Methali
(proverb)
Asiyekwenda
kuangalia mara kwa mara, hukuta utupu.
One
who does not check/review regularly, finds nothing.
Taking
risks or “going for the moonshot” are a very significant factor for eliminating
stagnation to bring out more factors that are not readily available in the
status quo. There might be undesired/unexpected outcomes, but these should be outweighed
from the benefits of the new factors. This is usually a transcendent scenario
and depends on the objectives and their significance. Within an immanent
scenario, when the immediate objectives only need improvement and the factors
of improvement are known and readily available, reviews are used to reduce unexpected
outcomes. Unexpected outcomes are caused by a lack of consistent regular
reviews. By regular reviews, things like errors and unaccounted factors can be
found, and their elimination will improve the effectiveness and accuracy of the
object of interest. This is the concept of continuous improvement.
Continuous
improvement is an ongoing effort to improve products, services, processes, or
models. These efforts can seek "incremental" improvement over time or
"breakthrough" improvement all at once. Processes are constantly
evaluated and improved in the light of their efficiency, effectiveness and
flexibility. Models are constantly evaluated and improved in the light of their
accuracy.
To
summarize, continuous improvement is a gradual never-ending change which is:
'... focused on increasing productivity, effectiveness, efficiency, accuracy to
fulfil objectives.’
The
key features of continuous improvement in general are:
1.
Feedback:
The core principle of continuous improvement is the (self) reflection of processes.
2.
Efficiency:
The purpose of continuous improvement is the identification, reduction, and
elimination of errors and unforeseen factors that cause less than optimal
results.
3.
Evolution:
The emphasis of continual improvement process is on incremental, continual
steps.
Angalia - 1 look (at), view. 2 pay attention
(to), think, take thought for. 3 be careful, beware. 4 regard, take care of,
review, take special note (of), tend.
Angalifu - accurate, canny, careful, scrupulous,
cautious, circumspect, observant, careful, attentive.
Anga3 – count.
Derived
terms
Verbal
derivations:
Reciprocal:
-angaliana (“look at each other”)
Nominal
derivations:
mwangalizi (“supervisor”)
Conceptual
derivations:
angalifu (“careful, observant, attentive,
accurate”)
Regression
analysis
Regression
analysis is a process for estimating the relationships between a dependent
variable (often called the 'outcome' or 'response' variable, or a 'label' in
machine learning jargon) and one or more independent variables (often called ‘exposures’,
'predictors', 'covariates', 'explanatory variables' or 'features'). The most
common form of regression analysis is linear regression, in which one finds the
line that most closely fits the data according to a specific mathematical
criterion. For example, when one has a variety of data collected over a given
time period (independent variable), through mathematical computation of constant averages/mean, a rough prediction of outcome can be extrapolated. To elaborate,
census data collected and compared over 10-year periods, can be used to compute
average rate of growth to give a rough prediction of expected outcomes at a
certain time in the future. When the projected time arrives, and actual outcomes
are compared to the previously-modelled predicted outcomes, there will often be
a mismatch between the predicted and actual outcome. This can be due to unforeseen
circumstances or due to inaccuracy of the prediction model. To improve the
model, various mathematical interventions are used to uncover losses to inform
how to optimize inputs for the next modelled prediction. The mathematical
interventions used to uncover these losses include ‘mean absolute error’, ‘mean
squared error’, and the more robust ‘hubber loss calculation’ that calculates
error at each data point.
References
TUKI (2001), Kamusi Ya
Kiswahili-Kiingereza; Swahili-English Dictionary. Published by Taasisi ya
Uchunguzi wa Kiswahili (TUKI), Chuo Kikuu cha Dar es Salaam, Tanzania.
Comments
Post a Comment