General overview: The
course discusses the problem of measurement errors in survey. It will show the
consequences of the errors in the results of the research. It will also be
shown how large the differences are in results assuming perfect measurement and
taking into account the fact that there are measurement errors.

This requires, of course, that we are able to estimate or predict the quality
of survey questions. In this course two approaches will be discussed. The first
is the estimation of the reliability and validity of questions using
multitrait-multimethod matrix (MTMM) experiments. The second is the prediction
of the reliability and validity of questions using the program SQP 2.0.

It will be shown how this information
can be used for improvement of questions before they are used in the field and
for the correction of measurement errors in the analysis of the relationships
between variables.

About the trainer: Dr. Armine Petrossian received her education from Yerevan, Novosibirsk
and Moscow universities. She holds a PhD degree in Economics from Moscow
Institute of Econometrics and MA Political Science from the American University
of Armenia. Her professional carrier includes years of leadership positions in
the Armenian government during the 1990s, plus a number of US and European
projects in development, democracy, civil society, good governance,
institutional reform, public relations, municipal service. Armine is now the
Program Manager for Data Initiative and Methodological Training at Caucasus
Research Resource Centers – Armenia.