This page contains a Flash digital edition of a book.

strongly shaped by the character of the land which it has replaced. Particularly interesting are those areas that

are briefly inundated before the water recedes and those that end up below or just above a new water margin. I have recently been consulting on the data-analytic aspects of a study of the ecologies adjacent to waterlines in a number of separate, but physically similar valleys. One important strand is ecological comparison between natural lake valleys and those that have become naturally or artificially flooded. A number of similarities and differences (equally interesting and not always unconnected) are coming out of the waterline analyses. (As an aside, the study involves several

different academic, commercial, government and industrial partners, which has produced an interestingly shiſting soſtware ecology of its own. Data moves between heterogeneous, but interacting analysis products, from the commercial Analytica to the open source Xlisp-stat. GenStat is emerging as the landscape dominant species, though there are vigorous colonies of other products including a thriving population of three-dimensional visualisation packages as well as specialised tools such as FragStats.) Dry-land habitats are not just shrunk

by flooding of a valley: they are ruptured, and change their natures. Changes occur at


differing tempos: very rapidly at the water’s edge; more slowly at greater distance from it. Te fauna that continue to inhabit the area change their behaviour to accommodate new realities, while changes in both soil and microclimate affect vegetation. Tere seems to be evidence to suggest that the long-term tendency is for flooded valleys to move towards congruence with naturally occurring lake valleys, but quite profound statistical differences, and statistical processes of change persist between the two for many decades aſter flooding occurs.

Pestilence Disease is a fascinating area of analysis: effectively, it is a term denoting explicit interaction between different ecological layers. In myxomatosis, for instance, a microbiological agent is transmitted through a mammal population by an intermediate-sized biovector. A more topical example is the infection of human tourists by hantavirus carried by mice.

Human shaping of landscapes, for example in the establishment of food or cash crop monocultures, also shapes the epidemiology of ecological linkages. Laboratory work which identifies these links between scales oſten results from statistical analysis of infection patterns; exploring, quantifying, modelling and predicting their ecological effects and implications is an extension of the same analytic process.

War War, in the human sense, has many ecological impacts: some of them akin to fire, flood, and pestilence (though oſten both more acute and more localised), others to industrial pollution or urbanisation. Once again, the degree of statistical complexity reflects the multiple interactions. From another viewpoint, though, constant warfare (or, equally important, strategies for its avoidance), overt or latent, between organisms, populations, species, or competitor types, is intrinsic to ecological equilibrium. Te description and analysis of binding patterns within and between levels here is arguably at a higher level of complexity than any other. Within the complexity, however, are many tractable subsystems. A recently published[4]

study, widely picked

up by mainstream news media, analysed statistically one strategy for the avoidance of ecological conflict. Tigers in Chitwan,

for Missing Data Analysis

In statistical analysis, it is not an acceptable option to simply ignore missing data. Analysis of data with missing values can lead to a biased analysis, incorrect inference and fl awed conclusions. SOLAS for Missing Data Analysis imputes your missing data scientifi cally and accurately; decreasing the bias associated with missing data and potentially reducing the variability in your estimates.


Highlights of SOLAS for Data Imputation:

◗ Choose the best, most appropriate imputation technique for your particular data.

◗ Easily comply with ICH & FDA sensitivity analysis requirements. ◗ Script Language Facility to record and re-run your selections. ◗ Structure your missing data protocols to ensure the most accurate imputations are calculated to achieve your scientifi c and business unit goals.

◗ Readily identify missing data patterns with purpose built Exploratory Data Analysis tools.

Statistical Solutions Stonehill Corporate Center, Suite 104, 999 Broadway, Saugus MA 01906, U.S.A. Tel: +1 781 231 7680 • Fax: +1 781 231 7684 • Toll Free 1800-2621171 Email: Web:

If you have any questions about Missing Data Analysis contact me, Andrew Grannell at


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52