Please enable JavaScript.
Coggle requires JavaScript to display documents.
ANALYTICAL APPTITUDE, Defined as the KSAOs needed to collect and analyze …
ANALYTICAL APPTITUDE
DATA SOURCE
Quantitative and Qualitative Data
and Assessing
Validity
hiệu lực
of Sources
QUANTITATIVE = HARD
which
are objective and measurable
and can be stated in such terms as frequency, percentage, proportion, or time e.g.
the number of….
QUALITATIVE = SOFT
data
which are more intangible, anecdotal
không hoàn toàn đúng
, personal, and subjective, as
in opinions, attitudes, assumptions, feelings, values, and desires
.
Measurements
can be made
by a third party observer/self assessments
Assessing
Validity
of Data Sources
Does the source have
authority
? A government agency, such as a labor department or ministry, or an academic institution is more credible than a blogger.
What are the source’s
possible biases
? Bias can lead to “
cherry picking
” data—including
only the facts that support a certain position
.
Are the sources for data used in a publication
clearly cited
trích
dẫn
? And are those sources
reliable and accurate?
Are the
facts relevant
? For example, data about trends in one industry may not apply to all industries.
Is the data
current
? Some concepts are classic, but data is subject to variables that can weaken its relevance over time. For example, data from a recessionary
suy thoái
period can be highly inaccurate in describing conditions in an expanding economy.
If the data is
being offered as proof of an argument
, is the argument itself sound? Are its deductions from the data logical?
1. INTERVIEW as Data Source
offer the opportunity for
follow-up questions that may not be possible in a survey
or may be discouraged by the size, composition, or timing of a focus group
:green_cross: ADVANTAGE:
Safer
, confidential environment may
generate significant information.
Comments can
suggest direction
for further group research (focus groups and surveys).
:red_cross: CHALLENGES
Can be
time-intensive
Requires strong relationship-building skills
Requires vigilance
cảnh giác
to
avoid bias
from influencing questions
and interpretation
sự diễn kịch
of answers.
EFFECTIVE
Interviewing
:check:
Trust
building relationship
:check:
Confidence
should be
respected
:check: Start with
safe questions to build rapport
2. FOCUS GROUP as Data Source
Small group
(6-12)
invited to
actively participate in a structured discussion
with a
facilitator
.
From 1 to 3 hours
Serve a
variety of purposes
collect qualitative data
that
enriches quantitative survey results
CONSIDER WHEN PLANNING
a focus group
:question:The importance of
planning
:question:The
context
in which a focus group might occur
:question: The importance of the
facilitator
:question: The importance of the
recorder
4 TOOLS
MIND-MAPPING
:
Begin with core ideas
. Add related ideas & indicate logical connections
AFFINITY DIAGRAMMING
:
sorting
a large amount of data.
Categorizes & subcategorizes
data until relationships are
clearly drawn
NOMINAL GROUP TECHNIQUE
:
each suggest ideas until no further idea
. Proceed thru rounds, discuss & eliminate until agreement
DELPHI TECHNIQUE
:
Anonymous rounds of ideas
, to facilitate group involvement, problem solving, & individual thinking
avoiding “group think,”
SURVEY & QUESTIONNAIRE
as Data Source
Inexpensive, large amount of data but
may have
low response rate
:red_cross:SERIOUS
CHALLENGES
remain
Obtaining a valid sample:
needs make sure the
number of returned
surveys is sufficiently
large to be representative
and that the group responding accurately reflects the attributes of the entire group
2.
Designing the survey with analysis in mind:
Questions
should be asked in a way that
makes compiling and comparing responses easier
Asking the right questions:
various internal and external environmental factors that can affect attitudes and work
:green_cross:ADVANTAGES:
Efficient way to
gather a lot of data
from a large and dispersed
phân tán
group
Easier to quantify data
for analysis and reporting
OBSERVATION
as Data Source
First-hand, unfiltered
data
but
may
not
be
representative
:green_cross: ADVANTAGES:
Provides firsthand and immediate data
rather than self-reported data, which can be affected by memory and selectivity.
Is
time-efficient
for subjects.
:red_cross: CHALLENGES
Requires skill to be unseen
. When the group is very aware of the observer, the data becomes less reliable.
Requires vigilance
cảnh giác
to r
emove personal bias
from observations.
Requires experience
to
note significant behaviors
.
Observations
may not be representative
of the entire body of data (i.e., the totality of every meeting, every work process, every transaction).
Gather data
by observing the workplace and work processes.
Observation can
also strengthen the HR professional’s understanding of the work at hand and the culture of the workplace.
EXISTING DATA & DOCUMENT
as Data Source
Eliminate bias but can be time-intensive-
:green_cross:ADVANTAGES
Eliminates
the effects of observation and involvement and possible
bias
of facilitator/interviewer/observer
Rich, multi-perspective source of data
:red_cross: CHALLENGES
Can be
time-intensive
Requires experience
to
extract key data
May require
ingenuity *
khéo léo* to find data
Include information from the organization itself, from public information sources (for example, government agencies), or from industry/professional associations.
Official documents
Performance data
Correspondence and reports
ARTIFACTS
hiện tượng
as Data Source
may be
best used when
they
confirm or conflict
with findings
gathered by other means
a researcher can misinterpret
giải thích sai
the meaning and importance of artifacts.
Are objects created by members of a culture
that convey a sense of that culture’s values and priorities, beliefs, habits and rituals
nghi lễ
, or perspectives. Concludes
Physical workplaces:
suggest characteristics of organizational culture
Virtual environments
:green_cross: ADVANTAGES
Provides
additional insight into cultural issues
Can be observed
without the help of those being observed
:red_cross: DISADVANTAGE
Requires
researcher
to understand the principles of culture
Can
create misunderstandings
if
the researcher is
not familiar with the culture.
7. MARKETING DATA
as Data Source
HR professionals may need marketing data to aid in workforce planning or establishing a business case.
better understand target audiences
or certain segments of society and/or business
In addition to these publicly available sources of data, there are
many respected private market research companies who
gather data that can be syndicated by other organizations
. Some examples include Ipsos, Nielsen, and Gartner.
TOWARD BETTER BUSINESS DECISION
Analytical Aptitude &
Evidence-based Decision Making (EBDM)
ANALYTICAL APTITUDE
: refers
Examining
an idea/ process/ event
with an open, objective & inquiring mind
.
EBDM
: Using
sound data to hypothesize
đưa ra giả thuyết
,
assess & select solutions
Data advocacy:
what
data drives the business
and where it can be found
Data gathering:
what constitutes
cấu thành
sufficient, credible
đáng tin cậy
, and
objective evidence
and being able to find it
Data analysis:
organize data
so that it
reveals*
tiết lộ
patterns
and to analyze it
*to detect logical relationships
EBDM
:
apply the results
of data gathering and analysis
to make better business decisions
How to Become an
HR Data Advocate
???
5 STEPs
Develop a questioning mind
: try
not to accept the status quo
. They are naturally curious about everything
Build fluency in the scientific literature for HR
:
identify new and reliable sources of data
, monitoring the topics that are being discussed
Gather data on a continuous basis
: the
efficacy
and
efficiency
of legacy systems and stakeholder interests
:!:
Efficacy
is getting things done. It is the
ability
to produce a desired amount of the desired effect, or success in
achieving a given goal.
:!:
Efficiency
is doing things
in the most economical way.
Use evidence when communicating
: recommend solutions and include the data supporting their analysis and recommendations
Institutionalize
thể chế hóa
the competency in HR function
: establishing journal study groups
6 Steps
in EBDM
ASK
: translate the situation into a
question
that can then
be answered through information gathering
ACQUIRE
:
Gather information
from varied sources
APPRAISE
:
Determine
whether the
evidence gathered
is relevant, valid, reliable, accurate, complete, and unbiased
AGGREGATE
tập hợp
:
Combine and organize
the data to prepare it for analysis.
Determine the priority
to be given to different types of information
APPLY
: See the
logical connections
🡪 draw
conclusions
, develop
possible solutions
,
decision, and take action
ASSESS
:
Monitor the solution
that has been implemented and objectively measure the extent to which the objectives have been attained
đạt được
STATISTICAL PRINCIPLE
Statistics
:
Collection, organization & analysis
of large amounts of
numerical data
Reliability and Validity
of Data,
Statistical Sampling
lấy mẫu thống kê
RELIABILITY
reflects the
ability of a data-gathering instrument or tool
, such as a survey or a rater’s observation or a physical measurement,
to provide results that are consistent
VALIDITY
tính hợp lệ
is the ability of an instrument
dụng cụ
to measure what it is intended to measure
. Validation
answers two questions:**
What does
the instrument measure
?
How well
does the
instrument measure it
:check: Validity reflects the degree to which a tool measures attributes that are to the measurement’s intention.
Tính hợp lệ phản ánh mức độ mà một công cụ đo lường các thuộc tính phù hợp với mục đích của phép đo.
STATISTICAL SAMPLING
is often
used when the population to be analysed is very large
or when data cannot be obtained from the entire population.
Errors and Bias
in Statistical Analysis:
ERRORS
may be introduced into a statistical study when:
Incorrect data
is used. A measurement may be taken incorrectly, or a number may be entered incorrectly.
A study’s design
includes
, intentionally or unintentionally,
different types of biases that affect outcomes.
BIASES
could involve
Sampling
:A sample may
not represen
t the general population
Selection
: can occur in a controlled study when
participants are not randomly assigned
to control and experimental groups.
Response
: This is the
inverse of selection bias
Performance
:
Participants
in a controlled study
behave differently because they are being studied
Measurement
: Raters are
measuring incorrectly
, either unintentionally or intentionally
Data
CLEANSING
“
Data Wrangling
": process by which incomplete sets, anomalies, errors & gaps in the
data are identified & addressed
công việc xử lý dữ liệu để biến dữ liệu thô thành dữ liệu thích hợp
Connected to validation and identifying bias
, as these processes assess how useful and correct the data is 🡪
ensure that decisions are made based on better-quality data
Not an ad-hoc process,
should embed into org culture
DATA
MEASUREMENT TOOLS
Measures of
CENTRAL TENDENCY
xu hướng trung tâm
MEDIAN (50th percentile)
Is the Middle value in range of value
Preferer when the distribution in a dataset is skewed (contains a few excessively high or low values
MODE
Most frequently
occurring value in dataset
MEAN/ARITHMETIC
is the
average
score or value
Calculated by 2 ways
Unweighted MEAN
: sum of all values/ no. of values
Weighted MEAN:
Individual values multiplied by a factor that adjusts the value, when the values are not considered equally impactful 🡪 reflect skew toward 🡪 often used in creating scales for evaluation
RANGE
: The difference
between
the
highest
number
and lowest
number
FREQUENCY DISTRIBUTION
phân phối tần suất
QUARTILES
and
PERCENTILES
describe dispersion
phân tán
across a group of ranked data. Are f
requently used in benchmarking
Quartiles divide a data set into quarters. A quartile ends at a certain percentile
A percentile indicates the proportion of the dataset at a certain percentage
are
used to sort data
into groups according
to some factor
, such as years of employment
allows analysts
to understand the distribution of the data
STANDARD DEVIATION
Distance
of any data point from center of a distribution when data
is distributed in a “normal” or expected pattern
Khoảng cách của bất kỳ điểm dữ liệu nào từ trung tâm phân phối khi dữ liệu được phân phối theo mẫu "bình thường" hoặc mong muốn
Data curve shape
Low SD
🡪
Curve is high and narrow
High SD
🡪
curve is flatter, more spread out
DATA
ANALYSIS TOOL
6 APPROACHS
VARIANCE ANALYSIS
identifies
the degree of
difference between planned and actual performance
:check: usually applied to analysis against objective baselines, such as
schedules and budgets
TREND ANALYSIS
examines data from different points
in time to
:check:
determine
if a
variance
is an
isolated *
đơn lẻ
event
or
if it is part of a
longer trend
:check: can also be used to
forecast future conditions
, such as the ability of an initiative to meet its objectives
:check: are
important tools
in discovering
recurring peaks
đỉnh
or troughs
đáy* in an activity
RATIO ANALYSIS
compares
the relative size
of two variables and yields a percentage
ROOT-CAUSE ANALYSIS
starts with a result and then works backward = Toyota 5 WHY method
Each cause is queried to
identify a preceding cause
,
then
proceed
backward
in rounds
until the fundamental or root cause is identified
= the point at which
no further causes can be identified
REGRESSION ANALYSIS
phân tích hồi quy
refers to a statistical method
used to determine
whether a
relationship exists between variables
and the strength of the relationship by scattergram
:check:
determine the most significant indicators of success in a given job
,
testing variables
such as recruitment source, education, job experience, personality type, and so on
against job performance ratings.
SCENARIO/ WHAT IF ANALYSIS
:check: be used to
test the possible effects
of altering the details of a situation
to see how the outcomes will vary under different conditions
USING DATA TO SUPPORT BUSINESS CASE
A business case
that
successfully establishes how a specific problem or issue is to be resolved
or addressed must include data
. Process are
BUSINESS CASE
A successful business case
must include data
🡪 make decisions based on reality and evidence 🡪
show how they align with organizational strategy
Tell a fact-based story
/ narrative
Understanding organization strategy 🡪 compile relevant data 🡪 t
ell the correct story to the correct audience
.
Challenge of disposition of report-generating groups
🡪 request information and reports across organization 🡪 breakdown information silos 🡪
dataset out of isolation
Know
how to turn information into a narrative
, and that’s where interpretation, visualization, and graphical representation come in
Step 3: RISK & OPPOTUNITIES
What are risks
associated with each option?
What
risk if not doing
?
Opportunities = outcomes which require action
Step 1: EXECUTIVE SUMMARY
The
purpose
of the project. (What is the problem...)
The
condictions or change
... (Why need to do? Buz opportunities.
Step 2: RECOMMENDED SOLUTION
How can we address
the problem? Options available to implement solution
Define desirable outcomes
of an ideal/chosen solutions
Step 4: ESTIMATE COST & TIME FRAME
Define the
budget & timeline
Propose
Project charter
(Project members, objectives, key milestones and forecast budget)
GRAPHIC DATA
Analysis Tools
often used
to support analysis and visualize results
PIE CHART:
:check: To
present a high-level impression
of the data distribution
as a percentage
of a whole
HISTOGRAM / BAR CHART:
:check:
To sort data
a
n
d to support rapid
comparison of categories of data
TREND DIAGRAM:
Plots data points on two axes. The horizontal axis usually represents time, while the vertical axis represents volume.
:check: Can be
used to test for presence of cycles or developing trends.
E.G. analyzes workforce demand to identify overall trends in demand as well as high and low points in the calendar year.
PARETO CHART:
Applies the
Pareto principle (that 80% of effects come from 20% of causes)
:check:
Distinguishes between the “vital few” categories
that contribute most of the issues
and the “trivial many” categories
of infrequent occurrence
to support more-focused quality improvement activities.
E.G. analyze and illustrate
causes of voluntary and involuntary employee
separation from the organization.
SCATTER DIAGRAM
: Plots data points against two variables that form the chart’s x and y axes. Each axis is scaled
:check: Can be
used to test possible causal relationships and narrow focus on subsequent tests.
E.G. HR professional maps the correlation of
workplace accidents with a series of factors,
such as access to safety training
Defined as the
KSAOs
needed to
collect and analyze qualitative and quantitative data
, and to
interpret and promote findings
that evaluate HR initiatives and inform
business decisions and recommendations.
