Forecasting using targeted diffusion indexes

The simplicity of the standard diffusion index model of Stock and Watson has certainly contributed to its success among practitioners, resulting in a growing body of literature on factor‐augmented forecasts. However, as pointed out by Bai and Ng, the ranked factors considered in the forecasting equation depend neither on the variable to be forecast nor on the forecasting horizon. We propose a refinement of the standard approach that retains the computational simplicity while coping with this limitation. Our approach consists of generating a weighted average of all the principal components, the weights depending both on the eigenvalues of the sample correlation matrix and on the covariance between the estimated factor and the targeted variable at the relevant horizon. This ‘targeted diffusion index’ approach is applied to US data and the results show that it outperforms considerably the standard approach in forecasting several major macroeconomic series. Moreover, the improvement is more significant in the final part of the forecasting evaluation period. Copyright © 2009 John Wiley & Sons, Ltd.     

A new approach to forecasting intermittent demand based on the mixed zero-truncated Poisson model

This paper proposes a new approach to forecasting intermittent demand by considering the effects of external factors. We classify intermittent demand data into two parts—zero value and nonzero value—and fit nonzero values into a mixed zero-truncated Poisson model. All the parameters in this model are obtained by an EM algorithm, which regards external factors as independent variables of a logistic regression model and log-linear regression model. We then calculate the probability of occurrence of zero value at each period and predict demand occurrence by comparing it with critical value. When demand occurs, we use the weighted average of the mixed zero-truncated Poisson model as predicted nonzero demands, which are combined with predicted demand occurrences to form the final forecasting demand series. Two performance measures are developed to assess the forecasting methods. By presenting a case study of electric power material from the State Grid Shanghai Electric Power Company in China, we show that our approach provides greater accuracy in forecasting than the Poisson model, the hurdle shifted Poisson model, the hurdle Poisson model, and Croston's method.     

Methods for backcasting,nowcasting and forecasting using factor‐MIDAS: With an application to Korean GDP

We utilize mixed‐frequency factor‐MIDAS models for the purpose of carrying out backcasting, nowcasting, and forecasting experiments using real‐time data. We also introduce a new real‐time Korean GDP dataset, which is the focus of our experiments. The methodology that we utilize involves first estimating common latent factors (i.e., diffusion indices) from 190 monthly macroeconomic and financial series using various estimation strategies. These factors are then included, along with standard variables measured at multiple different frequencies, in various factor‐MIDAS prediction models. Our key empirical findings as follows. (i) When using real‐time data, factor‐MIDAS prediction models outperform various linear benchmark models. Interestingly, the “MSFE‐best” MIDAS models contain no autoregressive (AR) lag terms when backcasting and nowcasting. AR terms only begin to play a role in “true” forecasting contexts. (ii) Models that utilize only one or two factors are “MSFE‐best” at all forecasting horizons, but not at any backcasting and nowcasting horizons. In these latter contexts, much more heavily parametrized models with many factors are preferred. (iii) Real‐time data are crucial for forecasting Korean gross domestic product, and the use of “first available” versus “most recent” data “strongly” affects model selection and performance. (iv) Recursively estimated models are almost always “MSFE‐best,” and models estimated using autoregressive interpolation dominate those estimated using other interpolation methods. (v) Factors estimated using recursive principal component estimation methods have more predictive content than those estimated using a variety of other (more sophisticated) approaches. This result is particularly prevalent for our “MSFE‐best” factor‐MIDAS models, across virtually all forecast horizons, estimation schemes, and data vintages that are analyzed.     

Forecasting and nowcasting emerging market GDP growth rates: The role of latent global economic policy uncertainty and macroeconomic data surprise factors

In this paper, we assess the predictive content of latent economic policy uncertainty and data surprise factors for forecasting and nowcasting gross domestic product (GDP) using factor-type econometric models. Our analysis focuses on five emerging market economies: Brazil, Indonesia, Mexico, South Africa, and Turkey; and we carry out a forecasting horse race in which predictions from various different models are compared. These models may (or may not) contain latent uncertainty and surprise factors constructed using both local and global economic datasets. The set of models that we examine in our experiments includes both simple benchmark linear econometric models as well as dynamic factor models that are estimated using a variety of frequentist and Bayesian data shrinkage methods based on the least absolute shrinkage operator (LASSO). We find that the inclusion of our new uncertainty and surprise factors leads to superior predictions of GDP growth, particularly when these latent factors are constructed using Bayesian variants of the LASSO. Overall, our findings point to the importance of spillover effects from global uncertainty and data surprises, when predicting GDP growth in emerging market economies.     

Predicting Recessions with Factor Linear Dynamic Harmonic Regressions

We propose a new framework for building composite leading indicators for the Spanish economy using monthly targeted predictors and small‐scale dynamic factor models. Our leading indicator index, based on the low‐frequency components of four monthly economic variables, is able to predict the onset of the Spanish recessions as well as the gross domestic product (GDP) growth cycles and classical industrial production cycles, both historically and in real time. Also, our leading indicator provides substantial aid in forecasting annual and quarterly GDP growth rates. Using only real data available at the beginning of each forecast period, our indicator one‐step‐ahead forecasts shows substantial improvements over other alternatives. Copyright © 2013 John Wiley & Sons, Ltd.     

Short‐Term Forecasts of French GDP: A Dynamic Factor Model with Targeted Predictors

In recent years, factor models have received increasing attention from both econometricians and practitioners in the forecasting of macroeconomic variables. In this context, Bai and Ng (Journal of Econometrics 2008; 146 : 304–317) find an improvement in selecting indicators according to the forecast variable prior to factor estimation (targeted predictors). In particular, they propose using the LARS‐EN algorithm to remove irrelevant predictors. In this paper, we adapt the Bai and Ng procedure to a setup in which data releases are delayed and staggered. In the pre‐selection step, we replace actual data with estimates obtained on the basis of past information, where the structure of the available information replicates the one a forecaster would face in real time. We estimate on the reduced dataset the dynamic factor model of Giannone et al. (Journal of Monetary Economics 2008; 55 : 665–676) and Doz et al. (Journal of Econometrics 2011; 164 : 188–205), which is particularly suitable for the very short‐term forecast of GDP. A pseudo real‐time evaluation on French data shows the potential of our approach. Copyright © 2013 John Wiley & Sons, Ltd.     

Factor forecasts for the UK

Data are now readily available for a very large number of macroeconomic variables that are potentially useful when forecasting. We argue that recent developments in the theory of dynamic factor models enable such large data sets to be summarized by relatively few estimated factors, which can then be used to improve forecast accuracy. In this paper we construct a large macroeconomic data set for the UK, with about 80 variables, model it using a dynamic factor model, and compare the resulting forecasts with those from a set of standard time‐series models. We find that just six factors are sufficient to explain 50% of the variability of all the variables in the data set. These factors, which can be shown to be related to key variables in the economy, and their use leads to considerable improvements upon standard time‐series benchmarks in terms of forecasting performance. Copyright © 2005 John Wiley & Sons, Ltd.     

Estimation of short-run predictive factor for US growth using state employment data

We estimate a predictive single factor model targeted to unobserved common growth in gross domestic product and gross domestic income (GDI) using a state-space framework with select state employment data. We use likelihood-based comparison to select the states to estimate the dynamic factor. The results show improved in-sample and out-of-sample performance than threshold principal component factors and financial spreads. Out-of-sample evaluations indicate larger gains for GDI growth with 14% to 20% lower mean squared forecast errors than other alternatives. Sectoral employment factors based on selected sectors using the state-space framework also show forecasting gains. An expanded model using both sectoral and state employment data shows that their common component is the primary predictive factor.     

On detecting and estimating a major level or slope change in general exponential smoothing

Exponential smoothing methods do not adapt well to a major level or slope change. In this paper, Bayesian statistical theory is applied to the dynamic linear model, altered by inclusion of dummy variables, and statistics are derived to detect such changes and to estimate both the change-point and the size. The paper also gives test statistics for such problems related to exponential smoothing. The statistics are simple functions of exponentially weighted moving averages of the forecast errors, using the same discount factor used in the exponential smoothing. Gardner has derived an approximate test statistic to detect a mean change in the constant mean model. When the present results are applied to this model they give the exact statistic.     

Custom-designed zinc finger nucleases: What is next?

Custom-designed zinc finger nucleases (ZFNs)--proteins designed to cut at specific DNA sequences--combine the non-specific cleavage domain (N) of Fok I restriction endonuclease with zinc finger proteins (ZFPs). Because the recognition specificities of the ZFPs can be easily manipulated experimentally, ZFNs offer a general way to deliver a targeted site-specific double-strand break (DSB) to the genome. They have become powerful tools for enhancing gene targeting--the process of replacing a gene within a genome of cells via homologous recombination (HR)--by several orders of magnitude. ZFN-mediated gene targeting thus confers molecular biologists with the ability to site-specifically and permanently alter not only plant and mammalian genomes but also many other organisms by stimulating HR via a targeted genomic DSB. Site-specific engineering of the plant and mammalian genome in cells so far has been hindered by the low frequency of HR. In ZFN-mediated gene targeting, this is circumvented by using designer ZFNs to cut at the desired chromosomal locus inside the cells. The DNA break is then patched up using the new investigator-provided genetic information and the cells' own repair machinery. The accuracy and high efficiency of the HR process combined with the ability to design ZFNs that target most DNA sequences (if not all) makes ZFN technology not only a powerful research tool for site-specific manipulation of the plant and mammalian genomes, but also potentially for human therapeutics in the future, in particular for targeted engineering of the human genome of clinically transplantable stem cells.     

New approaches to therapy of cancers of the stomach,colon and pancreas based on peptide analogs

Cancers of the stomach, colon and exocrine pancreas are major international health problems and result in more than a million deaths worldwide each year. The therapies for these malignancies must be improved. The effects of gastrointestinal (GI) hormonal peptides and endogenous growth factors on these cancers were reviewed. Some GI peptides, including gastrin and gastrin-releasing peptide (GRP) (mammalian bombesin), appear to be involved in the growth of neoplasms of the GI tract. Certain growth factors such as insulin-like growth factor (IGF)-I, IGF-II and epidermal growth factor and their receptors that regulate cell proliferation are also implicated in the development and progression of GI cancers. Experimental investigations on gastric, colorectal and pancreatic cancers with analogs of somatostatin, antagonists of bombesin/GRP, antagonists of growth hormone-releasing hormone as well as cytotoxic peptides that can be targeted to peptide receptors on tumors were summarized. Clinical trials on peptide analogs in patients with gastric, colorectal and pancreatic cancers were reviewed and analyzed. It may be possible to develop new approaches to hormonal therapy of GI malignancies based on various peptide analogs.Received 20 November 2003; accepted 6 January 2004     

Related‐variables selection in temporal disaggregation

Two related‐variables selection methods for temporal disaggregation are proposed. In the first method, the hypothesis tests for a common feature (cointegration or serial correlation) are first performed. If there is a common feature between observed aggregated series and related variables, the conventional Chow–Lin procedure is applied. In the second method, alternative Chow–Lin disaggregating models with and without related variables are first estimated and the corresponding values of the Bayesian information criterion (BIC) are stored. It is determined on the basis of the selected model whether related variables should be included in the Chow–Lin model. The efficacy of these methods is examined via simulations and empirical applications. Copyright © 2008 John Wiley & Sons, Ltd.     

Forecasting key macroeconomic variables from a large number of predictors: a state space approach

We use state space methods to estimate a large dynamic factor model for the Norwegian economy involving 93 variables for 1978Q2–2005Q4. The model is used to obtain forecasts for 22 key variables that can be derived from the original variables by aggregation. To investigate the potential gain in using such a large information set, we compare the forecasting properties of the dynamic factor model with those of univariate benchmark models. We find that there is an overall gain in using the dynamic factor model, but that the gain is notable only for a few of the key variables. Copyright © 2009 John Wiley & Sons, Ltd.     

Targeted polymeric micelles for delivery of poorly soluble drugs

Polymeric micelles (micelles formed by amphiphilic block copolymers) demonstrate a series of attractive properties as drug carriers, such as high stability both in vitro and in vivo and good biocompatibility, and can be successfully used for the solubilization of various poorly soluble pharmaceuticals. These micelles can also be used as targeted drug delivery systems. The targeting can be achieved via the enhanced permeability and retention effect (into the areas with the compromised vasculature), by making micelles of stimuli-responsive amphiphilic block copolymers, or by attaching specific targeting ligand molecules to the micelle surface. Immunomicelles prepared by coupling monoclonal antibody molecules to p-nitrophenylcarbonyl groups on the water-exposed termini of the micelle corona-forming blocks demonstrate high binding specificity and targetability. Immunomicelles prepared with cancer-specific monoclonal antibody 2C5 specifically bind to different cancer cells in vitro and demonstrate increased therapeutic activity in vivo. This new family of pharmaceutical carriers can be used for the solubilization and targeted delivery of poorly soluble drugs to various pathological sites in the body.     

Sulfatide-tenascin interaction mediates binding to the extracellular matrix and endocytic uptake of liposomes in glioma cells

Tenascin-C is an extracellular matrix glycoprotein, whose expression is highly restricted in normal adult tissues, but markedly up-regulated in a range of tumors, and therefore serves as a potential receptor for targeted anticancer drug or gene delivery. We describe here a liposomal carrier system in which the targeting ligand is sulfatide. Experiments with tenascin-C-expressing glioma cells demonstrated that binding of liposomes to the extracellular matrix relied essentially on the sulfatide-tenascin-C interaction. Following binding to the extracellular matrix, the sulfatide-containing liposomes were internalized via both caveolae/lipid raft- and clathrin-dependent pathways, which would ensure direct cytoplasmic release of the cargoes carried in the liposomes. Such natural lipid-guided intracellular delivery targeting at the extracellular matrix glycoproteins of tumor cells thus opens a new direction for development of more effective anticancer chemotherapeutics in future. K. Shao & Q. Hou: These authors contributed equally to this work. Received 22 September 2006; received after revision 5 December 2006; accepted 9 January 2007     

Drug susceptibility of PCA in WBB6F1-W/Wv mice

Our previous study revealed that passive cutaneous anaphylaxis (PCA) can be produced in congenitally mast cell-deficient WBB6F1-W/W^v (abbreviated as W/W^v) mice on sensitization with undiluted or slightly diluted allogeneic and xenogeneic antisera but not on sensitization with allogeneic monoclonal immunoglobulin (Ig)E and IgG1 antibodies regardless of the antibody concentration [1]. In view of these findings, the present study was conducted to characterize PCA in this strain from its drug susceptibilities using mast cell-bearing WBB6F1-+/+ (abbreviated as +/+) and B6D2F1 mice as references. PCA in W/W^v mice mediated by a low dilution (1  4) of hyperimmune serum to bovine serum albumin of the B6D2F1 mouse origin was markedly suppressed by CV-6209, an antagonist of platelet-activating factor (PAF), but not by antihistamines such as cyproheptadine and oxatomide. In contrast, PCA in +/+ and B6D2F1 mice mediated by a high dilution (1  128) of the anti-serum (virtually by IgG1 antibody) was nearly completely suppressed by antihistamines but not by CV-6209. A remarkable difference between PCA in W/W^v and reference mice was also observed in the susceptibility to monoclonal anti mouse granulocyte (Gr-1) antibody PCA in W/W^v mice was potently suppressed by the 1- to 3-day pretreatment with this antibody but that in references was not at all. Putting these present results together with the previous finding that anti-granulocyte antibody greatly reduces circulatory Gr-1⁺ leukocytes, 1 to 3 days after the treatment [2], it is highly probable that PCA in W/W^v mice mediated by some antibody isotypes other than IgE and IgG1 is produced by PAF mainly released from Gr-1⁺ cells, while IgG1 antibody-mediated PCA in mast cell-bearing reference mice is evoked by histamine derived from mast cells. PCA homologous to that in W/W^v mice could also be produced in the reference mice on sensitization with undiluted or slightly diluted antiserum, when generalized blueing due to excess IgG1 antibody was removed by the oxatomide treatment be fore the antigen challenge. Received 10 December 1997; received after revision 2 February 1998; accepted 23 February 1998     

Recent advances in the development of new transgenic animal technology

Transgenic animal technology is one of the fastest growing biotechnology areas. It is used to integrate exogenous genes into the animal genome by genetic engineering technology so that these genes can be inherited and expressed by offspring. The transgenic efficiency and precise control of gene expression are the key limiting factors in the production of transgenic animals. A variety of transgenic technologies are available. Each has its own advantages and disadvantages and needs further study because of unresolved technical and safety issues. Further studies will allow transgenic technology to explore gene function, animal genetic improvement, bioreactors, animal disease models, and organ transplantation. This article reviews the recently developed animal transgenic technologies, including the germ line stem cell-mediated method to improve efficiency, gene targeting to improve accuracy, RNA interference-mediated gene silencing technology, zinc-finger nuclease gene targeting technology and induced pluripotent stem cell technology. These new transgenic techniques can provide a better platform to develop transgenic animals for breeding new animal varieties and promote the development of medical sciences, livestock production, and other fields.     

Change in sensitivity to lipopolysaccharide during the differentiation of human monocytes to macrophages in vitro

Mononuclear phagocytes in distinct differentiation stages and cultured under different conditions were tested for their sensitivity towards lipopolysaccharide (LPS), using procoagulant activity (PCA) expression and tumor necrosis factor (TNF) production as indices. The response of mature monocyte-derived macrophages differed from that of freshly isolated monocytes 1) by higher levels of constititive PCA, 2) by responding to approximately 1,000-fold lower concentrations of LPS with PCA and TNF production, and 3) by a faster rise in PCA and TNF production. Due to the high constitutive level of PCA expression, the PCA stimulation index for LPS was low in macrophages when compared with that in monocytes. Thus, during differentiation to macrophages, human monocytes acquire increased sensitivity to LPS (2 orders of magnitude more sensitive than a sensitive turbidimetricLimulus amoebocyte lysate assay). This exquisite sensitivity to LPS is expressed regardless of whether LPS is offered in the presence or absence of lipopolysaccharide binding protein-containing serum. This points to as yet uncharacterized pathways of high affinity interaction between LPS and macrophages.     

P/E changes: some new results

The P/E ratio is often used as a metric to compare individual stocks and the market as a whole relative to historical valuations. We examine the factors that affect changes in the inverse of the P/E ratio (E/P) over time in the broad market (S&P 500 Index). Our model includes variables that measure investor beliefs and changes in tax rates and shows that these variables are important factors affecting the P/E ratio. We extend prior work by correcting for the presence of a long‐run relation between variables included in the model. As frequently conjectured, changes in the P/E ratio have predictive power. Our model explains a large portion of the variation in E/P and accurately predicts the future direction of E/P, particularly when predicted changes in E/P are large or provide a consistent signal over more than one quarter. Copyright © 2008 John Wiley & Sons, Ltd.