Page 2730
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
Leveraging Financial Data for Research: An Empirical Demonstration of
Statistical Tools on Key Variables
Dr. R. Jayaraman
1
, Dr. M. S. Ramaratnam
2
1
Associate Professor,Department of Management Studies SCSVMV (Deemed to be University) Enathur,
Kanchipuram,Tamil Nadu
2
Professor Department of Management Studies SCSVMV (Deemed to be University) Enathur,
Kanchipuram,Tamil Nadu
DOI:
https://doi.org/10.51583/IJLTEMAS.2026.150500221
Received: 27 May 2026; Accepted: 01 June 2026; Published: 18 June 2026
ABSTRACT
The paper has made an attempt to understand the application of financial variables on research. The paper has
identified some key variables in accounting and finance and the way the ratios show the relationship among the
variables. The paper has brought forth statistical application of accounting variables for selected companies
during the period. By applying the technique of ANOVA, it is understood that the selected companies employ
different amount of debt during the period by showing the significant difference in terms of leverage ratio. The
application of correlation and regression techniques show the relationship between Non-Performing Asset
(NPA) and Return on Equity (ROE)and the extent to which ROE is affected by NPA for the selected period by
taking into account of various banks. With the help of Altman Z score the discriminant analysis is carried out to
identify the financial health of the firm for the selected period.
Keywords: Leverage Ratio, Return on Equity, Non-Performing Assets, ANOVA, Z score.
INTRODUCTION
Financial statements are prepared to understand the financial position of firm. Financial statements are referred
by various stakeholders such as Investors, Suppliers, Employees, Tax authorities, Government, Competitors and
customers. In this line, financial statements of corporates are used by researchers too. The Information extracted
from the financial statements are considered to be the data and the financial statements are the data sources for
carrying out Industrial and academic research. As the financial statements are audited statements, the data
extracted therefrom stands reliable and valid for research. The data extracted from the financial statements are
known as financial / accounting variables. The accounting variables are interrelated to each other and one or
more accounting variable(s) will have an impact over the other variable(s). The interrelationship amongst the
accounting variables and the impact of one or more accounting variable(s) over the other can be brought to light
through statistical tools and the results therefrom can be interpreted and concluded in a systematic way. There is
a wide scope for considering the Financial variables for research by applying both Descriptive statistic and
Inferential Statistics. Beyond that It is also possible to construct Linear Regression model(s), Multiple
Regression Models(s), Discriminant Model(s) and Structural Equation Model(s) using the financial variables.
Financial variables are also widely used in Time series analysis with the help of various econometric tools. With
the help of Financial Variables, it is quite possible to study a firm, Sector and the economy as whole. Enormous
studies were conducted with the help of Financial variables worldwide. Altman’s Z score, Du Point Analysis,
Capital Asset Pricing model, Capital Structure Theories, Dividend Theories, Random Walk Theory, Efficient
Market Hypothesis, CAMEL Model, Arbitrage Pricing Theory etc are the famous studies conducted in the area
of accounting and finance with major utilization of Accounting/ Financial Variables. Hence it is essential for
the present-day researchers to acquire skillset for analysing the accounting/ Financial Variables nothing but
secondary Data. In this connection, an attempt has been made in this paper to exhibit how to perform statistical
analysis with accounting variables by using MS-Excel and SPSS.
Page 2731
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
Scope for accounting Variables into research
The accounting variables are interrelated. The change in one will result in change in the other. In simple words
one variable can sensitize the other. With this ideology, it is quite possible to study the position of a firm in the
micro aspect and study the position of the sector and the whole economy in the macro perspective. A firm’s
performance is measured in terms of its Liquidity, Profitability, Turnover, operational efficiency, Return on
Investment, Shareholder wealth etc. Similarly, a sector’s performance is measured in terms of its Competitive
advantage, Market share, Sustainability etc. whereas the economy’s soundness can be assessed in terms of its
Inflation, GDP, Growth Rate, Balance of Trade, Balance of Payment, Stock market efficiency, Financial policy
and system etc.,The research over the position or performance of a firm, sector or the economy as the whole,
warrants to consider the relevant accounting variables as metrics. The accounting variables are not only used to
study the past and present performances and positions, those are also very much useful to predict the future
trends, prospects, and patterns.
The market has been transformed to buyer oriented. Now the current market is decided by data. Under business
analytics and the big data regimes, accounting variables have its own significance. Accounting variables plays a
major role in the big the big data.
For obtaining accurate and optimum results, it is quite essential to melange the appropriate accounting variables
with statistical tools as selected for analysis based on the Research problem, objectives and hypothesis.
The following figure illustrates the same:
In this paper, an attempt is made to empirically exhibit how to perform statistical analysis with accounting
variables
LITERATURE REVIEW
Altman (1968), Made an attempt in predicting the corporate bankruptcy using his
multiple discriminate analyses (MDS) model called Z-Score model/equation that exactly discriminated the 94% of
the bankrupt companies a year prior to bankruptcy
Jayakkodi&Rengarajan (II), studied the impact of NPA on ROA of both public and private sector banks. From
their study they found that there is a high degree of negative correlation between Gross Non-Performing Asset
with Return on Asset of Punjab National Bank, Bank of Baroda, Bank of India, ICICI and HDFC Bank
Narula &singh (II), Mentioned in their study that NPA affects the liquidity, profitability, Asset Quality and
Bank Survival
M.S.Ramaratnam&R.Jayaraman (2010), predicted the corporate bankruptcy of select companies of Indian
Steel Industry. The study concludes that none of the select companies will be bankrupt as they are financially
sound during the study period
M.S.Ramaratnam&R.Jayaraman (III), Studied the determinants of capital structure of Indian pharmaceutical
sector. In their study the influence of financial variables such as tangibility ratio, return on total assets, net profit
margin, and accumulated depreciation to total assets were analyzed with respect to the dependent variable of
Input
(Accounting Variables)
Research Process
with
1.Research Problem
2. Research objectives
3. Research hypothesis
4. Statistical tools
5. Analysis & Intrepretation
Output
(Conclusion)
Decision Making
Page 2732
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
leverage ratio. From the analysis the relationship between the independent variable and dependent variable has
been witnessed.
Data Analysis & Interpretations
Exhibit 1
Performance of ANOVA using financial variables
Objective
To test the significant difference among the Leverage ratio
(capital structure) of select companies for the select time period
Sector
Indian Steel Industry
Companies
1. JSW Steel
2. Tata Steel
3. Hindalco
4. SAIL
5. Jindal Steel
Ratio used
Leverage Ratio
Variables used
1. Total Debt
2. Total Asset
Time period
Last five years
Data Source
www.moneycontrol.com
Research Output
Tables showing Computation of ANOVA using financial variables
Year
Leverage Ratio
I
III
IV
V
JSW Steel
0.60
0.62
0.55
0.51
Tata Steel
0.68
0.69
0.60
0.56
Hindalco
0.63
0.56
0.48
0.48
SAIL
0.41
0.51
0.53
0.51
Jindal Steel
0.66
0.57
0.56
0.52
Groups
Count
Sum
Average
Variance
JSW Steel
5
2.942876
0.588575
0.003476
Tata Steel
5
3.206813
0.641363
0.003234
Hindalco
5
2.769367
0.553873
0.005343
SAIL
5
2.418089
0.483618
0.002553
Jindal Steel
5
2.874381
0.574876
0.002578
anova: Single Factor
ANOVA
Source of Variation
SS
df
MS
F
P-value
F crit
Page 2733
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
Between Groups
0.065858
4
0.016464
4.790745
0.00711
2.866081402
Within Groups
0.068734
20
0.003437
Total
0.134592
24
Inference
The above tables are related to the structure of ANOVA. The purpose of ANOVA in statistics is to ensure the
difference in means of the given data. In this case the variable of leverage has been taken among the different
steel companies in the steel industry. The concept of leverage is the application of debt in the capital structure
such a way to take the benefit of the instrument. By using ANOVA, the inference can be made such as the
employment of debt over the period among the selected companies may differ because the amount of debt will
not be equal among the companies. In this context it is understood from the table that the variable leverage shows
that there is significant difference in terms of employment of debt among the selected companies in the given
period by displaying the F value and its corresponding p value which is less than 0.01
Exhibit 2
Performance of Correlation using financial variables
Objective
To test the correlation among the Return on Equity and NPA of public sector Banking
companies for the select time period
Sector
Indian Banking Industry
Companies
Indian Public Sector Banks
Variables used
1.Return on Equity
2.NPA
Time period
Five years
Data Source
www.moneycontrol.com
www.rbi.org.in
Research Output
Table showing computation of correlation using financial variables
Correlations
NPA
ROE
NPA
Pearson Correlation
1
-.820
**
Sig. (2-tailed)
.000
N
105
105
ROE
Pearson Correlation
-.820
**
1
Sig. (2-tailed)
.000
N
105
105
**. Correlation is significant at the 0.01 level (2-tailed).
Inference
Page 2734
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
In the second application, the tool of correlation was taken between the variable of Non-Performing Assets
(NPA) and Return on Equity (ROE). The analysis was carried out in the banking industry by selecting the public
sector banks. The purpose of the analysis is to show the close relationship between NPA and ROE.As per the
theory higher NPA may lead to speedy erosion of profit. It is normally understood that the public sector banks
are exposed more to advances which may in turn give a scope for bad quality of asset. In this aspect the above
table shows the correlation between the two accounting variables of NPA and ROE, respectively. The result
proves that a strong negative association by displaying the correlation coefficient of 0.82 with negative sign and
the result is highly significant.
Exhibit 3
Performance of Regression using financial variables
Objective
To test the Impact of NPA on Return on Equity of public sector Banking companies
for the select time period
Sector
Indian Banking Industry
Companies
Indian Public Sector Banks
Variables used
1.Return on Equity
2.NPA
Time period
Five years
Data Source
www.moneycontrol.com
www.rbi.org.in
Research Output
Tables showing computation of Regression using financial variables
Model Summary
Model
R
R Square
Adjusted
R Square
Std. Error of the
Estimate
Change Statistics
R Square
Change
F Change
df1
df2
Sig. F
Change
1
.820
a
.672
.669
6.52286
.672
210.970
1
103
.000
a. Predictors: (Constant), NPA PUBLIC SECTOR
ANOVA
b
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
8976.272
1
8976.272
210.970
.000
a
Residual
4382.408
103
42.548
Total
13358.680
104
a. Predictors: (Constant), NPA PUBLIC SECTOR
b. Dependent Variable: ROE PUBLIC SECTOR
Coefficients
’
Page 2735
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
ANOVA
b
Model
Sum of Squares
df
Mean Square
F
Sig.
1
Regression
8976.272
1
8976.272
210.970
.000
a
Residual
4382.408
103
42.548
Total
13358.680
104
Model
Unstandardized Coefficients
Standardized
Coefficients
t
Sig.
B
Std. Error
Beta
1
(Constant)
16.743
1.171
14.292
.000
NPA PUBLIC SECTOR
-3.086
.212
-.820
-14.525
.000
a. Dependent Variable: ROE PUBLIC SECTOR
Inference
As an extension of application and validation of correlation technique, Linear regression model is used to
understand the extent to which the variables are influenced with each other. In this context NPA is taken as
predictor variable and ROE is taken as outcome variable.
In the process it is understood that the variance in ROE is explained by the variance in NPA through the value
of R squared which indicates 0.6 explaining the power of predictor variable over outcome variable. It shows that
almost 60% of variance in the outcome variable such as ROE is explained by the predictor variable of NPA.
Since the value of R square is reasonably good, the analysis is carried in the model of overall fit with the help of
ANOVA table. As the table shows the significant result, it is observed that the fit aspect is validated.
The coefficient table shows the impact of NPA on ROE. From the table it is observed that the change in one unit
of NPA may lead to 0.8 unit of erosion in terms of ROE and the result is also significant. The influence of NPA
on ROE is exhibited through linear regression model.
Exhibit 4
Performance of Altman’s Z-Score using Financial Variables
Objective
To test the financial health of Tata Power Company for the select time period using
Altman’s Z-Score
Sector
Indian Power Sector
Company
Tata Power Company
Variables used
1. Working Capital/Total Assets
2. Retained Earnings/Total Assets
3. Earnings before Interest and Taxes/Total Assets
4. Market Value of Equity/Book Value of Total Debt
5. Sales/Total Assets
Time period
Five years
Data Source
www.moneycontrol.com
Page 2736
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
Altman's model takes the following form -:
Z = 1.2A + 1.4B + 3.3C + 0.6D + .999E ………………(1)
A = Working Capital/Total Assets
B = Retained Earnings/Total Assets
C = Earnings before Interest and Taxes/Total Assets
D = Market Value of Equity/Book Value of Total Debt
E = Sales/Total Assets
Measurement of Financial Health
Altman established the following guidelines to be used to classify firms as either financially
sound or bankrupt.
Score Interpretation
Above 3.00 - The company is financially safe
2.77 – 2.99 - The company is on alert to exercise the caution
1.8 – 2.00 - There are chances that the company could go bankrupt in the next two years
Below 1.8 - The company’s financial position is embarrassing
Research Output
Tables showing computation of Altman’s Z-score using financial variables
Year
Tata Power Company
I
II
III
IV
V
WC
3,716.31
3,535.49
3,795.13
5,026.59
2,767.60
TA
33,561.19
30,539.03
28,092.86
25,117.71
21,205.30
RE
14,196.14
11,648.74
10,803.46
10,525.23
9,801.41
EBIT
1,515.65
1,491.16
1,703.38
1,682.87
1,111.82
Total Debt/Equity (X)
0.73
0.74
0.87
0.71
0.67
Total Operating Revenues
8,677.69
8,627.04
9,567.28
8,495.84
6,918.48
YEAR
A
B
C
D
E
Z-Score
I
11.07
42.30
4.52
1.37
25.86
3.47
II
11.58
38.14
0.05
1.35
28.25
3.50
III
13.51
38.46
0.06
1.15
34.06
4.11
IV
20.01
41.90
0.07
1.41
33.82
4.22
V
13.05
46.22
0.05
1.49
32.63
4.07
Inference
Page 2737
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
Basically, Altman Z score is used to discriminate among the firms with viability of bankruptcy. The score is
derived by taking total assets of the firm as a common denominator indicating the efficiency with which the firm
coverts the total assets into sales as well as operating profit. In addition to that the firm’s efficiency in terms of
using current assets against the total assets with the help of working capital aspect and the portion of retained
earning against the total assets revealing the usage of retained earnings to finance current assets and there by
depending on external source of borrowing to the minimum extent. The weights are assigned according to the
importance of ratios. The above tables give a clear picture that the selected company does not have a threat to
become bankruptcy since the total value of the equation 1 is more than 3.0 for the selected years
Summarized outcomes
Exhibit
Objective
Statistical
Tool used
Variables used
Result obtained
1
To test the significant
difference among the
Leverage ratio
(capital structure) of select
companies for the select
time period
ANOVA
Leverage Ratio (Total
Debt & Total Asset)
The leverage ratios
of select companies
are not uniform
2
To test the correlation
among the Return on Equity
and NPA of public sector
Banking companies for the
select time period
Correlation
Return on Equity and
Non-Performing Asset
There is a high
degree of negative
correlation between
ROE and NPA
3
To test the Impact of NPA
on Return on Equity of
public sector Banking
companies for the select
time period
Regression
Return on Equity and
Non-Performing Asset
The NPA is
negatively impacting
ROE
4
To test the financial health
of Tata Power Company for
the select time period using
Altman’s Z-Score
Altman’s Z-
Score
1. Working Capital/Total
Assets
2. Retained
Earnings/Total Assets
3. Earnings before Interest
and Taxes/Total Assets
4. Market Value of
Equity/Book Value of
Total Debt
5.Sales/Total Assets
The Firm has been
maintaining sound
Financial position
over the years.
CONCLUSION
With few exhibits, the current paper explores the possibilities of accommodating the accounting/Financial
variables into research work thereby obtaining solution for the various research problems in the fields of
Economics, Commerce, Finance, Banking and Stock market. It is concluded that the scope for accounting
variables in Business analytics is enormous.
REFERENCES
1. Altman,(1968). “Financial ratios discriminate analysis and prediction of corporate bankruptcy”, Jour
nal of finance, sep. 598
Page 2738
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue V, May 2026
2. Jayakkodi, D. &Rengarajan , D. P., II. Impact of non-performing assets on return on assets of public and
private sector banks in India. International Journal of Applied Research, 2(9), pp. 696-702.
3. Narula, D. S. &singh, m., II. Empirical Study on Non-Performing Assets of Bank. International Journal of
Advance Research in Computer Science and Management Studies, january, 2(1), pp. 194-199.
4. M.S. Ramaratnam and R. Jayaraman (III), Determinants of Capital Structurewith Special Reference
toIndian PharmaceuticalSector: Panel Data Analysis, Journal of Commerce and Accounting Research,
Volume 2 Issue 4 October III (Self-cited reference)
5.
Ramaratnam, M. S., & Jayaraman, R. (2010). A study on measuring the financial soundness of select firms
with special reference to Indian steel industry–An empirical view with Z score. Asian Journal of
Management Research, Online Open Access publishing platform for Management Research, 724-73.
(Self-cited reference) www.rbi.org.in www.moneycontrol.com