INTRODUCTION

So far we have confined our discussion to models in which the effects of omitted variables are either individual-specific or time-specific or both. But there are cases in which there are changing economic structures or unobserved different socioeconomic and demographic background factors that imply that the response parameters of the included variables may be varying over time and/or may be different for different cross-sectional units. For instance, in farm production it is likely that variables not included in the specification could also impact the marginal productivity of fertilizer used such as soil characteristics(e.g., slope, soil fertility, water reserve, etc.) or climatic conditions. The same applies to empirical studies of economic growth. The per capita output growth rates are assumed to depend on two sets of variables over a common horizon. One set of variables consists of initial per capita output, savings, and population growth rates, variables that are suggested by the Solow growth model. The second set of variables consists of control variables that correspond to whatever additional determinants of growth a researcher wishes to examine (e.g., Durlauf 2001; Durlauf and Quah 1999). However, there is nothing in growth theory that would lead one to think that the marginal effect of a change in high school enrollment percentages on the per capita growth of the United States should be the same as the effect on a country in sub-Saharan Africa. Had all these factors been taken into account in the specification, a common slope coefficients model may seem reasonable.