Estimating economic relations from incomplete cross-section/time-series data

Authors dealing with combined cross-section/time-series data usually assume that complete time-series exist for all units under observation. In the context of micro data, however, this may be a very restrictive assumption. The paper is concerned with problems of model specification and estimation when the data at hand are incomplete time-series from a sample of micro units. Particular attention is paid to a situation where the sample of micro units ‘rotates’ over time. The main results are compared with those derived by Nerlove and others for the standard specification with complete cross-section/time-series data. Some illustrative examples based on data from Norwegian household budget surveys are also given.     

Demography and the demand for housing A reinterpretation of the Mankiw-Weil demand variable

This paper argues that the Mankiw-Weil forecast of a 47% decline in house prices over the period to 2007 is based on a serious misinterpretation of their demand variable. In a time-series context this variable, which comes from a cross-section regression of house values against the age of occupants, is a measure of the adult population, not the demand for housing services or the stock of houses. Econometric work suggests that in addition to adult population, real income, relative prices and real interest rates are important factors determining the aggregate demand for housing. To be credible, forecasts of house prices need to integrate information on demand with information on cost factors and the supply of new houses.     

Polynomial approximations in cross-sectional models

The time-series distributed lag techniques of econometrics can be usefully applied to cross-sectional, spatial and cross-section time-series situations. The application is perfectly natural in cross-section, time-series models when regression coefficients evolve systematically as the cross-section grouping variable changes. The evolution of such coefficients lends itself to polynomial approximation or more general smoothing restrictions. These ideas are not new, Gersovitz and McKinnon (1978) and Trivedi and Lee (1981) providing two of the earliest applications of cross-equation smoothing techniques. However, their applications were in the context of coefficient variation due to seasonal changes and this may account for the non-diffusion of these techniques. The approach here is illustrated in the context of age-specific household formation equations based on census data, using Almon polynomials when the regression coefficients vary systematically by age group. A second application is provided, using spatial data, explaining the incidence of crime, by region; using polynomial and geometric smoothing to model distance declining regional effects.     

General-to-Specific Modelling Using PcGets

Abstract.  This review examines the facilities provided by PcGets version 1.0, an OxMetrics module designed to implement automated general-to-specific model selection in the context of cross-section or dynamic time-series models that are linear in the parameters. A cross-section empirical example is used to illustrate the steps involved, the output produced and the options available for modellers.     

Screening the impacts of municipal service policy changes

The planning of municipal service delivery systems requires accurate forecasts of demand, and particularly of the effects the quality of service delivery has on demand. A metholology for this problem should meet three criteria, if it is to be useful for municipal planning: it must be low-cost and use generally available data; it must be based on user behavior, so that the effects of policy changes can be correctly attributed; and it must allow testing of the transferability of the results, since this is required for general forecasting use. This paper develops such a methodology, based on econometric analysis of data from a number of service areas within a number of regions, forming a double cross-section. Empirical tests of the methodology were performed for two local government services where the effect of service quality on demand is important: sewer and highway construction, which have been hypothesized to affect the patterns of development within regions; and solid waste collection, where the level of service provided affects how much waste enters the collection system and how much is littered, burned or recycled. The two case studies and other analyses suggest that the methodology is a useful tool for testing whether policy changes have an effect on the demand for service, but not for accurate demand forecasting. Thus, these simple models are relevant for the role of screening the effect of policy changes, but more detailed and localized approaches are necessary for system design.     

Small samples and collateral information: An application of the hyperparameter model

When time-series and cross-section data are available for estimating a linear relationship, the data may be pooled using a number of frameworks of varying degrees of restrictiveness. One possible framework which appears not to have been exploited in previous applied econometric work, but which may have some merit especially when the number of observations in the time-series or cross-section dimension is not very large, is the hyperparameter model of Lindley-Smith (1972). Under appropriate conditions the use of this framework enables one to obtain ‘improved’ Bayesian point estimates which yield predictions with smaller mean-square-error than those from ordinary least squares. The paper uses the hyperparameter framework to estimate a Cobb-Douglas production function using U.K. cross-sectional data. A cross-validation exercise is carried out to see how much of the potential of the Bayesian method is realised in practice.     

Price formation in commodity markets

This paper develops a theory-consistent market model for storable commodities and illustrates its characterization of the data-generating process for a set of major traded commodities. The dynamics of the system incorporate recent advances in modelling techniques. Cointegrated variables in the demand functions are represented by the error correction mechanism (ECM), and expected prices in the stock demand relationship are generated by a rational expectations process. The outside-sample performance of the model is tested against the pure time-series model used to formulate expected prices, and is shown to have a smaller mean square error than that of the time-series model. Thus the model provides comparatively efficient forecasts and, unlike models constructed in their reduced form, permits consideration of key behavioural relationships in commodity markets.     

Testing for homogeneity in demand systems when the regressors are nonstationary

An implication of optimizing theory is that demand functions are homogeneous of degree zero in prices and nominal income. Evidence based on estimations of demand systems has repeatedly found this restriction to be rejected by the data. However, the hypothesis is often formulated in terms of regressors that are non-stationary. This paper re-examines the evidence for homogeneity in light of recent developments in time-series econometrics with special emphasis on the treatment of trends. We find the demand system to be stochastically but not deterministically cointegrated. Using techniques developed for estimating cointegrating vectors in the presence of deterministic trends, we re-estimate the demand system and find that homogeneity holds in many cases.     

PRIVATISATION AND EFFICIENCY IN THE UK WATER INDUSTRY: AN EMPIRICAL ANALYSIS*

ABSTRACTS The post-privatisation structure of the UK water industry involves the separation of environmental services from other outputs previously produced under an integrated system by the publicly-owned water authorities. This paper examines the extent to which the integrated authorities benefitted from joint production. Estimating a dynamic multi-product cost function from pooled cross-section, time-series quality adjusted data drawn from the accounts of the water authorities for the period 1979/80–1987/88, prior to privatisation, significant elements of joint production are found. Divestiture of the industry, arguably justified on other criteria, implies the loss of substantial areas of cost complimentary.     

Property Rights and Rural Development in China''s Transitional Economy

This paper undertakes an empirical examination of the impact of the property rights system on agricultural growth in China's rural development. A model is developed, considering a conditional convergence hypothesis and control variables that capture the effect of property rights system, such as sown area, entrepreneurship and secondary school enrollment. Empirical testing is conducted under the error components method, using pooled cross-section (prefecture) and time-series data for the Shandong, Henan and Sichuan provinces. The empirical findings for the period 1994–2000 indicate that the initially less-developed prefectures tend to catch up with the initially more-developed prefectures through a more rapid growth rate in the Shandong, Henan and Sichuan provinces. The control variable of sown area affects agricultural growth in rural areas, whilst the effect of entrepreneurship on rural development is controversial. Small-scale household farming has limited the role of technological innovation in Chinese agricultural growth, thus, secondary school enrolment is less important for agricultural growth.     

Autoverkopen en autopark in Nederland, 1950–1970

Summary  This is a study of the demand for the ownership of new or firsthand cars, i.e. the demand of 'first owners' who habitually buy new cars which are then traded in long before they are obsolescent. Upon combining the evidence of various surveys with time-series for 1950-64 it is found that this ownership has an income elasticity of 2 and a price elasticity of – 1.25 in respect of the constant-quality index of new car prices earlier provided. On the average new cars are traded in after three years so that roughly one third of the existing stock is replaced every year. These values together determine an equation for purchases of new cars which accurately predicts new registrations in 1965 and 1966. Projections for the years 1967-70 are provided.
In the model employed the total number of cars (including used cars) is determined by the active demand exerted by 'first owners' on one hand and by the hitherto fairly constant scrappage rates on the other. Projections of the overall ownership rate can therefore be derived from the forecasts of new registrations. The ownership rate will approach 80% around 1970, and it is likely that at that stage the current scrappage rates will cease to apply in view of the greater predilection for comparatively younger cars.     

NATIONAL AND REGIONAL WAGE CURVES IN JAPAN 1981–2001

There is evidence in many countries of an inverse relationship between the real wages paid to workers and the unemployment rate in their local labor market, a so-called wage curve. However, the evidence to date for Japan has been rather limited. In this paper, we estimate wage curves for Japan using pooled cross-section time-series data from 1981 until 2001. The presence of a wage curve is confirmed. The wage curve has become slightly more elastic after the bubble economy of the 1980s than it was in the pre-bubble and mid-bubble period. The unemployment elasticity of pay is greater for males than for females. We also estimate regional wage curves using time-series data. The male wage curve elasticity is larger in the northern regions of Hokkaido and Tohoku and the western region of Shikoku, while it is smaller in the central regions of Hokuriku, Tokai and Kinki.     

Economic and Noneconomic Factors Influencing Geographic Differentials in Homelessness: An Exploratory State-Level Analysis

In this exploratory state-level empirical study for the United States, the authors estimate a pooled time-series/cross-section framework, with control variables for population size and population growth, for the years 2015–2016. Within this context, the least squares estimates lead to the following tentative findings: (1) homelessness is positively associated with the overall cost of living, on the one hand, and the average rent level, on the other hand; (2) homelessness appears to be an increasing function of the percent of the population without a high school diploma but a decreasing function of the percent of the population with a bachelor’s degree or a higher level of formal education; (3) homelessness is a decreasing function of labor market freedoms reflecting the degree of union density and union power, on the one hand, and excessive government employment beyond that needed solely for productive and protective services, on the other hand; (4) homelessness is positively associated with personal freedom from incarceration and arrest; and (5) homelessness is negatively associated with income, as higher income reduces homelessness. Based on these findings, preliminary policy implications are also provided.     

Misspecified models with dependent observations

General results are given in this paper which allow the development of a theory of estimation and inference for situations in which the model of a data-generating process has been misspecified. Observations may come from time-series, cross-section, panel, or experimental data. The nonlinear regression model is examined in some detail. Conditions are provided which ensure the consistency and asymptotic normality of the least-squares estimator with respect to the parameter vector of a weighted least-squares approximation to the underlying data-generating process. A specification-robust estimator of the asymptotic covariance matrix is given, allowing a proper treatment of inference in potentially misspecified models. The properties of the approximation and the covariance estimator are exploited to yield new tests for model specification.     

Machine learning algorithms for forecasting and backcasting blood demand data with missing values and outliers: A study of Tema General Hospital of Ghana

The major challenge in managing blood products lies in the uncertainty of blood demand and supply, with a trade-off between shortage and wastage, especially in most developing countries. Thus, reliable demand predictions can be imperative in planning voluntary blood donation campaigns and improving blood availability within Ghana hospitals. However, most historical datasets on blood demand in Ghana are predominantly contaminated with missing values and outliers due to improper database management systems. Consequently, time-series prediction can be challenging since data cleaning can affect models’ predictive power. Also, machine learning (ML) models’ predictive power for backcasting past years’ lost data is understudied compared to their forecasting abilities. This study thus aims to compare K-Nearest Neighbour regression (KNN), Generalised Regression Neural Network (GRNN), Neural Network Auto-regressive (NNAR), Multi-Layer Perceptron (MLP), Extreme Learning Machine (ELM) and Long Short-Term Memory (LSTM) models via a rolling-origin strategy, for forecasting and backcasting a blood demand data with missing values and outliers from a government hospital in Ghana. KNN performed well in forecasting blood demand (12.55% error); whereas, ELM achieved the highest backcasting power (19.36% error). Future studies can also employ ML algorithms as a good alternative for backcasting past values of time-series data that are time-reversible.     

Regional differences in small firm entry in manufacturing industries: Lower Saxony, 1979–1991 †

This paper is an empirical study of inter-regional and inter-temporal variations in entry of new firms using longitudinal data covering all manufacturing establishments in Lower Saxony between 1979 and 1991. Patterns of entry are reported for sixteen regions based on gross rates of entry (number of new firms) and entry intensities (shares of employees). An empirical model is applied to detect regional characteristics that are highly correlated with entry. Pooling of cross-section and time-series data allows for control of influences of varying macroeconomic conditions and unobserved regional characteristics that turned out to be important. Small firm entry tends to be positively related to high overall economic growth, and to be higher in regions where both the small firm employment share and the level of wealth are high while the wage rate is low. We find no evidence for a negative impact of the business tax rate or for a positive effect of regional subsidies.     

A re-examination of the q theory of investment using u.s. firm data

Investment models based on Tobin's q are theoretically appealing, but they have been an empirical disappointment when applied to aggregate time-series data. This paper explores two potential explanations for the poor empirical performance of q investment models, problems arising from aggregation and imperfect competition. The results suggest that aggregation is responsible for spurious evidence of dynamic misspecification and at least partially responsible for an upward bias in estimated adjustment costs. The evidence also suggests that imperfect competition in output markets may have an effect on the investment behaviour of some firms.     

Intermediated surge pricing

Although Uber and Lyft are known for their flexible “surge pricing,” they are surprisingly rigid in another way: each firm takes a constant percentage of passenger fare whether or not there is a surge. In this paper, I investigate the possible reasons for, and the impact of, this rigidity. I study a market in which a profit‐maximizing intermediary facilitates trade between buyers and sellers. The intermediary sets prices for buyers and sellers, and keeps the difference as her fee. Optimal prices increase when demand increases, that is, shifts right. If a demand increase is due to an increase in the number of ex ante symmetric buyers, then the intermediary's optimal percent fee decreases. If, instead, a demand increase is due to a reduction in the elasticity of demand, then the intermediary's optimal percent fee increases. In either case, if the intermediary keeps a constant percent fee regardless of shifts in demand, as is the case with Uber and Lyft, then surge pricing (i.e., the ratio of price during high demand to price during low demand) is amplified on one side of the market and diminished on the other side.     

Autoverkopen en autopark in Nederland, 1950–1970

Summary This is a study of the demand for the ownership of new or firsthand cars, i.e. the demand of ‘first owners’ who habitually buy new cars which are then traded in long before they are obsolescent. Upon combining the evidence of various surveys with time-series for 1950-64 it is found that this ownership has an income elasticity of 2 and a price elasticity of – 1.25 in respect of the constant-quality index of new car prices earlier provided. On the average new cars are traded in after three years so that roughly one third of the existing stock is replaced every year. These values together determine an equation for purchases of new cars which accurately predicts new registrations in 1965 and 1966. Projections for the years 1967-70 are provided. In the model employed the total number of cars (including used cars) is determined by the active demand exerted by ‘first owners’ on one hand and by the hitherto fairly constant scrappage rates on the other. Projections of the overall ownership rate can therefore be derived from the forecasts of new registrations. The ownership rate will approach 80% around 1970, and it is likely that at that stage the current scrappage rates will cease to apply in view of the greater predilection for comparatively younger cars.     

Modernization in Mainland China:

A bstract . After 1949, mainland China, a developing socialist country, adopted an inward-looking policy with emphasis on self-reliance and economic independence. However, in their drive for economic reform that began in 1978, mainland China drifted to the new doctrine of "taking self-reliance as the principal means and external assistance as a subsidiary." A version of the two-gap model is constructed to test the hypothesis that both domestic capital accumulation and foreign capital inflows affect economic development in mainland China , the latter being an indicator of modernization. Due to insufficient data, pooled cross-section and time-series data for the period 1984–1986 are employed. The quantitative evidence suggests that foreign capital inflows, instead of domestic capital accumulation, have importantly affected the modernization drive of mainland China. The recent political turmoil in mainland China has slowed down foreign capital inflows which in turn may retard its modernization.