Regression with autocorrelated data: A study of time trend of global infant mortality rate

The infant mortality rate (IMR) is considered to be one of the most important indices of a country's well-being. Countries around the world and other health organizations like the World Health Organization are dedicating their resources, knowledge and energy to reduce the infant mortality rates. The well-known Millennium Development Goal 4 (MDG 4), whose aim is to archive a two thirds reduction of the under-five mortality rate between 1990 and 2015, is an example of the commitment. ^ In this study our goal is to model the trends of IMR between the 1950s to 2010s for selected countries. We would like to know how the IMR is changing overtime and how it differs across countries. ^ IMR data collected over time forms a time series. The repeated observations of IMR time series are not statistically independent. So in modeling the trend of IMR, it is necessary to account for these correlations. We proposed to use the generalized least squares method in general linear models setting to deal with the variance-covariance structure in our model. In order to estimate the variance-covariance matrix, we referred to the time-series models, especially the autoregressive and moving average models. Furthermore, we will compared results from general linear model with correlation structure to that from ordinary least squares method without taking into account the correlation structure to check how significantly the estimates change.^

Survival analysis of circulating tumor cells in triple-negative breast cancer

Background. Breast cancer is the most frequently diagnosed cancer and the leading cause of cancer death among females, accounting for 23% (1.38 million) of the total new cancer cases and 14% (458,400) of the total cancer deaths in 2008. [1] Triple-negative breast cancer (TNBC) is an aggressive phenotype comprising 10–20% of all breast cancers (BCs). [2-4] TNBCs show absence of estrogen, progesterone and HER2/neu receptors on the tumor cells. Because of the absence of these receptors, TNBCs are not candidates for targeted therapies. Circulating tumor cells (CTCs) are observed in blood of breast cancer patients even at early stages (Stage I & II) of the disease. Immunological and molecular analysis can be used to detect the presence of tumor cells in the blood (Circulating tumor cells; CTCs) of many breast cancer patients. These cells may explain relapses in early stage breast cancer patients even after adequate local control. CTC detection may be useful in identifying patients at risk for disease progression, and therapies targeting CTCs may improve outcome in patients harboring them. Methods . In this study we evaluated 80 patients with TNBC who are enrolled in a larger prospective study conducted at M D Anderson Cancer Center in order to determine whether the presence of circulating tumor cells is a significant prognostic factor in relapse free and overall survival . Patients with metastatic disease at the time of presentation were excluded from the study. CTCs were assessed using CellSearch System™ (Veridex, Raritan, NJ). CTCs were defined as nucleated cells lacking the presence of CD45 but expressing cytokeratins 8, 18 or 19. The distribution of patient and tumor characteristics was analyzed using chi square test and Fisher's exact test. Log rank test and Cox regression analysis was applied to establish the association of circulating tumor cells with relapse free and overall survival. Results. The median age of the study participants was 53years. The median duration of follow-up was 40 months. Eighty-eight percent (88%) of patients were newly diagnosed (without a previous history of breast cancer), and (60%) of patients were chemo naïve (had not received chemotherapy at the time of their blood draw for CTC analysis). Tumor characteristics such as stage (P=0.40), tumor size (P=69), sentinel nodal involvement (P=0.87), axillary lymph node involvement (P=0.13), adjuvant therapy (P=0.83), and high histological grade of tumor (P=0.26) did not predict the presence of CTCs. However, CTCs predicted worse relapse free survival (1 or more CTCs log rank P value = 0.04, at 2 or more CTCs P = 0.02 and at 3 or more CTCs P < 0.0001) and overall survival (at 1 or more CTCs log rank P value = 0.08, at 2 or more CTCs P = 0.01 and at 3 or more CTCs P = 0.0001. Conclusions. The number of circulating tumor cells predicted worse relapse free survival and overall survival in TNBC patients.^

Evaluation of memory B cells among perinatally HIV infected children from Houston Texas

Background: HIV associated B cell exhaustion is a notable characteristic of HIV viremic adults. However, it is not known if such alterations are present in perinatal HIV infected children, whose viral dynamics differs from those seen in adults. In the present study we perform an analysis of B cells subsets and measure antigen-specific memory B cells (MBC) in a pediatric HIV infected cohort. ^ Methods: Peripheral mononuclear cells (PBMC) of perinatal HIV infected individuals are characterized into naïve (CD21hi/CD27−), classic (CD27+), tissue like (CD21lo/CD27 −) and activated MBC (CD27+CD21− ) by FACS. A memory ELISPOT assay is used to detect antibody secreting cells. We measure total IgG and antibodies specific for influenza, HBV, mumps, measles, rubella and VZV. Memory was expressed as spot forming cells (SPC) /million of PBMC. Wilcoxon rank-sum was used to compare unpaired groups and linear regression analysis was used to determine predictors of B cell dysfunction ^ Results: 41 HIV perinatal infected children are included (51.2% females and 65.9% Black). Age at study is median (range) 8.78 years (4.39-11.57). At the time of testing they have a CD4% of 30.9 (23.2-39.4), a viral load (VL) of 1.95 log10 copies/ml (1.68-3.29) and a cumulative VL of 3.4 log10 copy × days (2.7-4.0). Ninety two percent of the children are on cARV for > 6 months. Overall, HIV+ children compared with controls have a significant lower number of IgG and antigen specific SFC. In addition, they have a lower proportion of classical MBC 12.9 (8.09-19.85) vs 29.4 (18.7-39.05); 0.01, but a significant higher proportion of tissue like memory MBC 6.01 (2.79-12.7) vs 0.99 (0.87-1.38); 0.003, compared with controls. Patients are parsed on VL (<400 and ≥ 400 copies/ml) with the objective to evaluate the effect of VL on B cell status. Patients with a VL ≥ 400 copies/ml have a significantly lower IgG, HBV, measles, rubella and VZV SPC compared with those with a VL < 400 copies/ml. There are no significant differences in B cell subpopulations between the groups. A moderate negative correlation was observed between the time of cARV initiation and the frequency of IgG memory B cells, suggesting that early initiation of cARV appears to lead to a better functionality of the IgG memory B cells (P=0.05). A statistically significant positive correlation was observed between the total number of IgG memory cells and the number of antigen-specific memory B cells/SPCs. Suggesting that the progressive recovery of the IgG memory B cell pull goes along with a progressive increase in the number of antigen-specific SPCs. ^ Conclusion: A pediatric cohort in overall good status with respect to HIV infection and on ART has defects in B cell function and numbers (reduced total and antigen specific MBC and increased tissue like and reduced classical MBC).^

Age -period -cohort analysis: An extension of Cox's lifetable regression with time -dependent covariates

It is well known that an identification problem exists in the analysis of age-period-cohort data because of the relationship among the three factors (date of birth + age at death = date of death). There are numerous suggestions about how to analyze the data. No one solution has been satisfactory. The purpose of this study is to provide another analytic method by extending the Cox's lifetable regression model with time-dependent covariates. The new approach contains the following features: (1) It is based on the conditional maximum likelihood procedure using a proportional hazard function described by Cox (1972), treating the age factor as the underlying hazard to estimate the parameters for the cohort and period factors. (2) The model is flexible so that both the cohort and period factors can be treated as dummy or continuous variables, and the parameter estimations can be obtained for numerous combinations of variables as in a regression analysis. (3) The model is applicable even when the time period is unequally spaced.^ Two specific models are considered to illustrate the new approach and applied to the U.S. prostate cancer data. We find that there are significant differences between all cohorts and there is a significant period effect for both whites and nonwhites. The underlying hazard increases exponentially with age indicating that old people have much higher risk than young people. A log transformation of relative risk shows that the prostate cancer risk declined in recent cohorts for both models. However, prostate cancer risk declined 5 cohorts (25 years) earlier for whites than for nonwhites under the period factor model (0 0 0 1 1 1 1). These latter results are similar to the previous study by Holford (1983).^ The new approach offers a general method to analyze the age-period-cohort data without using any arbitrary constraint in the model. ^

The number and timing of time -dependent covariate measurements for the Cox regression model

The problem of analyzing data with updated measurements in the time-dependent proportional hazards model arises frequently in practice. One available option is to reduce the number of intervals (or updated measurements) to be included in the Cox regression model. We empirically investigated the bias of the estimator of the time-dependent covariate while varying the effect of failure rate, sample size, true values of the parameters and the number of intervals. We also evaluated how often a time-dependent covariate needs to be collected and assessed the effect of sample size and failure rate on the power of testing a time-dependent effect.^ A time-dependent proportional hazards model with two binary covariates was considered. The time axis was partitioned into k intervals. The baseline hazard was assumed to be 1 so that the failure times were exponentially distributed in the ith interval. A type II censoring model was adopted to characterize the failure rate. The factors of interest were sample size (500, 1000), type II censoring with failure rates of 0.05, 0.10, and 0.20, and three values for each of the non-time-dependent and time-dependent covariates (1/4,1/2,3/4).^ The mean of the bias of the estimator of the coefficient of the time-dependent covariate decreased as sample size and number of intervals increased whereas the mean of the bias increased as failure rate and true values of the covariates increased. The mean of the bias of the estimator of the coefficient was smallest when all of the updated measurements were used in the model compared with two models that used selected measurements of the time-dependent covariate. For the model that included all the measurements, the coverage rates of the estimator of the coefficient of the time-dependent covariate was in most cases 90% or more except when the failure rate was high (0.20). The power associated with testing a time-dependent effect was highest when all of the measurements of the time-dependent covariate were used. An example from the Systolic Hypertension in the Elderly Program Cooperative Research Group is presented. ^

Evaluation of the Hosmer -Lemeshow global goodness -of-fit statistic for mixed variable logistic regression models

The performance of the Hosmer-Lemeshow global goodness-of-fit statistic for logistic regression models was explored in a wide variety of conditions not previously fully investigated. Computer simulations, each consisting of 500 regression models, were run to assess the statistic in 23 different situations. The items which varied among the situations included the number of observations used in each regression, the number of covariates, the degree of dependence among the covariates, the combinations of continuous and discrete variables, and the generation of the values of the dependent variable for model fit or lack of fit.^ The study found that the $\rm\ C$g* statistic was adequate in tests of significance for most situations. However, when testing data which deviate from a logistic model, the statistic has low power to detect such deviation. Although grouping of the estimated probabilities into quantiles from 8 to 30 was studied, the deciles of risk approach was generally sufficient. Subdividing the estimated probabilities into more than 10 quantiles when there are many covariates in the model is not necessary, despite theoretical reasons which suggest otherwise. Because it does not follow a X$\sp2$ distribution, the statistic is not recommended for use in models containing only categorical variables with a limited number of covariate patterns.^ The statistic performed adequately when there were at least 10 observations per quantile. Large numbers of observations per quantile did not lead to incorrect conclusions that the model did not fit the data when it actually did. However, the statistic failed to detect lack of fit when it existed and should be supplemented with further tests for the influence of individual observations. Careful examination of the parameter estimates is also essential since the statistic did not perform as desired when there was moderate to severe collinearity among covariates.^ Two methods studied for handling tied values of the estimated probabilities made only a slight difference in conclusions about model fit. Neither method split observations with identical probabilities into different quantiles. Approaches which create equal size groups by separating ties should be avoided. ^

IL -12 inhibits the metastatic potential of osteosarcoma cells and induces tumor regression via a mechanism involving Fas /Fas ligand pathway

Despite multiple changes in the adjuvant chemotherapy regimens used to treat osteosarcoma (OS), the 2-year metastasis-free survival has remained at 65–70% for the past 10 years. Characterizing the molecular determinants that permit metastatic spread of tumor cells is a crucial element in developing new approaches for the treatment of osteosarcoma. Since OS metastasizes almost exclusively to the lung, an organ with constitutive Fas ligand (FasL) expression, we hypothesized that the expression of Fas (CD95, APO-1) by OS cells may play a role in the ability of these cells to form lung metastases. Fas expression was quantified in human SAOS-2 OS cells and selected variants (LM2, LM4, LM5, LM6, LM7). Using northern blot, FACS and RT-PCR analysis, low Fas expression was found to correlate with higher metastatic potential in these cell lines. The highly metastatic LM7 cell line was transfected with the full-length human Fas gene and injected into athymic nude mice. The median number of metastatic nodules per mouse fell from over 200 to 1.1 and the size of the nodules decreased from a range of 0.5–9.0 mm to less than 0.5 mm in the Fas-transfected cell line compared to the native LM7 cell line. Additionally, the subsequent incidence of lung metastases was lower in the Fas-expressing cell line. IL-12 was seen to upregulate Fas expression in the highly metastatic LM sublines in vitro. To visualize the effects of IL-12 in vivo, nude mice were injected with LM7 cells and treated biweekly for 4 weeks with Ad.mIL-12, saline control or Ad.βgal. Lung sections were analyzed via immunchistochemistry for Fas expression. A higher expression of Fas was found in tumors from mice receiving IL-12. To study the mechanism by which IL-12 upregulates Fas, LM7 cells were transfected with a luciferase reporter gene construct containing the full-length human fas promoter. Treatment with IL-12 increased luciferase activity. We therefore conclude that IL-12 influences the metastatic potential of OS cells by upregulating the fas promoter, resulting in increased cell surface Fas expression and susceptibility to Fas-induced cell death. ^

Retinoid -induced regression of human head and neck squamous cell carcinomas is associated with the induction of a pro -inflammatory response

Retinoids are Vitamin A derivatives that are effective chemopreventative and chemotherapeutic agents for head and neck squamous cell carcinomas (HNSCC). Despite the wide application of retinoids in cancer treatment, the mechanism by which retinoids inhibit head and neck squamous cell carcinomas is not completely understood. While in vitro models show that drugs affect cell proliferation and differentiation, in vivo models, such as tumor xenografts in nude mice drugs affect more complex parameters such as extracellular matrix formation, angiogenesis and inflammation. Therefore, we studied the effects of retinoids on the growth of the 22B HNSCC tumors using a xenograft model. In this system, retinoids had no effect on tumor cell differentiation but caused invasion of the tumor by inflammatory cells. Retinoid induced inflammation lead to tumor cell death and tumor regression. Therefore, we hypothesized that retinoids stimulated the 22B HNSCC xenografts to produce a pro-inflammatory signal such as chemokines that in turn activated host inflammatory responses. ^ We used real time quantitative RT-PCR to measure cytokine and chemokine expression in retinoid treated tumors. Treatment of tumors with an RAR-specific retinoid, LGD1550, had no effect on the expression of TNFα, IL-1α, GROα, IP-10, Rantes, MCP-1 and MIP-1α but induced IL-8 mRNA 5-fold. We further characterized the retinoid effect on IL-8 expression on the 22B HNSCC and 1483 HNSCC cells in vitro. Retinoids increased IL-8 expression and enhanced TNFα-dependent IL-8 induction. In addition, retinoids increased the basal and TNFα-dependent expression of MCP-1 but decreased the basal and TNFα dependent expression of IP-10. The effect of retinoids on IL-8 and MCP-1 expression was very rapid with increased levels of mRNA detected within 1–2 hours. This effect did not require new protein synthesis and did not result from mRNA stabilization. Both RAR and RXR ligands increased IL-8 expression whereas only RAR ligands activated MCP-1 expression. ^ We identified a functional retinoid response element in the IL-8 promoter that was located adjacent to the C/EBP-NFkB response element. TNFα treatment of the 22B cells caused rapid, transient and selective acetylation of regions of the IL-8 promoter associated with the NFkB response element. Co-treatment of the cells with retinoids plus TNF increased the acetylation of chromatin in this region without altering the kinetics of acetylation. These results demonstrate that ligand activated retinoid receptors can cooperate with NFkB in histone acetylation and chromatin remodeling. We believe that in certain HNSCC tumors this cooperation and the resulting enhancement of IL-8 expression can induce an inflammatory response that leads to tumor regression. We believe that the induction of inflammation in susceptible tumors, possibly coupled with cytotoxic interventions may be an important component in the use of retinoids to treat human squamous cancers. ^

Relaciones de similitud y valor discriminativo de los indicadores bibliométricos: el caso de los indicadores de Scimago Journal and Country Rank aplicados a las revistas generalistas de paleontología

Los objetivos de este trabajo son: (1) analizar las relaciones de similitud de los indicadores bibliométricos; y (2) estudiar el valor de estos para discriminar/agrupar revistas científicas. Como unidades de estudio se utilizaron los 15 indicadores brindados por SCImago Journal Rank (SCImagoJR), aplicados a las 11 revistas paleontológicas generalistas listadas en dicha fuente durante el lapso 1999-2013. Las relaciones de similitud entre los indicadores se estimaron mediante un fenograma, mientras que el valor de los indicadores para agrupar/discriminar revistas se estimó mediante un análisis de componentes principales. Los resultados permiten concluir que, al menos para las revistas consideradas en este estudio, los 15 indicadores utilizados por SCImagoJR muestran redundancia por grupos, debido a las correlaciones existentes entre indicadores de producción, por una parte, y de citación, por otra. Sin embargo, esto es válido solo a los efectos de agrupar las revistas, ya que al considerar cada indicador por separado se aprecian variaciones entre los mismos, que permiten establecer una caracterización más específica de cada revista e, incluso, colaboran a explicar los resultados del análisis multivariado. Por otra parte, los resultados coinciden con los obtenidos por otros autores al reunir en un mismo grupo al SJR y al número de citas/documento en un período de dos años y en otro al índice h y al indicador número total de citas en un lapso de tres años.

Relaciones de similitud y valor discriminativo de los indicadores bibliométricos: el caso de los indicadores de Scimago Journal and Country Rank aplicados a las revistas generalistas de paleontología

Los objetivos de este trabajo son: (1) analizar las relaciones de similitud de los indicadores bibliométricos; y (2) estudiar el valor de estos para discriminar/agrupar revistas científicas. Como unidades de estudio se utilizaron los 15 indicadores brindados por SCImago Journal Rank (SCImagoJR), aplicados a las 11 revistas paleontológicas generalistas listadas en dicha fuente durante el lapso 1999-2013. Las relaciones de similitud entre los indicadores se estimaron mediante un fenograma, mientras que el valor de los indicadores para agrupar/discriminar revistas se estimó mediante un análisis de componentes principales. Los resultados permiten concluir que, al menos para las revistas consideradas en este estudio, los 15 indicadores utilizados por SCImagoJR muestran redundancia por grupos, debido a las correlaciones existentes entre indicadores de producción, por una parte, y de citación, por otra. Sin embargo, esto es válido solo a los efectos de agrupar las revistas, ya que al considerar cada indicador por separado se aprecian variaciones entre los mismos, que permiten establecer una caracterización más específica de cada revista e, incluso, colaboran a explicar los resultados del análisis multivariado. Por otra parte, los resultados coinciden con los obtenidos por otros autores al reunir en un mismo grupo al SJR y al número de citas/documento en un período de dos años y en otro al índice h y al indicador número total de citas en un lapso de tres años.

Relaciones de similitud y valor discriminativo de los indicadores bibliométricos: el caso de los indicadores de Scimago Journal and Country Rank aplicados a las revistas generalistas de paleontología

Los objetivos de este trabajo son: (1) analizar las relaciones de similitud de los indicadores bibliométricos; y (2) estudiar el valor de estos para discriminar/agrupar revistas científicas. Como unidades de estudio se utilizaron los 15 indicadores brindados por SCImago Journal Rank (SCImagoJR), aplicados a las 11 revistas paleontológicas generalistas listadas en dicha fuente durante el lapso 1999-2013. Las relaciones de similitud entre los indicadores se estimaron mediante un fenograma, mientras que el valor de los indicadores para agrupar/discriminar revistas se estimó mediante un análisis de componentes principales. Los resultados permiten concluir que, al menos para las revistas consideradas en este estudio, los 15 indicadores utilizados por SCImagoJR muestran redundancia por grupos, debido a las correlaciones existentes entre indicadores de producción, por una parte, y de citación, por otra. Sin embargo, esto es válido solo a los efectos de agrupar las revistas, ya que al considerar cada indicador por separado se aprecian variaciones entre los mismos, que permiten establecer una caracterización más específica de cada revista e, incluso, colaboran a explicar los resultados del análisis multivariado. Por otra parte, los resultados coinciden con los obtenidos por otros autores al reunir en un mismo grupo al SJR y al número de citas/documento en un período de dos años y en otro al índice h y al indicador número total de citas en un lapso de tres años.

Diagnostik von Regressionsschätzungen bei kleinen Stichproben (mit einem Exkurs zu logistischer Regression)

Wie alle anderen statistischen Verfahren konzentriert sich auch die Methode der Regression nur auf die Analyse ausgewählter Aspekte vorliegenden Datenmaterials. Entsprechend sind zu gegebenen Regressionsergebnissen ganz unterschiedliche Datenkonstellationen denkbar, wovon aber für die Interpretation der Ergebnisse nicht alle unproblematisch sind. So besteht besonders bei kleinen Stichproben die Gefahr, dass die Regressionsschätzung entscheidend von einzelnen Extremwerten abhängt, was die Verlässlichkeit der daraus abgeleiteten Schlussfolgerungen beeinträchtigt. In diesem Beitrag werden deshalb anhand von Beispielen einige einfache grafische und formale Instrumente zur Diagnose einflussreicher Datenpunkte in der linearen und logistischen Regression vorgestellt, die im Prozess der Datenanalyse standardmäßig angewendet werden sollten. Weiterhin werden nach Identifikation „atypischer“ Datenpunkte zu verfolgende Analysestrategien diskutiert.

From regression estimates to document tables: output formatting using -estout-

Postestimation processing and formatting of regression estimates for input into document tables are tasks that many of us have to do. However, processing results by hand can be laborious, and is vulnerable to error. There are therefore many benefits to automation of these tasks while at the same time retaining user flexibility in terms of output format. The estout package meets these needs. estout assembles a table of coefficients, "significance stars", summary statistics, standard errors, t/z statistics, p-values, confidence intervals, and other statistics calculated for up to twenty models previously fitted and stored by estimates store. It then writes the table to the Stata log and/or to a text file. The estimates are formatted optionally in several styles: html, LaTeX, or tab-delimited (for input into MS Excel or Word). There are a large number of options regarding which output is formatted and how. This talk will take users through a range of examples, from relatively basic simple applications to complex ones.