Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 2

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  OLS regression
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
EN
One of the key problems of many sociological regression models is their modest explanatory power. This has not only to do with the insufficient development of the underlying theories but also with the free will of the concerned social actors, which manifests itself in irrational, spontaneous, and sometimes even arbitrary decisions. The foreign and economic policy of the US government under Donald Trump is an excellent example of this source of indeterminacy. An alternative and more promising approach is an explanation of the constraints of social behaviour by the unequal distribution of power resources and the competing interests of the actors concerned. This approach requires, on the one hand, enough observational data which include cases that reached the analysed constraints. On the other hand, there is a need for statistical procedures which estimate and explain these constraints. Assuming that sufficient amounts of data are available, this paper proposes the use of sequential OLS regressions, which eliminate step by step non-critical observations in order to identify the cases that reached the mentioned constraints. For illustrative purposes, the author analyses the policy space of anti-democratic regimes with regard to their possibilities of curbing democracy. On the basis of the democracy scores of Freedom House, the author explores the governmental constraints set by (i) national civil societies and (ii) international NGOs for the promotion of political/civil rights. The related sequential regressions allow for an assessment of how effective the different constraints are and how far democracy may deteriorate in the worst case under given structural conditions.
EN
This paper examines the relationship between stock return and human behavior in ten well-established stock exchanges, from a monthly data sample from January 1991 to December 2015. The results show that there is no sufficient evidence to generalize the impact of human behaviour on common stock return, through mood state altered by weather variables. When the substance of the underlying process (i.e. the weather alters the mood state) is established by logit regression, the results reveal that there is a bias in the variable selection as regressors, which is subject to the metrological situation of each country (or region). As such, collectivism does not appear to be an explanatory variable of the magnitude of price changes, as a variable uncontrolled for in the regression. Although the null hypothesis is accepted for four countries in the sample, the findings do not warrant researchers to generalize the effect of human behavior on stock price changes through weather variables, for a large population.
PL
W tym artykule zbadano związek między zwrotem z akcji a ludzkim zachowaniem na przykładzie dziesięciu uznanych giełd, opierając się na miesięcznej próbce danych z okresu od stycznia 1991 r. do grudnia 2015 r. Wyniki pokazują, że nie ma wystarczających dowodów, aby uogólnić wpływ ludzkich zachowań wywołanych zmiennymi warunkami pogodowymi na zwrot z akcji zwykłych. Gdy zasada leżąca u podstaw procesu (tzn. pogoda zmienia stan nastroju) jest ustalana przez regresję logitów, wyniki ujawniają, że w wyborze zmiennych jako regresorów występuje nastawienie zależne od sytuacji metrologicznej każdego z krajów (lub regionów). Kolektywizm jako taki nie wydaje się zmienną wyjaśniającą wielkość zmian cen jako zmienną niekontrolowaną w regresji. Chociaż hipoteza zerowa w badanej próbie została przyjęta dla czterech krajów, odkrycia te nie upoważniają badaczy do uogólnienia wpływu ludzkich zachowań na zmiany cen akcji przez zmienne pogodowe, dla dużej populacji.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.