This paper examines problems involved in the specification of the correct set of independent variables in choice models. The analytical approach is similar to Theil's use of auxiliary regressions in the case of standard linear models. The key conclusions are that the inclusion of superfluous independent variables does not affect the consistency of the correct coefficients, but exclusion of independent variables can lead to inconsistent estimates. The sources of bias are the possible correlations between included and excluded independent variables and the change in the structure of the random error terms in the utility functions. Because of the flexibility of its error structure, particular attention is given to the multinomial probit model. 

When independent variables are excluded, asymptotic differences among are alternative estimators arise because of different implicit error structures. The differences among the alternative estimators and the general effects of under specification are examined empirically with simulated data.

A specification issue which has been handled differently in various empirical applications is whether or not to include alternative specific constants in models of choice behavior. Some applications have excluded constants, others have included a full set of constants, and a third class of examples uses unique constants for some alternatives, but not all. 

In logit models in which each individual has the same set of alterna tives, the exclusion of constants in the estimation of models when the correct model actually has alternative specific effects leads to inconsistent estimates of the coefficients of the remaining independent variables. However, the inclusion of constants when no such effects exist does not affect the consistency of the estimates of the coefficients. These results are illustrated by simple hypothetical examples and by empirical examples. 

When nonratio scale variables are used in logit models, the coefficients of the independent variables are not invariant under arbitrary scale shifts when alternative specific constants are excluded. 

Finally, the use of models to predict the response to new alternatives and the transferability of models which might or might not include alternative specific effects is discussed. 

The major conclusion is that the inclusion of: a full set of alternative specific constants in logit models estimated with large samples is generally preferred over the exclusion of one or more alternative specific constants.

The goals and objectives of providing public transportation services in small cities and rural areas are different from those of metropolitan regions. For the small cities and rural areas, the primary purpose is supplying transportation services to meet basic needs of people who do not have any convenient means of transportation. This group can be classified collectively as the carless. Carless simply implies that automobile transportation is not available. This group includes the poor, handicapped, elderly, and youth, as well as, members of households that do not own an automobile or do not have access to an automobile. 

The mobility needs of the carless are examined in this review. The characteristics of the special mobility groups are studied. The emphasis of the review is on the planning process and operation of public transportation services in the small cities and rural areas. A summary of the characteristics of existing nonmetropolitan transportation services is also presented. 

The state of the art in nonmetropolitan transportation planning is one of considerable disjointed effort. Although there has been careful planning related to the implementation of public transportation operations in the rural areas and small cities, little systematic development of goals, objectives, policies, and criteria could be found. The high per capita costs of providing transportation services to a small disadvantaged group require careful analyses with respect to the equity and efficiency of costs and benefits. In view of increasing competition of various public and social services for very limited funds, there will be greater demand for careful accounting and justification of public transportation services in small cities and rural areas.

This annotated bibliography is prepared for those who are interested in the problem, concerned citizens and planners in small cities and rural areas, and policy analysts in various levels of government. Public transportation planning in nonmetropolitan areas has been disjointed. There are few well developed goals, objectives, and policies. Standards and values are varied among different communities. Consequently, decisions on public transportation services can best be made locally with active citizen participation. This bibliography, together with a review paper (ITS Report D-SR-77-2), provides adequate information for gaining insights into the various facets of the problem. Additional information and assistance can be obtained from the library of the Institute of Transportation Studies (Berkeley and Irvine), the Division of Mass Transportation - California Department of Transportation, the Urban Mass Transportation Administration - U.S. Department of Transportation, and other agencies or institutes. 

The bibliography is divided into three sections. The first section is a list of references arranged alphabetically by author. Each article is classified by a system of coded keywords. The keyword codes are shown in parentheses after each reference. The second section contains the abstracts of the articles. The third section is an index of articles by subject. The cross-reference is shown by the article number.