The EM Approach to the Multiple Indicators and Multiple Causes Model Via the Estimation of the Latent Variable

Chen, Chan-fu

doi:10.2307/2287534

Cited by 16 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For data from exponential families, it is particularly easy to implement, and has been used for the static MIMIC model by Chen (1981). In a time series context Watson (1981) has shown how it can be used to obtain exact maximum likelihood estimates for the moving average model.…”

Section: Estimation By the Em Algorithmmentioning

confidence: 99%

Alternative algorithms for the estimation of dynamic factor, mimic and varying coefficient regression models

Watson

Engle

1983

Journal of Econometrics

408

268

View full text Add to dashboard Cite

This paper provides a general approach to the formulation and estimation of dynamic unobserved component models. After introducing the general model, two methods for estimating the unknown parameters are presented. Both are algorithms for maximizing the likelihood function. The first is based on the method of Scoring. The second is the EM algorithm, a derivative-free method. Each iteration of EM requires a Kalman filter and smoother followed by straightforward regression calculations. The paper suggests using the EM methods to quickly locate a neighborhood of the maximum. Scoring can then be used-to calculate the information matrix.pinpoint the maximum and

show abstract

Section: Estimation By the Em Algorithmmentioning

confidence: 99%

Alternative algorithms for the estimation of dynamic factor, mimic and varying coefficient regression models

Watson

Engle

1983

Journal of Econometrics

408

268

View full text Add to dashboard Cite

show abstract

“…The EM algorithm was introduced by Baum et al (1970) for Hidden Markov Models and it was generalized for models with incomplete observations in Dempster et al (1977). The EM algorithm with Kalman filter was applied for estimation of linear dynamics system for the first time in Chen (1981) and Shumway and Stoffer (1982).…”

Section: Estimation: the Expectation-maximization Algorithmmentioning

confidence: 99%

Co-existence of trend and value in financial markets: Estimating an extended Chiarella model

Majewski

Ciliberti

Bouchaud

2020

Journal of Economic Dynamics and Control

View full text Add to dashboard Cite

Trend and Value are pervasive anomalies, common to all financial markets. We address the problem of their co-existence and interaction within the framework of Heterogeneous Agent Based Models (HABM). More specifically, we extend the Chiarella (1992) model by adding noise traders and a non-linear demand of fundamentalists. We use Bayesian filtering techniques to calibrate the model on time series of prices across a variety of asset classes since 1800. The fundamental value is an output of the calibration, and does not require the use of an external pricing model. Our extended model reproduces many empirical observations, including the non-monotonic relation between past trends and future returns. The destabilizing activity of trend-followers leads to a qualitative change of mispricing distribution, from unimodal to bimodal, meaning that some markets tend to be over-(or under-) valued for long periods of time.

show abstract

“…Comparision of our model's performance with that of standard models used in direct marketing, such as logistic regression and RFM, unfortunately lies beyond the scope of our paper; it might, however, be an interesting avenue for further research. A natural predictor of h given the observables x and y is its expectation conditional on x and y (see Chen (1981) ¼ Px þ C*L 0 y þ L y C*L 0 y þ Q 1 h i 21 y 2 L y P x Â Ã :…”

Section: Limitations and Future Studymentioning

confidence: 99%

Identifying the direct mail-prone consumer

Leeflang

Spring

Doorn

et al. 2013

Journal of Global Scholars of Marketing Science

View full text Add to dashboard Cite

Current modeling research in target marketing usually stresses the identification of profitable names for specific mailings. There is little recent research about the characteristics of typical direct mail (DM) customers. In this paper we determine the link between customers' socio-demographic characteristics and their propensity to purchase products through the mail. We hypothesize the existence of a latent variable, DMproneness, which represents a consumer's tendency to shop via direct mail. Our model links the socio-demographics of customers to their self-reported purchase behavior through the latent variable of DM-proneness in a Multiple Indicators and Multiple Causes (MIMIC) model. We also introduce a second latent variable, DM information interest, which represents the desire to receive direct offers through the mail. The model allows for testing the influence of DM information interest on DM-proneness. We fit the model to actual consumer data using the LISREL program. The findings show that the characteristics of the DM-prone and the DM information-interested are similar, and that DM information interest appears to directly affect DM-proneness. The DM-prone consumer is identified as relatively younger, with somewhat lower education, rather welloff, from a relatively large family, and relatively more likely to have a female head of the household. We also show that consumers' tendency to shop via direct mail can be captured by a latent variable approach, and that DM-proneness can be quite well predicted by demographic consumer characteristics.

show abstract

The EM Approach to the Multiple Indicators and Multiple Causes Model Via the Estimation of the Latent Variable

Cited by 16 publications

References 0 publications

Alternative algorithms for the estimation of dynamic factor, mimic and varying coefficient regression models

Alternative algorithms for the estimation of dynamic factor, mimic and varying coefficient regression models

Co-existence of trend and value in financial markets: Estimating an extended Chiarella model

Identifying the direct mail-prone consumer

Contact Info

Product

Resources

About