex Acceptance Sets: A Reconciliation Get access Richard N. Rosett Richard N. Rosett University of Rochester Search for other works by this author on: Oxford Academic Google Scholar The Quarterly Journal of Economics, Volume 81, Issue 3, August 1967, Pages 534–535, https://doi.org/10.2307/1884819 Published: 01 August 1967

Some economic variables are restricted by an upper and lower limit but are continuous between the two limits. Measurements of such variables are sometimes available in their natural form and sometimes only in the form of three categories where information concerning the middle category is suppressed (unemployed, employed part time, employed full time, for example). Where such a variable is a continuous function of other variables between the two limits, the function can be estimated from data of either sort provided the function and the distribution of errors can be specified. WHEN THE LIMITED dependent variable technique developed by Tobin [3] is extended to provide for cases in which the dependent variable in a regression is subject to both an upper limit and a lower limit, a surprising property of the statistical model emerges.1 Estimates of the regression function can be obtained whether or not the exact values of the dependent variable are known for the nonlimit cases. Provided the functional form can be specified correctly, classification of the dependent variable into upper limit, lower limit, and non-limit observations provides enough information, along with observed values of the independent

This work is known to a generation of financial economists having marked the beginnings of the field known as financial econometrics. This edition sets out to show that the text, first written in 1964, is still relevant is still relevant at the beginning of the 21st century.

Data drawn from the 1960 Survey of Consumer Expenditures are used to estimate price and income elasticities of the demand for hospitalization and physicians' services. The price elasticity ranges from -0.35 to -1.5 for prices ranging from 20 to 80 percent of the 1960 market price. The income elasticity ranges from 0.25 to 0.45 for incomes ranging from 4,000 to 10,000. The estimated demand function is used to calculate the cost of providing protection against the highly probable, small losses typically covered by health insurance policies. A family with an income of 7,000 paid 2.5 times the actuarial value of the loss to protect itself against a highly probable 110 loss.