Data Analysis Design: An Employee's Perspective

Running head: IBRM
Assessment 4: Methods of Analysis of Data
Research title: An analysis of the impact of leadership style on employee’s
performance: A case study of Woolworths limited'

IBRM 2
Table of Contents
Data analysis design......................................................................................................... 3
Step 1: Data Validation.................................................................................................. 3
Step 2: Data Editing...................................................................................................... 3
Step 3: Data Coding...................................................................................................... 4
Quantitative Data Analysis Method...................................................................................... 5
Descriptive Statistics..................................................................................................... 5
References................................................................................................................... 20

IBRM 3
Data analysis design
Data Preparation
The initial phase for assessing data is the preparation of data in which, aim is to transform the
raw information into something readable as well as, meaningful. Followings are some phases for
assessing quantitative data:
Step 1: Data Validation
In this research study, initially, researcher would validate the data. Main aim of data validation is
to address whether data collection would be performed according to pre-set standards without
any partiality. Researcher would focus on given factors during data validation:
 Fraud can be supposed with respect to whether each participant would be really
interrogated or not
 Screening and ensuring that participants would be selected according to criteria of
investigation
 The process is properly followed to assess whether data gathering would be considered
(Laitinen & Senoo, 2019).
An investigator would make sure that all questions would be asked with participants as compared
to few required ones. For completing this, an investigator would require to pick a random sample
for completing a survey as well as, validating the gathered information. This could be time
taking for surveys due to number of responses. For instance, survey would be conducted on 50
participants of Woolworths. Subsequently, an investigator would reach out via email and check
their responds on specific set of questions (Schaffner, et. al., 2015).
Step 2: Data Editing

IBRM 4
In this step, researcher would create larger data sets because there is chances for occurring errors.
For illustration, respondents could fill fields inappropriately and skip them unintentionally. In
order to ensure that there would be no such error; an investigator would conduct basic
assessment of information, ensuring outliers, editing raw research information for addressing as
well as, clear out any point of information, which may hinder accurateness of outcomes (Stein,
et. al., 2017). For instance, an error can be in a field that would leave empty through participants.
When editing data, researcher would remove and fill all vacant fields. In addition, researcher
would focus on developing an organising as well as, compressed manner in terms of arranging
information via charts, text, and diagrams. This display would be supportive in order to
identifying themes, structures as well as, connections that support answering the evaluation
questions (Farmer, 2017). In this phase, researcher would focus on coding in which, they mark
passages of text that have the same message as well as, are linked in some manner. A researcher
will also write associated elucidation regarding what the selected passages have in common
(Render & Stair Jr, 2016).
Step 3: Data Coding
This is significant phase in preparation of data. In this phase, researcher will assign as well as,
creating set of values in responses within survey. For example, after selecting 50 individuals for
survey, researcher would address the number of participants through their average groups that is
shown as above table. An investigator would also develop age buckets as well as, categorizes age
of each of participants according to these codes. For illustration, participants among 25-30 years
were 60.00% and 31-40-years age of people were 20.00%.
In this phase, researcher would choose, emphasize, summarise as well as, transform data. The
procedure would be instructed through thinking regarding which information provides the best

IBRM 5
answer to evaluation questions. The procedure of transforming information would be related to
performing data analysis and identifying research objectives (Tricco, et. al., 2016).
Problems with Data Transformations
Median Split
A researcher would divide data set into two categories through placing participants below
median in one group as well as, participants above median in another. The strategy is best
implemented when data do certainly exhibition bimodal features. Infeasible collapsing of
constant variables and categorical variables avoids data within untransformed value (Turker,
Dunn, &Wilkie, 2017).
Calculating Rank Order
Ranking data would be summarized by performing a transformation of data. The transformation
would entail multiplying frequency by ranking score to each selection at the new scale.
Computer Programs for Analysis
In this investigation, spreadsheets could be used through Excel software. But, statistical software
i.e. SPSS (Statistical Package for Social Sciences) could be applied by a researcher to develop
better understanding regarding research issues.
Quantitative Data Analysis Method
Descriptive Statistics
The elementary change related to raw data in a manner defines the basic features like variability,
central tendency, and distribution. It is supportive for the investigator to summarise information
and address patterns. The given below are practiced for descriptive statistics:
 Mean: Numerical average regarding the set of data
 Median: Midpoint related to set of numerical amount

IBRM 6
 Mode: Common values between the set of values (Farmer, 2017).
 Percentage: It is practiced for expressing how value and set of participants within data
associated with a higher set of participants
 Frequency: number of times a data is found.
 Range: Highest and minimum values in set of values (Kuang, et. al., 2018).
Descriptive statistics offer unconditional numbers. However, they do not illustrate reasoning
behind those amounts. Before implementing descriptive statistics, it is significant for researcher
to think regarding feasible technique for research question as well as, needs to focus on data that
needs to demonstrate. For instance, percentage is feasible mode for demonstrating gender
distribution of participants (Hartas, 2015). Descriptive statistics is effective while an
investigation is limited to sample as well as, does not require to be generalized to a higher
population. For instance, when a researcher is addressing the impact of leadership style on
employee performance then descriptive statistics is adequate. Since, this technique is highly
implemented for assessing single variable and it is known as univariate assessment (Röst, et. al.,
2016).
Age-group
Mean 16.66666667
Standard Error 6.666666667
Median 10
Mode 10
Standard Deviation 11.54700538
Sample Variance 133.3333333
Kurtosis #DIV/0!
Skewness 1.732050808
Range 20
Minimum 10
Maximum 30
Sum 50
Count 3