is it a correct prediction?

Forecasting annuals from monthly data

Оценка годовых показателей по, звиняюсь, месячным -- увлекательное занятие, вполне заменяющее гадание на кофейной гуще. Как утверждают эксперты (без имён) по 6 месяцам прикинуть можно, а уж по 9 вполне и угадать. К примеру, число смертей или тех же рождений.

В прошлом году тт тандемотянитолкаичы всё ждали естественного прироста населения, годового. Он даже наблюдался в некоторых месяцах, даже подряд временами, но, сцуко, Росстат начальства не послушался, и, как всегда, показал ессную убыль населения, хотя и небольшую и перекрытую сальдом миграции, от которой у нек-рых г-ваба литъ.

Forecasting annual totals from monthly data
запись в блоге Роба Хиндмана, кроме этого предлагает и R код, но немного для другой задачи, но похожей

продолжение банкета в ФБ

MicMac Software

The MicMac software was developed at the Max Planck Institute for Demographic Research in Rostock. The software development was guided by the following principles:

1. The software should be free with no license restrictions. Transparency is mandatory. Open-source software is used to give the user the freedom to make adjustments and extensions. 
2. The software should be computationally efficient to handle large numbers of individual life courses with relatively large attributes (states). 
3. MicMac provides tools without forcing the user to adopt the solutions we suggest. Well-defined interfaces should assure flexibility and freedom. 

The MicMac software structure consists of a pre-processor, a processor and a post-processor. The pre-processor is a suite of R functions to estimate transition rates from data and to prepare the input data. The processor performs the actual simulation. It consists of two modules: a module that implements the cohort-component model (Mac) and a module that implements the microsimulation (Mic). The latter module is referred as the MicCore. It is written in Java. The postprocessor is a suite of R functions to tabulate, summarize and graphically display the results.

 The MicMac software is freely available on the website of Max Planck Institute for Demographic Research

forecasting manual

Wel­come to our new online text­book on fore­cast­ing. This book is intended as a replace­ment for Makri­dakis, Wheel­wright and Hyn­d­man (Wiley 1998).

The entire book is avail­able online and free-of-charge. Of course, we won’t make much money doing this, but text­books never make much money any­way — the pub­lish­ers make all the money. We’d rather cre­ate some­thing that is widely used and use­ful, than have large pub­lish­ers profit from our efforts.

Even­tu­ally a print ver­sion and a down­load­able e-version of the book will be avail­able to pur­chase on Ama­zon, but not until a few more chap­ters are written.

This text­book is intended to pro­vide a com­pre­hen­sive intro­duc­tion to fore­cast­ing meth­ods and present enough infor­ma­tion about each method for read­ers to use them sen­si­bly. We don’t attempt to give a thor­ough dis­cus­sion of the the­o­ret­i­cal details behind each method, although the ref­er­ences at the end of each chap­ter will fill in many of those details.

The book is writ­ten for three audi­ences: (1) people find­ing them­selves doing fore­cast­ing in busi­ness when they may not have had any for­mal train­ing in the area; (2) undergraduate stu­dents study­ing busi­ness; (3) MBA stu­dents doing a fore­cast­ing elec­tive. We use it our­selves for a second-year sub­ject for stu­dents under­tak­ing a Bach­e­lor of Com­merce degree at Monash Uni­ver­sity, Australia.

For most sec­tions, we only assume that read­ers are famil­iar with alge­bra, and high school math­e­mat­ics should be suf­fi­cient back­ground. Read­ers who have com­pleted an intro­duc­tory course in sta­tis­tics will prob­a­bly want to skip some of Chap­ters 2and 4. There are a cou­ple of sec­tions requir­ing knowl­edge of matri­ces, but these are flagged.

We use R through­out the book and we intend stu­dents to learn how to fore­cast with R. R is free and avail­able on almost every oper­at­ing sys­tem. It is a won­der­ful tool for all sta­tis­ti­cal analy­sis, not just for fore­cast­ing. See Using R for instruc­tions on installing and using R.

The book is dif­fer­ent from other fore­cast­ing text­books in sev­eral ways.

• It is free and online, mak­ing it acces­si­ble to a wide audience.
• It is con­tin­u­ously updated. You don’t have to wait until the next edi­tion for errors to be removed or new meth­ods to be dis­cussed. We will update the book frequently.
• There are dozens of real data exam­ples taken from our own con­sult­ing prac­tice. We have worked with hun­dreds of busi­nesses and orga­ni­za­tions help­ing them with fore­cast­ing issues, and this expe­ri­ence has con­tributed directly to many of the exam­ples given here, as well as guid­ing our gen­eral phi­los­o­phy of forecasting.
• We empha­sise graph­i­cal meth­ods more than most fore­cast­ers. We use graphs to explore the data, analyse the valid­ity of the mod­els fit­ted and present the fore­cast­ing results.

Use the table of con­tents on the right to browse the book. If you have any com­ments or sug­ges­tions on what is here so far, feel free to add them below.

Happy fore­cast­ing!

Rob J Hyn­d­manGeorge Athana­sopou­los
March 2012.

book site

Health care under aging

Estimating the future healthcare costs of an aging population in the UK: expansion of morbidity and the need for preventative care

Background The healthcare costs of an aging population have major consequences for healthcare organizations and have major implication for strategic planning of services. An impending freeze in budgets in the UK makes these consequences especially significant.
 Methods We present a methodology of estimating the future healthcare costs to an organization due to an aging population that takes account of the excess costs in the years before death and the effect of morbidity compression or expansion. The performance of three different models is evaluated.
Results The three models all give markedly different estimated costs. Models failing to take into account both the cost burden towards the end of life and compression or expansion of morbidity can vastly under- or overestimate the most accurate estimates of healthcare expenditure due to an aging population with annual increases in costs varying from 0.48 to 1.12%.
 Conclusion The importance of being able to accurately predict demand and costs of health care within the NHS cannot be underestimated. Making over simplistic assumptions and not using well-established principles in these models leads to greatly different outcomes that have the potential to have massive organizational consequences in terms of short-to-medium term strategic planning. Key words economics management and policy morbidity and mortality

Could Demographic Trends Cripple Europe by 2050?

Demography is destiny. This axiom is underlined by HSBC's "World in 2050″ survey.
The bank's detailed analysis is based on the theoretical work of Harvard professor Robert Barro. It analyzes everything from fertility rates to education levels and the rule of law, and predicts that the world's economic output will triple by 2050, provided the major states can avoid conflict. However, a grim future seems assured for much of continental Europe.
A birth rate of 2.1 children per woman will keep a society stable in population terms. However, according to the Daily Telegraph: "The low fertility of Korea (1.1), Singapore (1.2) Germany (1.3), Poland (1.3), Italy (1.4), Spain (1.4) and Russia (1.4), more or less dooms these countries to aging crises and population decline unless they open the floodgates to immigration."
For this reason Britain is likely to displace Germany as Europe's leading economic player: "This is chiefly due to the UK's healthy fertility rate (1.9), although skeptics might question whether a birthrate inflated by the EU's highest share of unmarried teenager mothers is a good foundation for prosperity."
US birthrates will also keep America a major player in to mid-century: "America's high fertility rate (2.1) will allow it too keep adding manpower long after China's workforce has begun to contract in 2020s and as even India starts to age in the 2040s."
"Demography matters," said Karen Ward, the report's chief author. The "big losers," she says will be the smaller states like Switzerland, Netherlands, Sweden, Belgium, and Austria, which will mostly drop out of the top 30: "They may struggle to maintain their influence in global policy forums."
The EU's own figures bear out a looming demographic crisis in Europe: Eurostat last year released the figures showing that in 2009 Italy's fertility rate remains one of the lowest in Europe. For any population to remain stable, it needs a "total fertility rate" of 2.1 children per woman. Italy has an average of only 1.31.
The Milan-based International Center for Family Studies has explored the country's ultra-low birth rates which have resulted in a rapidly aging nation. Their recent report on Italian population levels says that despite high levels of foreign immigration, 2009 statistics show a significant decrease in the Italian population.
Their study found that 57.8 percent of childless Italian households said they had no children out of "personal choice." Reasons given include a sense of uncertainty about the future and the difficulties involved in raising children.
Some demographers now hypothesize that Italy, along with many other European nations, has entered a "low fertility trap" -- a sort of death spiral where a nation tips over a demographic cliff, never to recover.
The "low fertility trap" hypothesis was pioneered by demographer Dr. Wolfgang Lutz of the Vienna Institute of Demography. Proponents note that no society has ever recovered from a sustained birth rate of under 1.5 children per woman.
This is because after a few decades of very low birth rates, very simply, there are no longer enough potential mothers to have enough children to recover, and an irreversible downward spiral begins. Simultaneously, they say, a more subtle cultural shift also occurs: childlessness and small families become the norm, thereby institutionalizing the trend of low birth rates.
An example of this self-reinforcing cultural change has been noted Germany, where thirty per cent of young women say they don't intend to have children at all. 48 percent of German men under 40 nowadays agree that you can have a happy life without children. When their fathers were asked the same question at the same age, only 15 percent agreed.
Unsurprisingly, given the prevalence these opinions, Germany now even surpasses Italy as the EU nation with the lowest birth rate and is also heading toward population collapse.
Demographer Peter McDonald estimates that if Italy's recent fertility levels remain as they are, bar mass immigration, it will lose 86 percent of its population by the end of this century, falling to a population of 8 million, down from 56 million today. Similarly, he estimates Spain's population will drop by 85 percent, Germany 83 percent and Greece 74 percent.
Not since the Black Death stalked Europe in the Middle Ages have we seen populations collapse like this.

источник

полезные вещи с сайта Гриффита Фини

собственно блог Фини (хотя это и не блог совсем, но теперь -- всё блог)
кто это такой, см тут (пдф)

• Component Projection Tutorial: Part 1
• Population Projection by Spreadsheet