Efficient Parameter Estimation For Semi-Continuous Data: An Application To Independent Component Analysis

Popuri, Sai K.; Boukouvalas, Zois

doi:10.1109/mlsp.2019.8918850

“…In the statistics literature, this is often referred to as semicontinuous data. Statistical methods for semicontinuous data were considered as early as 1955 by [1] and have been developed through applications such as health sciences and services [27,28,34,37], nutrition [18,19,30,38,41,42], manufacturing [20], economics [7], and climate science [32].…”

Section: Measurement Error Model (Mem)mentioning

confidence: 99%

The relationship between moderate to vigorous physical activity and metabolic syndrome: a Bayesian measurement error approach

Ries

¹

,

Carriquiry

²

2022

Journal of Applied Statistics

0

View full text Add to dashboard Cite

“…For example, Papalexiou and Koutsoyiannis (2012) have focused on the MaxEnt solution of the continuous part alone and explored various distributions including a generalized gamma distribution, generalized beta distribution etc with applications for the daily rainfall data. More recently, Popuri and Boukouvalas (2019) too set the probability of observing a zero to the sample value and apply the entropy maximization method to the blind source separation problem for semi-continuous data. Notice that while fixing γ * to sample values will simplify the problem, the resulting solution is not the MaxEnt distribution.…”

Section: H(γ)mentioning

confidence: 99%

Density estimation using entropy maximization for semi-continuous data

Popuri¹,

Neerchal

²

,

Mehta

³

et al. 2021

Digital Signal Processing

Self Cite

2

0

View full text Add to dashboard Cite

Semi-continuous data comes from a distribution that is a mixture of the point mass at zero and a continuous distribution with support on the positive real line. A clear example is the daily rainfall data. In this paper, we present a novel algorithm to estimate the density function for semi-continuous data using the principle of maximum entropy. Unlike existing methods in the literature, our algorithm needs only the sample values of the constraint functions in the entropy maximization problem and does not need the entire sample. Using simulations, we show that the estimate of the entropy produced by our algorithm has significantly less bias compared to existing methods. An application to the daily rainfall data is provided.

show abstract

“…For example, Papalexiou and Koutsoyiannis (2012) have focused on the MaxEnt solution of the continuous part alone and explored various distributions including a generalized gamma distribution, generalized beta distribution etc with applications for the daily rainfall data. More recently, Popuri and Boukouvalas (2019) too set the probability of observing a zero to the sample value and apply the entropy maximization method to the blind source separation problem for semi-continuous data. Notice that while fixing γ * to sample values will simplify the problem, the resulting solution is not the MaxEnt distribution.…”

Section: An Alternating Entropy Maximization Algorithm For Semi-conti...mentioning

confidence: 99%

Density Estimation using Entropy Maximization for Semi-continuous Data

Popuri¹,

Neerchal²,

Mehta³

et al. 2020

Preprint

Self Cite

0

View full text Add to dashboard Cite

Semi-continuous data comes from a distribution that is a mixture of the point mass at zero and a continuous distribution with support on the positive real line. A clear example is the daily rainfall data. In this paper, we present a novel algorithm to estimate the density function for semi-continuous data using the principle of maximum entropy. Unlike existing methods in the literature, our algorithm needs only the sample values of the constraint functions in the entropy maximization problem and does not need the entire sample. Using simulations, we show that the estimate of the entropy produced by our algorithm has significantly less bias compared to existing methods. An application to the daily rainfall data is provided.

show abstract

Efficient Parameter Estimation For Semi-Continuous Data: An Application To Independent Component Analysis

Cited by 3 publications

References 17 publications

The relationship between moderate to vigorous physical activity and metabolic syndrome: a Bayesian measurement error approach

The relationship between moderate to vigorous physical activity and metabolic syndrome: a Bayesian measurement error approach

Density estimation using entropy maximization for semi-continuous data

Density Estimation using Entropy Maximization for Semi-continuous Data

Contact Info

Product

Resources

About