W pracy przedstawione są różne metody podejścia do problemów braków odpowiedzi w przypadku badań koniunktury. Zaproponowane są ważone metody szacowania statystyki bilansowej dla badanych cech oraz metody imputacji danych. Analiza empiryczna oparta jest na Badaniu Koniunktury w Przemyśle prowadzonym przez Instytut Rozwoju Gospodarczego SGH. Badania koniunktury w przemyśle, prowadzone w celu uzyskania informacji o stanie gospodarki, mają kluczowe znaczenie dla praktyki ekonomicznej i stanowią podstawę wielu empirycznych analiz ekonomicznych.
Most tendency surveys are organized to be based on a fixed sample of units across time. This fixed panel constitutes a designed sample. But in practice the resulting sample always differs from the designed one, sometimes quite considerably. In tendency surveys, like in all real surveys, some sampled units refuse to participate, some agree to cooperate but forgo several periods later, some respond irregularly. Consequently, the resulting samples across time never constitute a perfect panel, they form an overlapping sample pattern. In the paper we propose a formula for adjusted balance statistics that takes into account distortion of a sample. The main idea of adjusted balance statistics is analogous to estimators known from statistical overlapping samples theory. Theoretical part of the paper is extended by empirical analysis of monthly business tendency survey data. In particular, the response pattern is studied and comparison of original and adjusted balance statistics is conducted.
W artykule przeanalizowano wpływ metod ważenia na własności szeregów czasowych statystyk bilansowych otrzymanych na podstawie badania koniunktury w przemyśle prowadzonego przez IRG SGH. Analizie poddano wszystkie zmienne o trzech wariantach odpowiedzi testowane w badaniu IRG z częstotliwością miesięczną. W przypadku każdego z szeregów przedmiotem analiz był zarówno raportowany stan obecny, jak i prognozy. Zbadano m. in. statystyki opisowe, punkty zwrotne oraz stacjonarność otrzymanych różnymi metodami szeregów sald. Otrzymane wyniki wskazują, że wnioski, jakich dostarcza analiza szeregów uzyskanych różnymi metodami są zbieżne. Przeprowadzone na szerokim zbiorze zmiennych badanie pozwala na stwierdzenie adekwatności zastosowanych przez IRG metod ważenia szeregów, pomimo arbitralności stosowanych wag.
EN
The article examines the impact of weighting methods on the properties of balance series obtained on the basis of business tendency surveys, conducted by RIED WSE. We analyzed all variables with three available variants of answers which are tested in the RIED survey regularly every month. For each variable, both state and expectations were studied. We analyzed, among others, descriptive statistics, turning points and stationarity of the obtained by different methods series. The conclusions that could be drawn from the analysis of balance series obtained with the use of different methods coincide. The analysis that has been carried out with the use of a broad set of variables allows to conclude that despite the arbitrary weights used, series provided by RIED WSE are adequate. Key words: weighting methods, sample structure, tendency surveys, turning points, stationarity, KPSS test.
Rationality of economic agents belongs to the basic assumptions of neoclassical economic theory, and for decades it has inspired research on whether expectations are indeed formed rationally. Direct data on expectations are available mainly through business tendency surveys which are subject to various types of non-response problems. Inclination of industrial enterprises to respond may be correlated with values of measured variable, introducing response bias. Response bias may also occur as a result of introducing weighting systems to control variable size of respondents. The two key properties of rational expectations, on which the majority of empirical analyses of survey data are focused, are unbiasedness and orthogonality. We analyze several sample balance statistics and expectations series based on quantified survey data, taking into consideration issues of non-response and weighting schemes. Alternative definitions of expectations series aim to account for: 1) influence of arbitrary assumptions concerning weighting of individual data, 2) changing sample structure that results from non-response, 3) response rates varying with degree of optimism / pessimism of respondents. Results of our analysis indicate that expectations concerning relative changes in production are unbiased but not efficient with respect to freely available information, namely, observed relative changes in production (lagged three months) and expectations balance (lagged two months). This result holds for a range of weighting schemes and non-response issues analyzed, including changes introduced to sample structure by non-response, and increased inclination of “optimists” and “pessimists” to supply answers in the business tendency survey, as long as their shares remain constant in time.
Sensitive attributes are extremely difficult to be measured directly. Recently new indirect methods of questioning, called Poisson and negative binomial item count techniques, have been proposed by [Tian et al. 2014]. This paper focuses on important problem of comparing proportions of sensitive items in two populations when using new indirect method. Proper statistical theory is introduced, including tests for equality of two sensitive proportions followed by derivation of their asymptotic power functions. Simulation studies are conducted to illustrate the problem.