Department of Statistics, UCLA

 This paper presents a novel empirical study of innovation practices of U.S. com-

panies and their relation to productivity levels using new business micro data from

the Business Research and Development and Innovation Survey (BRDIS) for the years

2008-2011. The paper follows the work of Frenz and Lambert, who use factor analysis

to reduce a set of inputs and outputs of innovation activities into four latent unob-

served innovation modes or practices for OECD countries using Community Innovation

Surveys (CIS). Patterns obtained with BRDIS data are very similar to those found by

those authors in some OECD countries. Companies are grouped according to their

scores across the four factors to see that in large, small and medium companies more

than one mode of innovation practices prevails. The next step in the analysis links dif-

ferent types of innovation practices to levels of productivity using regression analysis.

The four innovation modes have a statistically signicant positive relation with the

level of productivity, other things constant. The paper demonstrates the possibility of

taking into account the multidimensionality of innovation without the use of composite indicators.