CHAPTER THREE

INTRODUCTION

3.1 Research Design

This study adopts an ex-post facto research design, which is appropriate because the

variables under investigation poverty rates, inflation rate, unemployment rate, GDP

growth, and exchange rate are already existing in national datasets and cannot be

manipulated by the researcher. Ex-post facto design is widely used in socio-economic

studies where data are historical, secondary, and non-manipulable.

The design allows the researcher to systematically analyze how changes in economic

indicators relate to current poverty levels in Nigeria over a specific period. Since the

study examines past trends, patterns, and relationships using time-series data, it aligns

well with quantitative, data-driven analyses that rely on empirical evidence rather than

controlled experimental conditions.

In addition, this research design helps establish the direction and magnitude of

relationships between variables, although not necessarily causation. It is suitable for

policy-oriented research aimed at explaining macroeconomic phenomena.

3.2 Population of the Study

The population of the study refers to all economic data on poverty and key national

economic indicators in Nigeria. Specifically, the population includes:

1. National poverty headcount data

2. Multidimensional poverty index data

3. Annual inflation rate

4. Unemployment rate

5. GDP growth rate

6. Exchange rate figures

7. Other macroeconomic performance indicators

These datasets are published annually by reputable national and international

institutions, including the National Bureau of Statistics (NBS), Central Bank of

Nigeria (CBN), World Bank, and IMF.

Because this research focuses on Nigeria’s macro-level performance, the entire nation

constitutes the population, represented statistically through aggregate national data

spanning multiple years.

3.3 Sample Size and Sampling Technique

3.3.1 Sample Size

The sample size consists of annual time-series data from the year 2000 to 2023. This

provides 24 observations, which is statistically adequate for regression-based analysis

as recommended in time-series methodology.

A 24-year dataset is appropriate because:

1. It captures multiple economic cycles

2. It reflects long-term poverty and macroeconomic trends

3. It allows for robust statistical analysis

4. It covers major policy eras and reforms (e.g., economic liberalization, recession,

recovery periods)

3.3.2 Sampling Technique

A purposive sampling technique is adopted. This method is used when the researcher

selects data based on relevance and availability. The chosen period (2000–2023) is

selected because:

1. Data for all variables are consistently available

2. The period covers significant economic fluctuations

3. Nigeria implemented major policy reforms during this time

4. It includes years with severe poverty spikes and inflation shocks

Thus, the sampling technique ensures that the data set accurately represents the

economic realities relevant to the study.

3.4 Sources of Data

This study relies solely on secondary data, which are obtained from recognized,

credible, and authoritative institutions. The data sources include:

1. National Bureau of Statistics (NBS)

2. Poverty reports

3. Inflation rate

4. Unemployment rate

5. National accounts

6. Central Bank of Nigeria (CBN) Statistical Bulletin

7. GDP growth rates

8. Exchange rate trends

9. Monetary policy reports

10. World Bank Development Indicators (WDI)

11. Poverty headcount ratio

12. Economic performance indices

13. International Monetary Fund (IMF)

14. Country economic assessments

15. Macroeconomic trend analyses

16. United Nations Development Programme (UNDP)

17. Human development and multidimensional poverty indicators

The use of secondary data enhances reliability because the figures originate from

expert agencies that apply standardized measurement approaches.

3.5 Methods of Data Collection

1. Data will be collected through systematic extraction from official publications.

The steps include:

2. Downloading statistical reports from NBS and CBN official websites.

3. Extracting time-series poverty data from NBS and World Bank indicators.

4. Reviewing IMF and UNDP reports for supplementary data.

5. Organizing all extracted figures into Microsoft Excel spreadsheets.

6. Consolidating the datasets into a uniform structure suitable for analysis.

7. All data collected are quantitative and numerical.

3.6 Method of Data Analysis

The study employs quantitative econometric techniques to analyze the relationship

between poverty and economic indicators. The tools and methods used include:

3.6.1 Descriptive Statistics

Descriptive statistics will summarize the data using:

1. Mean

2. Median

3. Standard deviation

4. Minimum and maximum values

5. Trend charts
These help visualize the behavior of each variable over the 24-year period.

3.6.2 Multiple Regression Analysis

The study will use Ordinary Least Squares (OLS) regression to estimate the impact of

economic indicators on poverty. The model is:

Povt = β0 + β1INFt + β2UNEMPt + β3GDPGRt + β4EXCHRt + μt

Where:

1. Povt = Poverty rate in year t

2. INFt = Inflation rate

3. UNEMPt = Unemployment rate

4. GDPGRt = GDP growth rate

5. EXCHRt = Exchange rate

6. μt = Error term

3.6.3 Stationarity Tests

Time-series data often exhibit non-stationarity. To avoid spurious regression, unit root

tests such as:

Augmented Dickey-Fuller (ADF)

Phillips-Perron (PP) test

are conducted.
3.6.4 Co-integration Test

If variables are non-stationary but integrated at the same order, the Johansen Co-

integration test will determine whether a long-run equilibrium relationship exists

among them.

3.6.5 Diagnostic Tests

To ensure model reliability, the following will be carried out:

1. Autocorrelation test (Durbin-Watson statistic)

2. Heteroskedasticity test (Breusch-Pagan test)

3. Model specification test (RESET test)

4. Normality test (Jarque-Bera test)

These confirm that the model meets classical linear regression assumptions.

3.7 Model Specification

The functional form of the model is:

Pov = f (INF, UNEMP, GDPGR, EXCHR)

The econometric form is:

Povt = β0 + β1INFt + β2UNEMPt + β3GDPGRt + β4EXCHRt + μt

Where:

β₀ = Intercept

β₁ – β₄ = Coefficients measuring sensitivity of poverty to each indicator

Expected signs of coefficients:

1. Inflation (+) → expected to increase poverty

2. Unemployment (+) → expected to increase poverty

3. GDP growth (–) → expected to reduce poverty

4. Exchange rate (+/–) → depending on import dependence

3.8 Validity and Reliability of Data

3.8.1 Validity

Validity is ensured by using data from highly credible institutions (World Bank, NBS,

CBN). These organizations follow strict international statistical guidelines.

3.8.2 Reliability

1. Data reliability is strengthened because:

2. Multiple sources confirm the values

3. Data undergo rigorous verification processes

4. Standardized definitions are used consistently over time

Thus, the dataset is fit for economic analysis.

3.9 Ethical Considerations

Although this study uses secondary data and does not involve human subjects, ethical

standards are still observed:

1. No manipulation of data

2. Proper citation of all sources

3. Avoidance of plagiarism

4. Transparent reporting of methods and findings

5. Respect for copyright and data usage rights

6. The research maintains objectivity and avoids bias in interpretation.

3.10 Limitations of the Methodology

Some limitations include:

1. Dependence on accuracy of external data sources

2. Unavailability of some data for certain years

3. Time-series data may contain structural breaks due to policy changes

4. OLS regression cannot fully establish causality

5. Socio-political factors like insecurity or corruption are difficult to quantify

Despite these limitations, the methodology remains robust, academically acceptable,

and suitable for achieving the research objectives.

REFERENCES

Asteriou, D., & Hall, S. G. (2016). Applied econometrics (3rd ed.). Palgrave
Macmillan.

Brooks, C. (2019). Introductory econometrics for finance (4th ed.). Cambridge

University Press.

Central Bank of Nigeria (CBN). (2022). Statistical bulletin: Financial and

macroeconomic indicators. CBN Publications.

Creswell, J. W. (2014). Research design: Qualitative, quantitative and mixed methods

approaches (4th ed.). Sage Publications.

Gujarati, D. N., & Porter, D. C. (2009). Basic econometrics (5th ed.). McGraw-Hill.

International Monetary Fund (IMF). (2023). Nigeria country report 2023. IMF
Publications.

Iyoha, M. A., & Ekanem, O. T. (2020). Introduction to econometrics. Mindex

Publishing.

Johansen, S. (1991). Estimation and hypothesis testing of co-integration vectors in

Gaussian vector autoregressive models. Econometrica, 59(6), 1551–1580.

Kothari, C. R. (2004). Research methodology: Methods and techniques (2nd ed.).

New Age International Publishers.

National Bureau of Statistics (NBS). (2023). Nigeria inflation and unemployment

report 2023. NBS Publications.

National Bureau of Statistics (NBS). (2022). Nigeria multidimensional poverty index

(MPI) report. NBS Publications.

Olofin, S. O., & Folawewo, A. O. (2006). Applied econometrics: A simplified

approach. University of Ibadan Press.

Phillips, P. C. B., & Perron, P. (1988). Testing for a unit root in time series regression.
Biometrika, 75(2), 335–346.

Punch, K. (2013). Introduction to social research: Quantitative and qualitative

approaches (3rd ed.). Sage Publications.

Sekaran, U., & Bougie, R. (2019). Research methods for business: A skill-building
approach (8th ed.). Wiley.

Tabachnick, B. G., & Fidell, L. S. (2019). Using multivariate statistics (7th ed.).
Pearson.
United Nations Development Programme (UNDP). (2022). Human development
report 2022: Uncertain times, unsettled lives. UNDP Publications.

Wooldridge, J. M. (2016). Introductory econometrics: A modern approach (6th ed.).

Cengage Learning.

World Bank. (2022). World development indicators 2022. World Bank Publications.