In time series macroeconometric models, the first difference in the logarithm of a variable is routinely used to represent the rate of change of that variable. It is often overlooked that the assumed approximation is accurate only if the rates of change are small. Models of hyper-inflation are a...

A way to test the relevance of endogenous growth theory is to test this existence of the relationship between innovation and total factor productivity at the country level. More recently this approach has been extended to take account of externalities induced by innovation activities from...

In most liberalised electricity retail markets, incumbent firms still hold the majority of residential consumers. This situation focused the attention of regulatory institutions and energy economists on the determinants of consumers switching decisions. Fewer studies have, however, been devoted...

Economists have long recognized that in free markets, incentives to innovate will be diluted unless some factors grant innovators with a temporary monopoly. Patenting is the most cited factor in the economic literature. This survey concentrates on another factor that confers innovators with...

In the Gauss-Markov regression model, one can always update the least square estimate of the slope vector, given new observations at the values of the explanatory variables. The updated estimate is often considered as a time-varying state of an auto-regressive system in Kalman filtering and...