Written assignment 5 (optional)

Receive a grade

Readings

DeVellis, R. F. (2003). Scale development theory and applications. Thousand Oaks: Sage. (third edition of the book will also do)

Wooldridge, J. M. (2013). Introductory econometrics: a modern approach (4th ed.). Mason, OH: South Western, Cengage Learning. (Chapter 9.4)

Chang, H., & Cartwright, N. (2010). Measurement. In S. Psillos & M. Curd (Eds.), The Routledge companion to philosophy of science (1. publ. in paperback, pp. 367–375). London: Routledge.

Mesquita, L. F., & Lazzarini, S. G. (2008). Horizontal and Vertical Relationships in Developing Economies: Implications for SMEs' Access to Global Markets. Academy of Management Journal, 51(2), 359-380.

Yli-Renko, H., Autio, E., & Sapienza, H. J. (2001). Social capital, knowledge acquisition, and knowledge exploitation in young technology-based firms. Strategic Management Journal, 22(6-7), 587-613. doi:10.1002/smj.183

Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A review and recommendations. The Leadership Quarterly, 21(6), 1086-1120. doi:10.1016/j.leaqua.2010.10.010

Instructions

Read the listed material and answer the questions below.

You can skim through the non-methodological parts of the two empirical papers. The versions available in the course Zotero library contain highlighted sections that are discussed in class. Note that both empirical papers are used in multiple classes so not all highlighted sections are discussed in the next class.

Questions

1) Chang and Cartwright explain that two broad perspectives on measurement are nominalism and realism. Explain these two perspectives. Devellis uses the terms scale and index. How do these two terms relate to nominalism and realism? Does Yli-Renko et al use scales or indices and do they follow nominalism or realism or a mix of these? Justify your answer.

2) Yli-Renko et al. report that they "used previously validated measurement items wherever possible". (p.598) a) Out of the five constructs that were measured with multiple items, which items had and which had not been previously validated as measures of those constructs? Note that the fact that Yli-Renko et al report that the scales were based on prior research does not necessarily mean that those same items were used or even if they were that they were validated. b) Focus on the construct "relationship quality" indicators: How these items were generated and what validity evidence has been presented for these indicators in previous studies? When answering the part b of this question, also check how these earlier versions of the Yli-Renko et al report the "relationship quality" indicators:

Autio, E. (2000). Learning processes in high-technology clusters (Helsinki University of Technology Institute of Strategy and International Business Working Paper Series No. 5).

Yli-Renko, H., Autio, E., Sapienza, H. J., & Hay, M. J. (1999). Social Capital, Relational Learning, and Knowledge Distinctiveness in Technology-Based New Firms. In Frontiers of Entrepreneurship Research. Retrieved from http://fusionmx.babson.edu/entrep/fer/papers99/XXVIII/XXVIII_D/XXVIII_D%20Text.htm

3) What are the consequences of measurement error in a) independent and b) dependent variables for regression results. How Wooldridge and Antonakis et al. suggest that researchers should deal with measurement error in their models?

Submit your answers two days before the lecture and bring them also to the lecture. The answer should be 3-6 pages. If you have done this assignment as a part of a previous attempt at this course, you can use your old answer as a starting point and do a revision. If you need help or have questions about the assignment, please post those to the course forum.