Valerie Poynor | California State University, Fullerton (original) (raw)

Papers by Valerie Poynor

arXiv (Cornell University), Nov 27, 2014

The mean residual life function is a key functional for a survival distribution. It has a practic... more The mean residual life function is a key functional for a survival distribution. It has a practically useful interpretation as the expected remaining lifetime given survival up to a particular time point, and it also characterizes the survival distribution. However, it has received limited attention in terms of inference methods under a probabilistic modeling framework. We seek to provide general inference methodology for mean residual life regression. Survival data often include a set of predictor variables for the survival response distribution, and in many cases it is natural to include the covariates as random variables into the modeling. We thus employ Dirichlet process mixture modeling for the joint stochastic mechanism of the covariates and survival responses. This approach implies a flexible model structure for the mean residual life of the conditional response distribution, allowing general shapes for mean residual life as a function of covariates given a specific time point, as well as a function of time given particular values of the covariate vector. To expand the scope of the modeling framework, we extend the mixture model to incorporate dependence across experimental groups, such as treatment and control groups. This extension is built from a dependent Dirichlet process prior for the group-specific mixing distributions, with common locations and weights that vary across groups through latent bivariate Beta distributed random variables. We develop properties of the regression models, and discuss methods for prior specification and posterior inference. The different components of the methodology are illustrated 1

Ecological Complexity, Dec 1, 2017

As a consequence of the complexity of ecosystems and context-dependence of species interactions, ... more As a consequence of the complexity of ecosystems and context-dependence of species interactions, structural uncertainty is pervasive in ecological modeling. This is particularly problematic when ecological models are used to make conservation and management plans whose outcomes may depend strongly on model formulation. Nonlinear time series approaches allow us to circumvent this issue by using the observed dynamics of the system to guide policy development. However, these methods typically require long time series from stationary systems, which are rarely available in ecological settings. Here we present a Bayesian approach to nonlinear forecasting based on Gaussian processes that readily integrates information from several short time series and allows for nonstationary dynamics. We demonstrate the utility of our modeling methods on simulated from a wide range of ecological scenarios. We expect that these models will extend the range of ecological systems to which nonlinear forecasting methods can be usefully applied.

Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival t... more Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival times of patients with small cell lung cancer 2.

Cancer Epidemiology, Biomarkers & Prevention, 2023

Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in ... more Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in 2019. Since this number is projected to increase to over 22 million by 2030 and cancer survivors often face long-term challenges and late effects of treatment, it has become increasingly important to evaluate patients’ health-related quality of life in order to better understand their needs, identify disparities, and develop strategies to improve their overall well-being. Racial/ethnic differences in cancer survivorship have been previously reported, but few have evaluated quality of life among a nationally representative, population-based sample of U.S. patients. Methods: We used self-reported data from the Medical Expenditure Panel Survey (MEPS) as well as its Experience with Cancer Survivorship Supplement questionnaire from 2016-17, which collected information on patient experiences with cancer including quality of life based on the Patient-Reported Outcomes Measurement Information System (PROMIS) measures of physical and mental health. A Global Physical Health (GPH) score using questions related to physical health, physical function, fatigue, and pain and a Global Mental Health (GMH) score using questions related to quality of life, mental health, social support, and emotional problems were calculated where the lower the score indicated the poorer the health. In addition, questions related to whether cancer had a positive impact on patients were considered as well. Multiple logistic regression models with odds ratios (ORs) and 95% confidence intervals (CIs) were used to examine the impact of race on these various quality of life/cancer experience outcomes after considering relevant confounders. Results: A total of 1608 cancer survivors (1225 non-Hispanic Whites, 165 Hispanic Whites, 176 Blacks, 42 Asians) were included. When compared to non-Hispanic Whites, only Blacks were statistically significantly more likely to have a low GPH score (OR=1.95, 95% CI 1.15-3.27) and a low GMH score (OR=1.89, 95% CI 1.24-2.89). However, Blacks and Hispanic Whites were statistically significantly more likely to report their cancer experience leading to positive things in their lives; for example, both racial groups were three times as likely to report that their cancer helped them cope better with life’s challenges relative to non-Hispanic Whites (OR=3.66, 95% CI 2.34-5.73 for Blacks, OR=2.91, 95% CI 1.68-5.03 for Hispanic Whites). Conclusions: There are important racial disparities when it comes to health-related quality of life among cancer survivors. Although Blacks were more likely to see the positive aspects of their cancer diagnosis, they still experienced poorer physical and mental health overall. Future studies should explore the factors that may be contributing to these racial disparities as they could greatly inform targeted strategies to improve the overall survivorship experience of cancer patients. Citation Format: Alice W. Lee, Valerie Poynor, JinKyu Choi. Racial disparities in health-related quality of life among cancer survivors in the United States [abstract]. In: Proceedings of the 15th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2022 Sep 16-19; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2022;31(1 Suppl):Abstract nr A038.

The mean residual life function is a key functional for a survival distribution. It has a practic... more The mean residual life function is a key functional for a survival distribution. It has a practically useful interpretation as the expected remaining lifetime given survival up to a particular time point, and it also characterizes the survival distribution. However, it has received limited attention in terms of inference methods under a probabilistic modeling framework. We seek to provide general inference methodology for mean residual life regression. Survival data often include a set of predictor variables for the survival response distribution, and in many cases it is natural to include the covariates as random variables into the modeling. We thus employ Dirichlet process mixture modeling for the joint stochastic mechanism of the covariates and survival responses. This approach implies a flexible model structure for the mean residual life of the conditional response distribution, allowing general shapes for mean residual life as a function of covariates given a specific time poin...

Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival t... more Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival times of patients with small cell lung cancer 2.

Cancer Epidemiology, Biomarkers & Prevention

Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in ... more Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in 2019. Since this number is projected to increase to over 22 million by 2030 and cancer survivors often face long-term challenges and late effects of treatment, it has become increasingly important to evaluate patients’ health-related quality of life in order to better understand their needs, identify disparities, and develop strategies to improve their overall well-being. Racial/ethnic differences in cancer survivorship have been previously reported, but few have evaluated quality of life among a nationally representative, population-based sample of U.S. patients. Methods: We used self-reported data from the Medical Expenditure Panel Survey (MEPS) as well as its Experience with Cancer Survivorship Supplement questionnaire from 2016-17, which collected information on patient experiences with cancer including quality of life based on the Patient-Reported Outcomes Measurement Information Sy...

These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 19... more These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 1994). The patients were randomly assigned to one of two treatments referred to as Arm A and Arm B. Arm A patients received cisplatin (P) followed by etoposide (E), while Arm B patients received (E) followed by (P). There were a total of 62 patients in Arm A with 15 right censored survival times, while Arm B consisted of 59 patients with 8 right censored survival times.<br><br>The variables recorded in the dataset(s) are:<br>- age: age of the patient upon entry (in years)<br>- time: survival time of the patient (in days)<br>- cens: indicator for survival time - 0 if observed, 1 if right censored<br><br>We analyze these data using a Dirichlet Process Mixture Model with a Gamma kernel distribution (Poynor and Kottas, 2017). The primary emphasis of our work is to obtain inference for the mean residual life function. Our code is shared through github (...

These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 19... more These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 1994). The patients were randomly assigned to one of two treatments referred to as Arm A and Arm B. Arm A patients received cisplatin (P) followed by etoposide (E), while Arm B patients received (E) followed by (P). There were a total of 62 patients in Arm A with 15 right censored survival times, while Arm B consisted of 59 patients with 8 right censored survival times.<br><br>The variables recorded in the dataset(s) are:<br>- age: age of the patient upon entry (in years)<br>- time: survival time of the patient (in days)<br>- cens: indicator for survival time - 0 if observed, 1 if right censored<br><br>We analyze these data using a Dirichlet Process Mixture Model with a Gamma kernel distribution (Poynor and Kottas, 2017). The primary emphasis of our work is to obtain inference for the mean residual life function. Our code is shared through github (...

Nutrition and Cancer, 2022

Phytoestrogens are plant-derived compounds that are structurally similar to endogenous estrogens.... more Phytoestrogens are plant-derived compounds that are structurally similar to endogenous estrogens. Studies have shown phytoestrogens to have possible health benefits although they could also act as endocrine disruptors. This is particularly relevant for estrogen-dependent cancers since estrogens increase risk of breast, endometrial, and ovarian cancer. Using data from the National Health and Nutritional Examination Survey (NHANES), we assessed the associations between urinary phytoestrogens (daidzein, equol, o-Desmethylangolensin (O-DMA), genistein, enterodiol, enterolactone) and breast, endometrial, and ovarian cancer using multivariate logistic regression with odds ratios (ORs) and 95% confidence intervals (CIs). Cancer diagnosis and other characteristics were collected via in-person questionnaires. We found women in the highest tertile for daidzein and enterodiol had over twice the odds of having breast cancer (OR = 2.51, 95% CI 1.44-4.36 for daidzein, OR = 2.78, 95% CI 1.44-5.37 for enterodiol). In addition, women in the highest tertiles for daidzein and genistein had three to four times the odds of having endometrial cancer, respectively (OR = 3.09, 95% CI 1.01-9.49 for daidzein, OR = 4.00, 95% CI 1.38-11.59 for genistein). Overall, phytoestrogens were positively associated with breast and endometrial cancer although the associations varied by phytoestrogen type. Additional studies are needed to further inform phytoestrogens' role in disease etiology.Supplemental data for this article is available online at at https://doi.org/10.1080/01635581.2021.2020304.

Nutrients, 2020

A multitude of dietary factors from dietary fat to macro and micronutrients intakes have been ass... more A multitude of dietary factors from dietary fat to macro and micronutrients intakes have been associated with breast cancer, yet data are still equivocal. Therefore, utilizing data from the large, multi-year, cross-sectional National Health and Nutrition Examination Survey (NHANES), we applied a novel, modern statistical shrinkage technique, logistic least absolute shrinkage and selection operator (LASSO) regression, to examine the association between dietary intakes in women, ≥50 years, with self-reported breast cancer (n = 286) compared with women without self-reported breast cancer (1144) from the 1999–2010 NHANES cycle. Logistic LASSO regression was used to examine the relationship between twenty-nine variables, including dietary variables from food, as well as well-established/known breast cancer risk factors, and to subsequently identify the most relevant variables associated with self-reported breast cancer. We observed that as the penalty factor (λ) increased in the logistic...

Environmental and Ecological Statistics, 2017

Gaussian process models have been used in applications ranging from machine learning to fisheries... more Gaussian process models have been used in applications ranging from machine learning to fisheries management. In the Bayesian framework, the Gaussian process is used as a prior for unknown functions, allowing the data to drive the relationship between inputs and outputs. In our research, we consider a scenario in which response and input data are available from several similar, but not necessarily identical, sources. When little information is known about one or more of the populations it may be advantageous to model all populations together. We present a hierarchical Gaussian process model with a structure that allows distinct features for each source as well as shared underlying characteristics. Key features and properties of the model are discussed and demonstrated in a number of simulation examples. The model is then applied to a data set consisting of three populations of Rotifer Brachionus calyciflorus Pallas. Specifically, we model the log growth rate of the populations using a combination of lagged population sizes. The various lag combinations are formally compared to obtain the best model inputs. We then formally compare the leading hierarchical Gaussian process model with the inferential results obtained under the independent Gaussian process model.

arXiv (Cornell University), Nov 27, 2014

The mean residual life function is a key functional for a survival distribution. It has a practic... more The mean residual life function is a key functional for a survival distribution. It has a practically useful interpretation as the expected remaining lifetime given survival up to a particular time point, and it also characterizes the survival distribution. However, it has received limited attention in terms of inference methods under a probabilistic modeling framework. We seek to provide general inference methodology for mean residual life regression. Survival data often include a set of predictor variables for the survival response distribution, and in many cases it is natural to include the covariates as random variables into the modeling. We thus employ Dirichlet process mixture modeling for the joint stochastic mechanism of the covariates and survival responses. This approach implies a flexible model structure for the mean residual life of the conditional response distribution, allowing general shapes for mean residual life as a function of covariates given a specific time point, as well as a function of time given particular values of the covariate vector. To expand the scope of the modeling framework, we extend the mixture model to incorporate dependence across experimental groups, such as treatment and control groups. This extension is built from a dependent Dirichlet process prior for the group-specific mixing distributions, with common locations and weights that vary across groups through latent bivariate Beta distributed random variables. We develop properties of the regression models, and discuss methods for prior specification and posterior inference. The different components of the methodology are illustrated 1

Ecological Complexity, Dec 1, 2017

As a consequence of the complexity of ecosystems and context-dependence of species interactions, ... more As a consequence of the complexity of ecosystems and context-dependence of species interactions, structural uncertainty is pervasive in ecological modeling. This is particularly problematic when ecological models are used to make conservation and management plans whose outcomes may depend strongly on model formulation. Nonlinear time series approaches allow us to circumvent this issue by using the observed dynamics of the system to guide policy development. However, these methods typically require long time series from stationary systems, which are rarely available in ecological settings. Here we present a Bayesian approach to nonlinear forecasting based on Gaussian processes that readily integrates information from several short time series and allows for nonstationary dynamics. We demonstrate the utility of our modeling methods on simulated from a wide range of ecological scenarios. We expect that these models will extend the range of ecological systems to which nonlinear forecasting methods can be usefully applied.

Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival t... more Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival times of patients with small cell lung cancer 2.

Cancer Epidemiology, Biomarkers & Prevention, 2023

Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in ... more Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in 2019. Since this number is projected to increase to over 22 million by 2030 and cancer survivors often face long-term challenges and late effects of treatment, it has become increasingly important to evaluate patients’ health-related quality of life in order to better understand their needs, identify disparities, and develop strategies to improve their overall well-being. Racial/ethnic differences in cancer survivorship have been previously reported, but few have evaluated quality of life among a nationally representative, population-based sample of U.S. patients. Methods: We used self-reported data from the Medical Expenditure Panel Survey (MEPS) as well as its Experience with Cancer Survivorship Supplement questionnaire from 2016-17, which collected information on patient experiences with cancer including quality of life based on the Patient-Reported Outcomes Measurement Information System (PROMIS) measures of physical and mental health. A Global Physical Health (GPH) score using questions related to physical health, physical function, fatigue, and pain and a Global Mental Health (GMH) score using questions related to quality of life, mental health, social support, and emotional problems were calculated where the lower the score indicated the poorer the health. In addition, questions related to whether cancer had a positive impact on patients were considered as well. Multiple logistic regression models with odds ratios (ORs) and 95% confidence intervals (CIs) were used to examine the impact of race on these various quality of life/cancer experience outcomes after considering relevant confounders. Results: A total of 1608 cancer survivors (1225 non-Hispanic Whites, 165 Hispanic Whites, 176 Blacks, 42 Asians) were included. When compared to non-Hispanic Whites, only Blacks were statistically significantly more likely to have a low GPH score (OR=1.95, 95% CI 1.15-3.27) and a low GMH score (OR=1.89, 95% CI 1.24-2.89). However, Blacks and Hispanic Whites were statistically significantly more likely to report their cancer experience leading to positive things in their lives; for example, both racial groups were three times as likely to report that their cancer helped them cope better with life’s challenges relative to non-Hispanic Whites (OR=3.66, 95% CI 2.34-5.73 for Blacks, OR=2.91, 95% CI 1.68-5.03 for Hispanic Whites). Conclusions: There are important racial disparities when it comes to health-related quality of life among cancer survivors. Although Blacks were more likely to see the positive aspects of their cancer diagnosis, they still experienced poorer physical and mental health overall. Future studies should explore the factors that may be contributing to these racial disparities as they could greatly inform targeted strategies to improve the overall survivorship experience of cancer patients. Citation Format: Alice W. Lee, Valerie Poynor, JinKyu Choi. Racial disparities in health-related quality of life among cancer survivors in the United States [abstract]. In: Proceedings of the 15th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2022 Sep 16-19; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2022;31(1 Suppl):Abstract nr A038.

The mean residual life function is a key functional for a survival distribution. It has a practic... more The mean residual life function is a key functional for a survival distribution. It has a practically useful interpretation as the expected remaining lifetime given survival up to a particular time point, and it also characterizes the survival distribution. However, it has received limited attention in terms of inference methods under a probabilistic modeling framework. We seek to provide general inference methodology for mean residual life regression. Survival data often include a set of predictor variables for the survival response distribution, and in many cases it is natural to include the covariates as random variables into the modeling. We thus employ Dirichlet process mixture modeling for the joint stochastic mechanism of the covariates and survival responses. This approach implies a flexible model structure for the mean residual life of the conditional response distribution, allowing general shapes for mean residual life as a function of covariates given a specific time poin...

Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival t... more Analysis of survival times of rats (ad libitum vs restricted eating) 2.3.3 Analysis of survival times of patients with small cell lung cancer 2.

Cancer Epidemiology, Biomarkers & Prevention

Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in ... more Background: There were an estimated 16.9 million cancer survivors in the United States (U.S.) in 2019. Since this number is projected to increase to over 22 million by 2030 and cancer survivors often face long-term challenges and late effects of treatment, it has become increasingly important to evaluate patients’ health-related quality of life in order to better understand their needs, identify disparities, and develop strategies to improve their overall well-being. Racial/ethnic differences in cancer survivorship have been previously reported, but few have evaluated quality of life among a nationally representative, population-based sample of U.S. patients. Methods: We used self-reported data from the Medical Expenditure Panel Survey (MEPS) as well as its Experience with Cancer Survivorship Supplement questionnaire from 2016-17, which collected information on patient experiences with cancer including quality of life based on the Patient-Reported Outcomes Measurement Information Sy...

These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 19... more These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 1994). The patients were randomly assigned to one of two treatments referred to as Arm A and Arm B. Arm A patients received cisplatin (P) followed by etoposide (E), while Arm B patients received (E) followed by (P). There were a total of 62 patients in Arm A with 15 right censored survival times, while Arm B consisted of 59 patients with 8 right censored survival times.<br><br>The variables recorded in the dataset(s) are:<br>- age: age of the patient upon entry (in years)<br>- time: survival time of the patient (in days)<br>- cens: indicator for survival time - 0 if observed, 1 if right censored<br><br>We analyze these data using a Dirichlet Process Mixture Model with a Gamma kernel distribution (Poynor and Kottas, 2017). The primary emphasis of our work is to obtain inference for the mean residual life function. Our code is shared through github (...

These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 19... more These data are described in (Ying et al., 1995) and originally collected in (Maksymuik et al., 1994). The patients were randomly assigned to one of two treatments referred to as Arm A and Arm B. Arm A patients received cisplatin (P) followed by etoposide (E), while Arm B patients received (E) followed by (P). There were a total of 62 patients in Arm A with 15 right censored survival times, while Arm B consisted of 59 patients with 8 right censored survival times.<br><br>The variables recorded in the dataset(s) are:<br>- age: age of the patient upon entry (in years)<br>- time: survival time of the patient (in days)<br>- cens: indicator for survival time - 0 if observed, 1 if right censored<br><br>We analyze these data using a Dirichlet Process Mixture Model with a Gamma kernel distribution (Poynor and Kottas, 2017). The primary emphasis of our work is to obtain inference for the mean residual life function. Our code is shared through github (...

Nutrition and Cancer, 2022

Phytoestrogens are plant-derived compounds that are structurally similar to endogenous estrogens.... more Phytoestrogens are plant-derived compounds that are structurally similar to endogenous estrogens. Studies have shown phytoestrogens to have possible health benefits although they could also act as endocrine disruptors. This is particularly relevant for estrogen-dependent cancers since estrogens increase risk of breast, endometrial, and ovarian cancer. Using data from the National Health and Nutritional Examination Survey (NHANES), we assessed the associations between urinary phytoestrogens (daidzein, equol, o-Desmethylangolensin (O-DMA), genistein, enterodiol, enterolactone) and breast, endometrial, and ovarian cancer using multivariate logistic regression with odds ratios (ORs) and 95% confidence intervals (CIs). Cancer diagnosis and other characteristics were collected via in-person questionnaires. We found women in the highest tertile for daidzein and enterodiol had over twice the odds of having breast cancer (OR = 2.51, 95% CI 1.44-4.36 for daidzein, OR = 2.78, 95% CI 1.44-5.37 for enterodiol). In addition, women in the highest tertiles for daidzein and genistein had three to four times the odds of having endometrial cancer, respectively (OR = 3.09, 95% CI 1.01-9.49 for daidzein, OR = 4.00, 95% CI 1.38-11.59 for genistein). Overall, phytoestrogens were positively associated with breast and endometrial cancer although the associations varied by phytoestrogen type. Additional studies are needed to further inform phytoestrogens' role in disease etiology.Supplemental data for this article is available online at at https://doi.org/10.1080/01635581.2021.2020304.

Nutrients, 2020

A multitude of dietary factors from dietary fat to macro and micronutrients intakes have been ass... more A multitude of dietary factors from dietary fat to macro and micronutrients intakes have been associated with breast cancer, yet data are still equivocal. Therefore, utilizing data from the large, multi-year, cross-sectional National Health and Nutrition Examination Survey (NHANES), we applied a novel, modern statistical shrinkage technique, logistic least absolute shrinkage and selection operator (LASSO) regression, to examine the association between dietary intakes in women, ≥50 years, with self-reported breast cancer (n = 286) compared with women without self-reported breast cancer (1144) from the 1999–2010 NHANES cycle. Logistic LASSO regression was used to examine the relationship between twenty-nine variables, including dietary variables from food, as well as well-established/known breast cancer risk factors, and to subsequently identify the most relevant variables associated with self-reported breast cancer. We observed that as the penalty factor (λ) increased in the logistic...

Environmental and Ecological Statistics, 2017

Gaussian process models have been used in applications ranging from machine learning to fisheries... more Gaussian process models have been used in applications ranging from machine learning to fisheries management. In the Bayesian framework, the Gaussian process is used as a prior for unknown functions, allowing the data to drive the relationship between inputs and outputs. In our research, we consider a scenario in which response and input data are available from several similar, but not necessarily identical, sources. When little information is known about one or more of the populations it may be advantageous to model all populations together. We present a hierarchical Gaussian process model with a structure that allows distinct features for each source as well as shared underlying characteristics. Key features and properties of the model are discussed and demonstrated in a number of simulation examples. The model is then applied to a data set consisting of three populations of Rotifer Brachionus calyciflorus Pallas. Specifically, we model the log growth rate of the populations using a combination of lagged population sizes. The various lag combinations are formally compared to obtain the best model inputs. We then formally compare the leading hierarchical Gaussian process model with the inferential results obtained under the independent Gaussian process model.