Correlation Analysis
We will work with data from the census – rate of unemployment, rate of university educated people, rate of entrepreneurs, rate of people employed in industry and rate of believers. We will work on the level of districts (LAU1).
In the SPSS the correlation is located in menu Analyze/Correlate/Bivariate. Then move all analyzed variables into the right window and select correct correlation coefficient (Pearson, Spearman or Kendall), select also a possibility to flag significant correlations. Results are in separate tables according to the correlation coefficient.
- Which of variables are significantly correlated?
- Plot the two variables with the highest correlation in a scatterplot. Do the same for variables with the lowest correlation.
- Compare results of correlation coeficients (Pearson x Spearman).
- Calculate correlation coefficient for the same variables on the geographical level of municipalities, regions of extended powers (ORP) and regions.
- Consider the influence of MAUP and ecological fallacy and how the results are changing with different level of aggregation.
Korelace v Excelu se spouští opět v rozšíření Analýza dat, kterou po zapnutí naleznete na kartě Data. Jako vstupní oblast vyberte všechny buňky s daty
Pro dokonalé pochopení rozdílu mezi Pearsonovým a Spearmanovým koeficientem korelace si oba vypočtěte ručně pro níže uvedené hodnoty pro dvě proměnné Příjem v tisících a Délka studia v letech. Pro připomenutí jsou uvedeny oba vzorce:
| ID | Income | Years of studies |
| 1 | 30 | 19 |
| 2 | 14 | 9 |
| 3 | 29 | 17 |
| 4 | 19 | 10 |
| 5 | 25 | 13 |
| 6 | 25 | 11 |
| 7 | 29 | 12 |
| 8 | 35 | 18 |
Video describing Pearson Correlation for combined studentsVideos describing Spearman Correlation for combined students
Data
Cvičení je vytvořeno v rámci projektu Inovace bakalářských a magisterských studijních oborů na Hornicko-geologické fakultě VŠB-TUO pod číslem CZ.1.07/2.2.00/28.0308. Tento projekt je realizován za spoluúčasti EU.