Analyzing Statistical Correlation Findings
Analyzing Statistical Correlation Findings
(Analyzing Statistical Correlation Findings)
Change the words in the sentences but keep the main idea don t change anything in the boxes add references
Correlations
Months with service
Household income in thousands
Months with service
Pearson Correlation: 1, .243**
Sig. (2-tailed): .000
N: 1000
Household income in thousands
Pearson Correlation: .243**, 1
Sig. (2-tailed): .000
N: 1000
Note: **. Correlation is significant at the 0.01 level (2-tailed).
3.The correlation coefficient between “Months with service (tenure)” and “Household Income (income)” is 0.243 as obtained from SPSS. This value is significant at the 1% level of significance. This implies that there is a weak positive linear relationship between the two variables. That is, as the value of Months with service increases, the value of household income increases slightly.
- Correlation doesn’t necessarily mean causation. Correlation measures the degree of association between the two variables, or in other words, it measures the strength of the linear relationship between them. However, causation implies that a change in one variable is caused by the other.
- The value of the correlation coefficient is 0.243. There is a weak positive linear relationship between the two variables. That is, as the value of Months with service increases, the value of household income increases slightly.
- Correlations
Level of education
Age in years
Kendall’s tau_b
Level of education:
Correlation Coefficient: 1.000, -.112**
Sig. (1-tailed): .000
N: 1000
Age in years:
Correlation Coefficient: -.112**, 1.000
Sig. (1-tailed): .000
N: 1000
Spearman’s rho
Level of education:
Correlation Coefficient: 1.000, -.152**
Sig. (1-tailed): .000
N: 1000
Age in years:
Correlation Coefficient: -.152**, 1.000
Sig. (1-tailed): .000
N: 1000
Note: **. Correlation is significant at the 0.01 level (1-tailed).
- According to Kendall’s tau_b, the value of the correlation coefficient is -0.112. This implies that there is a weak negative relationship or almost no relationship between the two variables.
According to Spearman’s rho, the value of the correlation coefficient is -0.152. This also implies that there is a weak negative relationship or almost no relationship between the two variables.
- I used a one-tailed test to test the significance of the negative relationship between the two variables, namely “Level of Education” and “Age in Years.” Here, my null hypothesis is that the value of the correlation coefficient is not significant, that is, p = 0. While my alternative hypothesis is that the value of the correlation coefficient is significant, that is, p < 0.
- The Pearson product-moment correlation coefficient is calculated between two variables measured on an interval or ratio scale of measurement. The ratio level of measurement has equal differences between scale values and equal quantitative meaning. It has a true zero point, meaning that a value of zero on the scale represents zero quantity of the construct being assessed. Here, both tenure and income variables are measured on a ratio scale of measurement.
Spearman’s and Kendall’s correlation coefficients are calculated between two variables measured on an ordinal scale. The ordinal level of measurement describes variables that can be ordered or ranked in some order of importance. Here, age and education are measured on an ordinal scale. It measures the monotonic relationship between the two variables.
- Marital status * Churn within last month Crosstabulation
Count
Churn within last month:
No | Yes | Total | |
---|---|---|---|
Unmarried | 358 | 147 | 505 |
Married | 368 | 127 | 495 |
Total | 726 | 274 | 1000 |
Chi-Square Tests
Value | df | Asymp. Sig. (2-sided) | Exact Sig. (2-sided) | Exact Sig. (1-sided) | |
---|---|---|---|---|---|
Pearson Chi-Square | 1.498a | 1 | .221 | ||
Continuity Correctionb | 1.329 | 1 | .249 | ||
Likelihood Ratio | 1.499 | 1 | .221 | ||
Fisher’s Exact Test | .229 | .124 |
Notes:
a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 135.63.
b. Computed only for a 2×2 table.
Null hypothesis Ho: Marital status and churn within the last month are independent.
Alternative hypothesis H1: Marital status and churn within the last month are not independent.
With p > 0.05, I fail to reject Ho at the 5% level of significance and conclude that marital status and churn within the last month are independent.