Quantifying Qualitative Survey Data with Panel Data Structure

Abstract

We develop a novel methodology to quantify forecasts based on qualitative survey data. The methodology is generally applicable when quantitative information is available on the realization of the forecasted variable, for example from firm balance sheets. The method can be applied to a wide range of panel datasets, including qualitative surveys on firm-level forecasts or household expectations. As an application, we employ a panel of Greek manufacturing firms and quantify firms' forecast errors of own sales growth. In this context, we conduct a variety of exercises to demonstrate the methodology's validity and accuracy.