This paper presents maximum score type estimators for linear, binomial, tobit and truncated regression models. These estimators estimate the normalized vector of slopes and do not provide the estimator of intercept, although it may appear in the model. Strong consistency is proved. In addition, in the case of truncated and tobit regression models, maximum score estimators allow restriction of the sample in order to make ordinary least squares method consistent.

The swap spread is defined as the difference between the fixed rate of an interest rate swap and the yield of the treasury with the same maturity. The swap spread is usually interpreted as the effective proxy of bank liquidity and the credit spread indicator. The interpretation is very similar to the LIBOR-OIS spread and in the context of Polish interbank market – WIBOR-OIS. However, WIBOR-OIS is less reliable during the crisis of confidence because of lack of interbank operation with the maturity longer than 1 month. Swap spreads base on two liquid instruments, thus they are free of this defect.

The main goal of this paper is to assess how Polish swap spreads and their conditional variance reacted to important events connected with the subprime crisis and crisis of confidence in the Polish interbank market.