Examples of Eviews Code

Eviews is one of the popular econometrics packages being used by research community and academicians. It is a GUI (Graphical User Interface) based program compatible with Windows and Macintosh operating systems. Other popular econometrics packages include, SHAZAM, LIMDEP, SAS and GAUSS etc. Eviews is one of the most popular software for analyzing time series data. Eviews, produced by Quantitative Micro Software (QMS) from Irvine, California, comes with very useful user guide and reference manuals called, The Users Guide and The Command and Programming Reference (www.eviews.com). If you are familiar with programs like C++ and Gauss you will be able to use your programming skills to run your own customized protocols in Eviews. Let us view some examples of Eviews code here.

Continue reading Examples of Eviews Code

Autocorrelation in GAM and GRASP

Autocorrelation in GAM and GRASP models is an important topic of discussion since these models are being widely used in predictive animal and plant distribution models in the discipline of ecology.

The most widely used statistical models in the fields of ecological modeling, biodiversity and conservation are Generalized Linear Models (GLM) and GAM (General Additive Model) which is a semi-parametric extension of GLM. GRASP stands for Generalized Regression Analysis and Spatial Prediction (http://www.cscf.ch/grasp/grasp-s/welcome.html). GRASP is a combination of advanced S Plus functions and GIS (Geographical Information System) Many of these applications can be run through the software “R” (www.r-project.org).

What is Autocorrelation?

Autocorrelation describes correlation between a process, say Xt, at a different point of time Xs. The autocorrelation function can be depicted in a formula as

eqnautocor.PNG

where Xt has the variance σ2 and mean μ. E is the expected value. The result will range between -1 and 1. 1 indicates perfect correlation while -1 indicates perfect anti-correlation. You must note that the function should be well defined.

Continue reading Autocorrelation in GAM and GRASP

A Glossary of Content

Before launching into a controversial topic, it is a good idea to get the definition of terms straight, so I put together a glossary of forms of content found on the web. By no means complete, please feel free to add more.

Content is a form of information, here referring mainly to text, or text and images together that form a coherent work, referred to as an article.

Free Content

Free content is work legally usable without paying a fee, although legal restrictions may exist on modification, redistribution, and attribution.

Open Content

Open content, generally free, may be redistributed provided it remains unaltered. Open content license also allows the charging of a fee for services but not for the OC material itself. The OC license also allows modification providing attribution information, OC license and zero cost remain intact.

Syndicated Content

Content syndication referees to the distribution of content to multiple Web sites through technologies as RSS, or catalogs of articles. The most common examples are the use of selective RSS newsfeeds to populate web pages with relevant daily changing updates.

Original Content

Original content refers to work that is significantly unlike any other work as to be regarded as ‘original’. For example, an original work would be expected to pass the plagiarism test at copyscape.com. Sources of original conent include vast compendiums such as ezine articles.

Custom Content

Custom content, in contrast to the above forms is paid for, and developed to the clients specifications. It should be original content, without the legal limitations of the above forms as it becomes owned by the client, and may be attributed to him/her, an used in any way. A familiar example of custom content is ‘advertising copy’ describing products for sale.

Creative Content

Creative content, like custom content, is paid for and owned, but unlike advertising copy is significantly creative that it might engage an audience to provoke comment, controversy, be read of recreational or educational purposes. For example, blog post would generally be regarded as creative content. For example, one might gauge the degree of creativity by the number of comments received by a post.

Technical Content

Technical Content, while being custom and original, would not generally be regarded as creative, consisting of such things as specification or requirements documents, legal documents, and objective accounts such as financial or scientific reports.

User-Generated Content

Sites with content generated such as Wikipedia, YouTube, Flickr, and MySpace by users have taken the web by storm, now five of the top ten fastest growing web brands. User-generated content has the advantages of being free, although the legal usages of the content are not clear.

Destination Content

One would imagine different industries would have unique forms of content. One major example is travel industry destination content, information and media for information potential travelers about their destination. For example see here for nice visualizations.

Generated Content

Generated Content usually refers to html code that is generated automatically in the course of displaying documents. As such, it is convenient and saves typing html. However, generated content can also refer to program text generated to contain bait for search engines without real creative content.

Spamdexing

A form of generated content, spamdexing, or search engine spamming, are web pages created or modified automatically from other web content expressly to improve rank and attract search hits to a website. Spamdexing is generally regarded as dishonest, though not illegal. Wikipedia has quite a good glossary of terms and techniques related to deceitful search engine optimization techniques.

Clearly, content must be original to boost the search engine rankings. It must also be creative to engage users in a blog, and provide the feedback, contributions, and excitement that forms the basis of an authority site. Ultimately, any shortcuts to search engine optimize that compromise creative quality will, sooner or later, be detected and the engine algorithms modified to drastic effect on your rankings.

Nonstationary Statistics

Nonstationary processes have been defined as random processes whose statistical properties vary over time (see Stationary and Nonstationary Random Processes by Michael Haag).

Nonstationary statistics presents a number of problems. For example, the definition of the power spectrum is a problem, as variation in properties is similar to low frequency noise.

The following is the most succinct statement of the problem of analysing non-stationary statistics I have seen. The following is quoted directly from comments by ‘bender’ starting in comment #18 in response to the post More Tangled Webs at Steve McIntyre’s blog ClimateAudit.

A high AR1 coefficient does not necessarily imply a trend+low AR1 coefficient. However a trend+low AR1 coefficient does lead to a high AR1 coefficient. That is the one of the points these guys are making: AR1 models are an improvement over AR0 models, but they are fraught with their own problems.

The problem with these Hockey Stick-shaped series is that they are nonstationary, so AR coeffs do not have a straightforward interpretation. (Split any time-series at the join of the shaft and blade, compute the PACF and you will see what I mean when you compare the two.) You could take out the trend, to give the coeffs a straightforward interpretation, but then you’ve got the problem of interpreting what it is you’ve taken out, and an autocorrelation analysis certainly isn’t going to help you now.

The purpose of autoregression is to figure out how Xt varies as a function of Xt-1. If they are autocorrelated only indirectly, through the action of some other forcing variable, then the autoregressive model is a bad model, and this badness will revealed when the forcing agent fades in and out (as teleconnections are wont to do).

Bender continues in post #20.

1. For a quasi-demonstration of how a PACF changes when a trend is removed, compare the PACFs of the tropical storm count (with 1970-2005 trend) vs. the landfalling hurricane count (without trend) with which it is strongly correlated (r=0.62 before 1930, r=0.49 afterward). See how PACs 1-4 drop in the detrended series?

2. A clarification for anyone who finds it necessary: the purpose of autoregression is to identify endogenous processes that are persistent through time. Exogenous processes that fade in and out tend to inhibit the estimation of the endogenous autoregressive component, because they introduce a complex nonstationary noise structure.

3. Incidentally, the more dominating the low-frequency exogenous component(s), the lower the precision on the ARMA model estimates. This is the real problem with 1/f noise: you increase your sample size over time, and you inevitably uncover some new “trend” caused by some hitherto unknown exogenous forcing agent. Consequently, it is impossible to obtain an “out-of-sample” sample. (Your new samples come from different populations, which thus nullifies the validation test.)

Thanks Bender…

When The Results Of The Research Are Controversial

In the field of biomedical research, people are often excited when the results of their research are controversial. However, it evoked limited attention when Cell, a scientific journal in the US, recently reported that some Japanese scientists at Kyoto University claimed that four genes or factors transformed mouse cells to act like ESCs (Ethical Embryonic Stem Cells). However, a lot of excitement was created recently when the US, Massachusetts-based, Advanced Cell Research (ATC), said that it has created ESCs without destroying the embryos, as this would seem to remove the principal objection to stem-cell research.

Sep 5. It has just been revealed that contrary to previous claims the team did in fact destroy the embryos according to two “clarifications” issued by the journal Nature. This latest controversy comes only months after the blog-based takedown and public trial of South Korean ESC researcher Hwang Woo Suk.

cell2.PNG

The supporters of ESCs believe that cells from embryos would be used to treat degenerative diseases and injuries of human beings in the future. However, this research has become controversial, since the early-stage embryo is damaged during the process of development. Patrick Goodenough at www.CNSNews.com says that it might be possible to generate ESCs through non-embryonic methods, as shown by the Japanese professors, including, Shinya Yamanaka and Kazutoshi Takahashi. Australasian Bioethics Information, a bioethics clearinghouse, said that making an adult cell revert into ESC would be “one of the great dreams of regenerative medicine.” The agency added that, “If this (Japanese) success can be replicated with human cells, it might indeed transform America’s stem cell politics.”

When The Results of the Research Are Controversial – US and Stem Cell Research

One of the biggest controversies in medical research in the 21st century is whether the human embryos need to be destroyed for creating cells that would be used to cure degenerative disorders and certain diseases. The US government allots limited budget to stem cell research. The US President George W Bush recently vetoed a bill which would have brought more investment into ESC research. There are serious critics within the US Congress of ESC research. According to www.swissinfo.org, Pascale Steck of the Basel Appeal against Genetic Technology, an organization opposing stem cell research, says that people are wondering where these researchers would get the embryos for research purposes and who would decide the usage of the resulting stem cells. Patrick Goodenough says that many people who are opposed to ESC research believe that more funds and attention should be given to research that use adult stem cells that involves non-controversial sources including bone marrow, umbilical chords and lining of the nose.

When The Results of the Research Are Controversial – Vaccines for Obesity

Recently a team of Californian researchers mentioned in the proceedings of the National Academy of Sciences (NAS) that they have developed a vaccine to combat obesity and weight gain. However, Dr William Colmers, A Professor of Pharmacology at the University of Alberta is not convinced by the Californian researchers. Colmers, while cautious about the finding of this controversial research, believes that there must be some potential dangers attached with it.

When the results of the research are controversial, it draws people’s attention. This can lead temptations to exaggerate claims, and finally the field itself, like ESC research, becoming controversial. But controversial results can lead to even more new developments as researchers strive to resolve the controversy with new solutions.

Professional creative content for building your web site and dominating your niche can be ordered here .

Circularity in Spreadsheets – Things to Consider

When you deal with spreadsheets like Microsoft Excel, circularities or circular references may lead to significant problems. Circularities in spreadsheets occur when one code requires information from another code, which requires the information from the first code. Patrick Burns, in his article on ‘Spreadsheet Addiction’ says that the spreadsheets that are available today, including Microsoft Excel and Works, have limitations in terms of operational risks. He goes on to say that some of the spreadsheets in the market available today will go obsolete due to lack of Sarbanes-Oxley compliance.

Many vendors, such as Spreadsheet Advantage (www.Spreadsheetadvantage.com), are there to help you deal with circularity in spreadsheets. Since you have to calculate iteratively when you deal with a spreadsheet with circularities, you might witness higher recalculation time, sometimes ending up with incorrect solutions.

If you are dealing with a large spreadsheet, tracking down all the circularities would be a tedious task. Custom-built software solutions to track down circularities is able to fetch you the circularities in minimal time. All you need to do is submit your spreadsheet containing circularities to the circularity finding software and the software will generate a list of all the circularities in your spreadsheet. Software solutions from vendors such as Advantage for Analysts (www.advantageforanalysts.com) include capabilities like handling circularities in spreadsheets, goal-seeking and optimization.

Continue reading Circularity in Spreadsheets – Things to Consider

New Business Analytics Project

Back after summer break, and deeply involved in a new project to apply niche modeling to business analytics in a completely novel way.

One of the main problems confronting new business owners is defining their market niche. A market niche is a bit like art, you know it when you see it, that is, when you are making a profit. But experimenting with product lines in conventional markets can be time consuming and expensive.

However, the Internet is a whole new world. Instant feedback from customers is possible, and can potentially be used to adjust and refine and optimize your business. Business entities and technologies are becoming an ecosystem in themselves. Niche theory provides a way of looking at it.

A new site called HitTail filters the massive amount of information from hits on your site due to natural search into a list of keywords called ‘suggestion’. These keywords can be used in a number of profitable ways. For example, GaryTheScubaGuy used these unique keywords in Adwords advertising campaigns to greatly reduce costs and increase the effectiveness.

… now my top 10 keywords on this campaign are #1 and I am spending 36% less than I was 3 months ago to be there.

The approach of my business analytics project is guiding and shaping a website or online business into a more profitable niche, a process I describe in the post What is NicheShaping About?. The theory is that using suggestions from HitTail to create novel content will inevitably give more hits on subject matter more relevant to more people. Ideally, the process discovers natural niche markets, and eventually produces total dominance — just like natural ecological processes.

Continue reading New Business Analytics Project