Distribution of the biased hypothesis sum of squares in linear models with missing observations

In a linear model with missing observations, one can substitute algebraic quantities and then minimize the error sum of squares for the augmented model. This gives the correct error sum of squares. But this method does not produce the correct hypothesis sum of squares for testing a linear hypothesis about the parameters. The sum of squares obtained is biased but practitioners still use it. The distribution of this biased sum of squares is derived in this paper and the consequences of using this biased sum of squares on the type I and II errors is examined.     

Missing plot technique in linear models

This paper extends the missing plot substitution technique to the case where the missing observations-cause some previously estimable functions to become non-estimable. It is shown that with appropriate modifications, the usual methods of analysis remain valid. We also obtain necessary and sufficient conditions under which the sum of squares due to a hypothesis can be calculated without “re-estimating” the missing observations     

A functional central limit theorem for the quadratic variation of a class of gaussian random fields

We prove a central limit theorem for the quadratic variation process of some Lévy-Baxter-type Gaussian random fields.     

Exploring the influence of pre-training factors on training effectiveness-moderating role of trainees’ reaction: a study in the public sector in India

Organizations invest in training initiative with an objective to improve the performance of its employees and ultimately organizational performance. However, training literature highlights the gap between the learning and the transfer of learning at the workplace. Thus, there is a need to have a deeper understanding of those variables which contributes to training transfer/effectiveness. This study is an attempt to understand those organizational factors that can help in improving training effectiveness. Data was collected at three different points of time (before training, immediately at the end of training and after some time of training) to determine the antecedents of motivation to learn and the training effectiveness. Findings of the study reveal that motivation to learn mediates the relationship between the predictor variables – training needs analysis, training information and type of training, and the resultant variable training effectiveness. Also, trainees’ reaction towards training was found to moderate the relationship between trainees’ motivation to learn and training effectiveness. The study reinforces the significance of organizational factors in ensuring motivation to learn and training effectiveness. Theoretical and managerial implications are discussed in the paper.     

An Experimental Analysis of Capacity-Sensitive Setup Parameters for MRP Lot Sizing

Most material requirements planning (MRP) systems apply standard costing (absorption costing) approaches to define setup costs that are used as fixed (time invariant) setup parameters in single-level lot-sizing methods. This paper presents a computationally simple approach for estimating more appropriate setup parameters based on estimates of work-center shadow prices. These setup parameters then are used in traditional single-level MRP lot-sizing procedures. The shadow price of capacity at each work center is calculated as the increase in the overall inventory carrying cost for each additional hour of capacity lost to setups. The opportunity cost of a setup for an order subsequently is determined based on the routing information for each order and is used by traditional MRP lot-sizing procedures to calculate lot sizes. A simulation experiment compares the performance period order quantity lot sizing with capacity-sensitive setup parameters with the fixed accounting-based setup parameters. The simulation replicates the planning and control functions of a typical MRP system. The results of the experiment show that capacity-sensitive setup parameters can make significant reductions in both carrying cost and lateness and can achieve many of the benefits of optimized production technology in the context of an MRP system.     

On consequences of one missing observation in a balanced design

It is shown that the C-matrix of a balanced design commutes with the C-matrix of a design resulting from this balanced design because of one missing observation. This commutativity leads us to a simple test procedure for testing equality of treatment effects.     

Long memory in intertrade durations,counts and realized volatility of NYSE stocks

We study the persistence of intertrade durations, counts (number of transactions in equally spaced intervals of clock time), squared returns and realized volatility in 10 stocks trading on the New York Stock Exchange. A semiparametric analysis reveals the presence of long memory in all of these series, with potentially the same memory parameter. We introduce a parametric latent-variable long-memory stochastic duration (LMSD) model which is shown to better fit the data than the autoregressive conditional duration model (ACD) in a variety of ways. The empirical evidence we present here is in agreement with theoretical results on the propagation of memory from durations to counts and realized volatility presented in Deo et al. (2009).