Kimberly D. Zieschang

Imputation of Missing Values When the Probability of Response Depends on the Variable Being Imputed

Abstract A method is developed for imputing missing values when the probability of response depends upon the variable being imputed. The missing data problem is viewed as one of parameter estimation in a regression model with stochastic censoring of the dependent variable. The prediction approach to imputation is used to solve this estimation problem. Wages and salaries are imputed to non-respondents in the Current Population Survey and the results are compared to the nonrespondents IRS wage and salary data. The stochastic censoring approach gives improved results relative to a prediction approach that ignores the response mechanism.

Consistent Estimation of the Impact of Tax Deductibility on the Level of Charitable Contributions

When charitable contributions are tax deductible, the marginal price of charitable giving in other consumption foregone per dollar of contributions is generally less than unity. Further, if the income tax schedule is a progressive step function, the marginal price of contributions is generally a rising step function of the level of contributions. The problem of estimating a contributions demand function for individuals is therefore complicated by the spurious correlation between the level of contributions and the observed marginal price. We take this econometric problem into account in estimating a contributions demand function using data from the 1972-73 Consumer Expenditure Survey. After comparing our results with those of estimation techniques used by other authors, we provide evidence on the impacts of alternative tax policies on charitable giving using our estimates of the model parameters.

An index number approach to measuring bank efficiency: An application to mergers

Abstract The current wave of bank mergers has resulted in an interest in the measurement of consequent efficiencies. Previous studies have generally focused on the measurement of merger-induced cost efficiencies. In this paper, we turn to the production side and examine the change in relative productivity arising from bank mergers. After deriving our superlative multilateral productivity index, we compute the indexes for our entire sample of banks, approximately 2,000 banks in each of the years 1984–1988, and for a cohort of 160 banks that merged in 1986. We find that acquiring banks achieve no gains in efficiency, and this finding supports those of other studies. On the other hand, we find that our acquiring banks are consistently more productive than the sample as a whole. By implication, if mergers can be generally characterized as the acquisition by a relatively more productive bank of a relatively less productive bank, an empirically valid supposition, then industry performance should improve as a result of these mergers.

The productivity of the banking sector: integrating financial and production approaches to measuring financial service output

Measurement of output for services in general, and for financial services in particular, is a challenge. In the context of the national accounts, there is a significant component of financial services output for which payment is made implicitly through the spread between the asset interest earned and liability interest paid by financial institutions. Although it is reasonably clear that the total value of output of financial institutions includes the net interest income on financial asset and liability products (such as loans and deposits for banks) plus explicit service charges, there are unsettled issues concerning the correct allocation of the net interest component across business (intermediate consumers) versus households, government, and the rest of the world (final consumers). Recent revisions in national accounting rules for banking, together with the developments since the late 1970s in the microeconomic theory of financial firms and of household consumption of financial asset services (Diewert 1974, Barnett 1978, Donovan 1978, Hancock 1985) represent important developments in our understanding of the economics of and measurement possibilities for the banking sector. Central to, and an important contribuLtion of, this last line of literature has been the characterization of the prices of individual service products in terms of the Barnett (1978)-Donovan (1978) user cost of money. These user cost prices are simple functions of items, such as interest rates, that can be measured in financial market transactions. The principal practical economic measurement issues these developments have illuminated are twofold:

A note on the decomposition of cost efficiency into technical and allocative components

In this note a simpler method of cost efficiency decomposition than that of Kopp and Diewert (1982) is proposed. The method is obtained by application of a duality theorem for cost and distance functions.

Incorporating ancillary measures of process and quality change into a superlative productivity index

One of the persistent problems plaguing the measurement of productivity and output is accounting for changes in product quality. A similar problem arises in attempting to explain shifts in a production function using information on changes in the characteristics of the production process itself. We consider these problems under a behavioral model in which the firm chooses a profit-maximizing bundle of input/output/process characteristics as well as the profit maximizing levels of input and output. This view of quality change is similar to the endogenous design index advocated by Triplett [1983] for industrial prices and the endogenous quality indexes analyzed by Pollak [1983] for consumer prices. We show how a price-characteristics locus can be used to adjust the Tornqvist output- and input-oriented multifactor productivity indexes of Caves, Christensen and Diewert [1982] for changes in input, output and process characteristics. To show the applicability of the methodology to services, we apply the results in the framework of the commercial banking measurement of Fixler [1988] to measure the impact of bank branching on multifactor productivity.

Measuring the Technical Efficiency of Multiple Output Production Technologies

In this paper we consider a production unit employing many inputs to produce many outputs, subject to the constraints imposed by given technology. Our purpose is to present and analyze various measures of the effectiveness with which inputs are transformed into outputs. Early efforts in this direction were made by Koopmans [1951] and Debreu [1951]. Koopmans defined a feasible input-output vector to be efficient if it is technologically impossible to increase any output and/or to reduce any input without simultaneously reducing other outputs and/or increasing other inputs. Using this definition, he was able to prove that a vector is efficient if, and only if, it possesses a positive normal to the production possibilities set. While Koopmans offered a definition and a characterization of efficiency, Debreu provided a measure of efficiency with his “coefficient of resource utilization.” This coefficient is computed as one minus the maximum equiproportionate reduction in all inputs consistent with continued production of existing outputs, and from it Debreu obtained a measure of the cost of inefficiency. More recently Vincze [1960] and Eichhorn [1972, 1978a, 1978b] have considered a production process involving many variable inputs, one fixed input, many outputs and a time dimension. In this context he defined the price-dependent notions of technical and economic “effectiveness” in terms of families of functional equations, and derived closed-form parametric indexes of technical and economic effectiveness as solutions to the respective families of functional equations.

Sample Weighting Methods and Estimation of Totals in the Consumer Expenditure Survey

Abstract The widely used Principal Person method of weighting households in federal government surveys uses external post-Censal information on population to improve survey sample weights by a form of poststratification. While the Principal Person Methodology can be viewed as part of a procedure to adjust for nonresponse and undercoverage, it is not oriented for efficiently incorporating ancillary information or combining information from multiple surveys into survey estimates of subdomain totals. In this article a generalized least squares adjustment algorithm is shown to incorporate ancillary information in a way that, in principle, reduces the design variance of estimated survey totals. The flexibility of the method is exploited in an application to the Consumer Expenditure Survey that makes use of its “weighting control” and “composition” features.

Evidence on taxation and charitable giving from the 1983 U.S. treasury tax model file

We have applied our model of taxation and charitable giving developed in Reece and Zieschang (1985) to the 1983 Treasury Tax Model File and found no response of giving to marginal tax rates and a small response to income.

Problems with the measurement of banking services in a national accounting framework

The paper considers some of the problems associated with the indirectly measured components of financial service outputs in the System of National Accounts (SNA), termed FISIM (Financial Intermediation Services Indirectly Measured). The paper utilizes a user cost and supplier benefit approach to the determination of the value of various financial services in the banking sector. The present paper also attempts to integrate the balance sheet accounts in the SNA with the usual flow accounts. An empirical example of various nominal output concepts that could be applied to the U.S. commercial banking sector is presented.