A structural model is developed and estimated by a maximum likelihood routine to investigate interrelated factor demand subject to nonconvex adjustment costs. The dataset concerns Norwegian plants operating in manufacturing industries and it covers the period 1993-2005. The estimates indicate that it is advantageous to adjust the stock of labour and capital simultaneously. The cost advantage of simultaneous changes is small for capital but is large for labour. The empirical results suggest that when estimating separate factor demand models the bias of parameter estimates is most severe in case of labour demand.