Stronge, William B.

This thesis demonstrates the theory and the application of
the Kalman filter model, a model where the coefficients are
not assumed to be constant over time but time-varying. This
model is approached in two different ways. The first is the
recursive approach and the second is the Mixed estimation
approach. Both of these two approaches describe in
different ways the original Kalman filter model. This thesis
also contains an empirical application of the Kalman filter
model, using real data from the Greek economy to estimate
the Demand for Money.

This thesis examines the relationship between
productivity growth and industrial policy using J.S. data
from 1948 to 1981. A growth accounting model is used to study
productivity growth and the recent productivity slowdown.
Beth sides of the industrial policy debate are offered. The analysis of the productivity slowdown is then applied
to the industrial policy debate to see if the establishment
of the latter could have avoided the former. The thesis
purports a negative response to the question.

The purpose of this thesis is to present an
econometric model for the region of Palm Beach County. This
type of economic analysis was chosen because it captures the
influence of the service and trade industries as well as the
simultaneous nature of other industries which dominate the
local economy.
The estimation results identified the construction
industry as a leading indicator of economic activity in
transportation, communications, utilities, finance,
insurance and real estate. This simultaneous structure of
the model led to the application of various multipler
analyses. It was found that local construction output
affected gross regional product, local personal income and
local total employment. National personal income was found
to influence local trade which in turn affects levels of
local output, employment and income.

This thesis demonstrates the theory and logic of the ridge
regression method of statistical estimation. The effect of
multicollinearity on ordinary least squares is explored,
and the optimality of the ridge estimators is derived. The
critical analyses of ridge regression that have been
developed in the biased estimation literature and by
Bayesian statisticians is discussed. The technique of
ridge regression is compared to ordinary least squares in
the context of estimating price and income elasticities for
Greek imports.

This paper uses annual time series, 1950-1980, to
estimate determinants of Canadian tourist expenditures in
the United States. Time series analysis is also given for
Florida tourism, but it is in small scale. In order to
examine Canadian and non-Canadian tourist behavior, results
of regression analysis are analyzed.

The purpose of this thesis is to estimate an econometric
model of Palm Beach County, Florida. An econometric
model was chosen as the appropriate method for study as the
said county is characteristic of a service based final
demand economy.
An underlying objective was to utilize data on income
and employment variables available on a consistent bases
from a Regional Economic Information System Data computer
tape provided by the u.s. Department of Commerce 1983.
These data distinguished among 11 industries and referred to
the years 1967-1983.
In conclusion the model shows that ordinary least
squares estimation results were generally significant in the
signas and goodness of fit. However evidence of positive
serial correlation of the disturbances was detected and the
results did not change substantially after applying the
Cocran-Orcutt procedure.

This thesis uses time series analysis to construct
models of income and consumption in the United States
between 1947 and 1983. The data are quarterly observations
on three measures of income and two of consumption. The
study begins with a survey of univariate and multivariate
model building techniques. With the life cycle - permanent
income hypothesis as a foundation, theoretical models of
income and consumption are discussed. These models are then
fit to the data and examined. Tests for causality are also
covered in order to determine the manner in which the two
processes are related in a multivariate model.

This paper uses annual time series, 1959-1975, to estimate
fundamental parameters of the production process of the
Greek manufacturing sector. The empirical analysis is carried
out using the translog production and cost functions.
Based on the results of the estimations some characteristics
of the Greek manufacturing sector are explained.

This thesis presents various formulations of finite distributed
lag models. The objective is to demonstrate how
prior restrictions may be imposed on econometric models in
order to estimate the lag distributions. Four formulations
are thus reviewed, namely, the arithmetic lag model, the
inverted-V lag model, the Almon polynomial, and the cubic
spline lag model. For the latter formulations, the interpolation
methods are reviewed. In addition, four models of
consumption are estimated under the various lag models, for
different lag lengths and orders of polynomials, in order
to demonstrate the properties of each formulation. In the
discussion of the results, certain inferences are made
about the consumption functions.

A 1979 input-output model was developed for Monroe County
regional data, by reducing the 1972 National Input-Output
Table using the simple location quotient technique of
Shaffer and Chu. A 1979 economic base model was also developed
for Monroe County using simple location quotients.
Input-output and economic base theory were presented prior
to the actual formulation of the regional models. The economic
structure of Monroe County, the components of the economic
base, and the income multipliers were presented. An
analysis of the economic impact on income in the region by
the components of the economic base under alternative models
is discussed.