Advice for Beginning Consultants
In a consulting relation- work involved in data analysis.
ship, statisticians need to lay Clients should know that data
‘ground rules’ early on for management and model ade-
coauthorship, consultation quacy checks are important
length, and remuneration. It aspects of data analysis and
is important that clients are help yield the best results.
clear about our expectation It has been said that “research
of coauthorship so our efforts not published” is “research not
do not remain unrecognized. done.” It is also thought bet-
This can be done if the rela- ter to leave a research ques-
tionship between client and tion unanswered than to carry
statistician is built in a man- out analysis that answers the
ner that minimizes difficulties question and leaves the results
associated with our becoming unused or, worse, hidden from
coauthors. In academic set- publication. Thus, in the early
tings, for example, some stat- stages of consultation, we
isticians waive payment for should inquire about the util-
services rendered in exchange ity of the results if they are to
for coauthorship with gradu- fall in either extreme of pos-
ate students or faculty. sible findings. If the extremes
research projects or questions that can be answered
It is also important that are not useful, the collabora-
using data from an existing project. To heighten
we apprise clients of the tor should be encouraged to
interest, it may even be necessary to modify a main
period that will be dedicated reconsider doing the project.
research question or objective.
to direct consultation or col- Often, decisions that have to
What can we do to promote uptake of data
laboration in preparation of be made based on the results
analysis findings by relevant stakeholders? We can
manuscripts for publication. are subject to managerial and
encourage our clientele and collaborators to practice
The acceptable remuneration budgetary constraints, rather
their presentations in front of us prior to present-
for services rendered must than statistically significant dif-
ing them in a more public domain. In addition, we
also be discussed and agreed ferences. Nevertheless, analysis
should feel privileged to see manuscripts based on
to early in the consultation. carried out can illustrate the
our work prior to their submission for publication.
Profitable discussion regard- best- and worst-case scenarios,
And, when possible, we should accompany collabo-
ing remuneration will make even if there cannot be direct
rators to the meetings at which they present find-
our clientele aware of the implementation of findings.
ings based on our data analysis.
Use of complex statistical methodology for data
analysis often produces more robust results that, if
used to drive policy decisions, could lead to more
appropriately targeted interventions. Unfortunately,
such results do not go beyond the journal in which
brown-bag lunches, and journal clubs at which
they are published at times, leaving human welfare
we learn each other’s languages. At all levels of the
deprived of further development. We must make
institutions in which we work, we should encourage
intense efforts to convert our findings to language
statistical thinking. We should encourage researchers
that stakeholders can apply. This can be aided by
and academics to publish data analysis findings that
the use of short, simple sentences and appropriate,
answer even simple research questions. Such publi-
easily understood pictures. It is also important that
cations, written in a manner readily understood by
we simplify results for newspapers, newsletters, and
those who really need to use the findings, will more
the general media. We have to be especially mindful
readily lead to the widespread use of statistics.
of whether our collaborators can explain results to
There are times when lack of interest in a project
the media in a clear and correct manner.
or research question leads to impaired and ineffec-
As statisticians, we carry out highly valued work
tive collaboration. It is useful to encourage other
that can greatly improve human welfare. Let us
specialists in the research team (e.g., public health
make every effort to maximize our efforts through
specialists or epidemiologists) to develop their own
effective collaboration and education. n
12 AmstAt News NOVEMBER 2009
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 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76