Regression is a versatile statistical test used to understand and quantify the relationship between two or more variables. It is popularly used in secondary and primary data. It helps to not only understand the past trends but also predict the future.
For example, businesses use various regression models to predict future sales. Similarly, government agencies use it to understand economic performances from secondary data.
However, before applying a regression model it is important to check the correlation between the variables first. The previous article explained how to perform correlation tests on secondary data using SPSS. This article will explain the application of regression tests on secondary data using SPSS, using the same dataset.
Case description for regression test on secondary data using SPSS
In the previous article, it was shown that there is a correlation present among India’s Gross Domestic Product (GDP), unemployment rate (UNE) and population growth (POPG) for the period 2012-18. This article explores the extent of the impact of UNE and POPG on India’s GDP.
Accordingly, the hypothesis is:
Null hypothesis (H0): There is no relationship between unemployment rate, population growth and economic growth of India for the period 2012-2018.
Follow the below steps to perform the regression.
Perform the correlation test as shown in the previous article.
Run the regression test. For this, click on ‘Analyse’, then ‘Regression’, then ‘Linear’ as shown below.
The following window will appear. From this window move the natural log-transformed variable LnGDP to Dependent followed by LnUNE and LnPOPG to Independent(s).
Click on ‘OK’. The following output window appears for regression analysis.
Interpreting the results showing impact of population growth and unemployment on India’s economic output
The above figure shows the output of the regression test. It has many values. Each must be interpreted independently before deciding whether to accept or reject the null hypothesis.
In the case of this example, the values of R square and adjusted R square are 0.98 and 0.97, depicting that about 97% of the variation in the economic growth of India is being represented by unemployment growth and population growth. This is a favourable result. The F value is 292.70, which is also favourable since it is more than 1. It denotes that there is more precision in the model due to the independent variables. The significance ‘Sig.’ value is 0.00. The significance value should always be less than 0.10 in order to prove that an impact is present. Since in this case, it is meeting the criteria, we can conclude that the unemployment rate and population growth rate rise has an impact on the economic growth of India.