PHC 274 Saudi Electronic University Data Evaluation Discussion
Description
Two discussion need for response
First discussion need for response :
1- ZAKI ALWABARI
Conducting an evaluation relies on the planning and execution of specific
practices that result in beneficial findings. Data applicable in impact evaluation may
sometimes encounter several challenges, resulting in concerns like poor reliability,
validity, and credibility (Boutron et al., 2019). Threats like biases, external
challenges, timing, and spillover effects affect data quality as they bring about
reliability concerns, credibility, and validity problems in these evaluations.
Biases
Selecting a specific population that will make the evaluation data reliable is a
critical concern. Biases serve as threats because they make it hard for researchers to
communicate accurate results or the impacts of various issues among people
(Boutron et al., 2019). There is a need for the people conducting these evaluations to
involve ethical conduct guidelines as they will prevent biased data collection
decisions. Such a concern will make it possible for data to be reliable during
assessments.
Timing
Timing is another threat that affects data quality when conducting evaluations.
As times keep changing, some information fails to apply among different people,
which requires data collection from reliable sources like surveys (Creevey & Ndiaye,
2008). Conducting impact assessments becomes unreliable if the responsible
individuals affect data quality by seeking information from secondary sources with
findings from past events. This concern, therefore, requires the use of recent and
reliable sources of useful data.
External Challenges
When collecting data for effect evaluations, people may encounter unexpected
events like disasters. Such instances make it hard for the revenant individuals to
collect accurate data during the studies. Disasters sometimes hinder reliable data
collection using primary sources such as surveys (Nita, 2019). Quality of data,
therefore, becomes unaccomplishable because of these events. Technological
advancements may also serve as other threats, including cyber-attacks. These issues
contribute to data processing challenges like system failures. Data privacy regulations
and lack of coordination hinder the prevention of these problems. Forecasting and
accurate planning may be applicable in countering the threats.
Impact Spillover
When impacts spillover, evaluations fail to communicate more accurate
information about their specific concerns. People engaging in the impact assessments
find it hard to learn about implications if people who encounter them are not among
the participants in their studies (Creevey & Ndiaye, 2008). Such a situation hinders
data from being credible and reliable in the evaluations process. More diverse studies
or evaluations are beneficial in countering the challenge.
In conclusion, biases, external challenges, timing, and the impact spillover
hinder data reliability, credibility, and validity. These effects are the ones that make
the above issues threats to the process of impact assessment. The above-discussed
solutions for each threat will enable the reliability, credibility, and validity of data for
impact evaluation in any sector.
References
Boutron, I., Page, M. J., Higgins, J. P., Altman, D. G., Lundh, A., Hróbjartsson, A., &
Cochrane Bias Methods Group. (2019). Considering bias and conflicts of interest
among the included studies. Cochrane handbook for Systematic Reviews of
Interventions, 177-204. https://doi.org/10.1002/9781119536604.ch7
Creevey, L., & Ndiaye, M. (2008). Common problems in impact assessment
research. Impact Assessment Primer Series, 7.
https://beamexchange.org/uploads/filer_public/09/8d/098d6e0b-5ca8-4001-9d29ac53827f67e8/260_pnadn201.pdf
Nita, A. (2019). Empowering impact assessments knowledge and international research
collaboration-A bibliometric analysis of Environmental Impact Assessment Review
journal. Environmental Impact Assessment Review, 78, 106283.
https://doi.org/10.1016/j.eiar.2019.106283
2nd discussion need for response :
2- Ahmed Bukhari
There are several threats to the quality of the data available for effect evaluation. The
data may be biased if the sample of individuals who are included in the evaluation is
not representative of the population of interest. For example, if the evaluation only
includes individuals who have already been treated for the condition under study, then
the results may not be generalizable to the population of individuals who have not yet
been treated. The data may also be of poor quality if the measures used to assess the
outcomes of interest are not reliable or valid. For example, if the measure of the
outcome only captures a limited range of possible values, then the results of the
evaluation may be inaccurate. In addition the data may be affected by confounding
factors that influence the results of the evaluation. For example, if the individuals who
are included in the evaluation are also taking medication that could affect the
outcome, then the results of the evaluation may not be attributable to the intervention
under study.
The quality of data available for effect evaluation depends on what databases were
searched, whether all potentially relevant studies were identified, and whether
appropriate publication biases were controlled for. In general, the greater the number
of records available for effect evaluation, the more likely it is that useful effect
estimates are available.
Data quality is as important as the data itself. The availability and accuracy of the data
is paramount to the study’s ability to demonstrate effect outcomes, such as the
effectiveness of a new product or process in effort to improve performance and reduce
costs, minimize waste and/or provide other appropriate benefits. It is critical that
representatives from all affected areas collaborate to ensure that the impacts of data
quality on the outcome of studies are adequately considered.
•
•
References
Cheng, H., Feng, D., Shi, X., & Chen, C. (2018). Data quality analysis and cleaning
strategy for wireless sensor networks. EURASIP Journal on Wireless
Communications and Networking, 2018(1), 1-11.
Casado‐Vara, R., Prieto‐Castrillo, F., & Corchado, J. M. (2018). A game theory
approach for cooperative control to improve data quality and false data detection in
WSN. International Journal of Robust and Nonlinear Control, 28(16), 5087-5102.
Purchase answer to see full
attachment