Browsing by Author "Modarres-Mousavi, Shabnam"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Methodological Foundations for Bounded Rationality as a Primary Framework
    Modarres-Mousavi, Shabnam (Virginia Tech, 2002-10-22)
    Experimental observations have shown that economic agents behave in ways different from the maximization of any utility function. Herbert Simon sought to deal with this by positing that individuals do not maximize, but rather "satisfice." This was a radical departure from the traditional economic framework, and one that still has not been adequately formalized. But Simon's suggestion is only the smallest part of what is needed for a theory that reflects the actual behavior. For instance, Simon's framework cannot deal with the observation that the act of choice changes the chooser. This dissertation is further developing Simon's original ideas through embracing John Dewey's transactional thinking to attain an adequate theory of economic choice that accounts for boundedly rational agents. I clarify that substantive rationality and bounded (procedural) rationality share the same basic utilitarian assumption of predetermined goals. In terms of a Deweyan (transactional) analysis, the idea of utilitarian "optimization" ultimately guides and constrains both theories. But empirical study of choice behavior and the behavior of subjects in experimental laboratories, both indicate that neither substantive nor procedural rationality can effectively account for actual economic choices. I emphasize the importance of treating bounded rationality without reference to the rational framework. To me, bounded rationality implies a realistic picture of behavior, which is associated with emerging goals and not ones that exist prior to the making of a choice. I consider uncertainty as a normal characteristic of the situation, which in turn allows consideration of acting based on inconsistent information, just as people actually do. The basis of a systematic approach to behavior that can capture inconsistency is developed by Tom Burke. He mathematizes Dewey's logic. He allows for impossible worlds in the set of states. Thus, not only can the initial state space hold inconsistent states, the information set can include mutually inconsistent elements. So the current neoclassical paradigm resembles the representative realism, but is there any good reason why we should accept this methodology as economists? Whatever one's ultimate metaphysics and epistemology, I want to show that an alternative approach to economic decision-making may prove highly useful in theory and practice.
  • Thumbnail Image
    Monitoring Markov Dependent Binary Observations with a Log-Likelihood Ratio Based CUSUM Control Chart
    Modarres-Mousavi, Shabnam (Virginia Tech, 2006-01-17)
    Our objective is to monitor the changes in a proportion with correlated binary observations. All of the published work on this subject used the first-order Markov chain model for the data. Increasing the order of dependence above one by extending a standard Markov chain model entails an exponential increase of both the number of parameters and the dimension of the transition probability matrix. In this dissertation, we develop a particular Markov chain structure, the Multilevel Model (MLM), to model the correlation between binary data. The basic idea is to assign a lower probability to observing a 1 when all previous correlated observations are 0's, and a higher probability to observing a 1 as the last observed 1 gets closer to the current observation. We refer to each of the distinct situations of observing a 1 as a "level". For a given order of dependence, , at most different values of conditional probabilities of observing a 1 can be assigned. So the number of levels is always less than or equal to . Compared to a direct extension of the first-order Markov model to higher orders, our model is considerably parsimonious. The number of parameters for the MLM is only one plus the number of levels, and the transition probability matrix is . We construct a CUSUM control chart for monitoring a proportion with correlated binary observations. First, we use the probability structure of a first-order Markov chain to derive a log-likelihood ratio based CUSUM control statistic. Then, we model this CUSUM statistic itself as a Markov chain, which in turn allows for designing a control chart with specified statistical properties: the Markov Binary CUSUM (MBCUSUM) chart. We generalize the MBCUSUM to account for any order of dependence between binary observations through implying MLM to the data and to our CUSUM control statistic. We verify that the MBCUSUM has a better performance than a curtailed Shewhart chart. Also, we show that except for extremely large changes in the proportion (of interest) the MBCUSUM control chart detects the changes faster than the Bernoulli CUSUM control chart, which is designed for independent observations.