CorrelationClass 11 Statistics For Economics Case Study Questions
10 Questions
Generated by KedovoAI
Case 1 of 10
Case Study7 marks
Visualising Relationships with Scatter Diagrams
An economist is studying the relationship between the average annual rainfall (in cm) in a district and the yield of a major crop (in tonnes per hectare). To begin her analysis, she collects data from the past 15 years and plots it on a graph, with rainfall on the X-axis and crop yield on the Y-axis. This type of graph is known as a scatter diagram. She observes that the points on the graph tend to cluster around an imaginary straight line that slopes upwards from left to right. This visual representation gives her a preliminary idea about the nature and strength of the association between the two variables. She notes that if the points were to lie exactly on a straight line, the correlation would be considered 'perfect'. Conversely, if the points were scattered randomly with no discernible pattern, she would conclude there is no correlation. This initial step is crucial before proceeding to calculate a precise numerical measure like Karl Pearson's coefficient.
Questions on this case
1(1 mark)MCQ
What does a scatter diagram visually represent?
2(1 mark)MCQ
The economist observed that the points sloped upwards from left to right. What type of correlation does this suggest?
3(1 mark)
According to the passage, what would a scatter diagram showing 'no correlation' look like?
4(2 marks)
Why is a scatter diagram considered a useful first step before calculating a numerical coefficient of correlation?
5(2 marks)
If all the data points on the scatter diagram were to lie exactly on a downward sloping straight line, what could you conclude about the value of Karl Pearson's coefficient of correlation (r)? Explain your reasoning.
Case Study7 marks
Analysing Business Performance with Karl Pearson's Coefficient
A market analyst for a fast-moving consumer goods (FMCG) company is tasked with understanding the effectiveness of its advertising campaigns. He collects quarterly data for the last two years (8 quarters) on 'Advertising Expenditure' (in Rs. Lakhs) and 'Sales Revenue' (in Rs. Crores). To measure the degree of linear relationship between these two variables, he calculates Karl Pearson's coefficient of correlation, also known as the product-moment correlation coefficient. The resulting value is
r = +0.92. The analyst presents this finding to the management, stating that there is a very strong, positive linear relationship between the amount spent on advertising and the sales revenue generated. He explains that as advertising expenditure has increased, sales revenue has also tended to increase consistently. However, he cautions that while the association is strong, this statistical measure does not, by itself, prove that advertising is the sole cause of the increase in sales.Questions on this case
1(1 mark)MCQ
What is another name for Karl Pearson's coefficient of correlation mentioned in the passage?
2(1 mark)
What does the value
r = +0.92 indicate about the relationship between advertising expenditure and sales revenue?3(1 mark)MCQ
The value of Karl Pearson's coefficient of correlation always lies between which range?
4(2 marks)
If the analyst had measured advertising expenditure in thousands of rupees instead of lakhs, would the value of
r change? Why or why not?5(2 marks)
The analyst warns that correlation does not prove causation. Besides advertising, suggest another possible factor that could be influencing both advertising expenditure and sales, leading to this strong positive correlation.
Case Study7 marks
Ranking Qualitative Attributes with Spearman's Method
In a local culinary competition, two renowned chefs, Judge A and Judge B, are asked to rank five participants based on the 'creativity' of their dishes. Since 'creativity' is a qualitative attribute and cannot be measured with a numerical value like weight or height, a quantitative method like Karl Pearson's is unsuitable. Instead, Spearman's rank correlation coefficient is the appropriate tool. It measures the association between the ranks assigned by the two judges, allowing the organisers to see how consistent the judges' perceptions are. The ranks are as follows:
| Participant | Rank by Judge A | Rank by Judge B |
|---|---|---|
| 1 | 2 | 1 |
| 2 | 5 | 4 |
| 3 | 1 | 2 |
| 4 | 3 | 5 |
| 5 | 4 | 3 |
By calculating the differences in ranks, squaring them, and applying the formula
r_s = 1 - (6ΣD²)/(n³-n), the organisers can determine the strength and direction of agreement between the judges.Questions on this case
1(1 mark)MCQ
Spearman's rank correlation is most suitable for which type of data?
2(1 mark)
Based on the passage, give one reason why Spearman's rank correlation was chosen over Karl Pearson's coefficient.
3(1 mark)MCQ
If the ranks given by both judges were identical for all five participants, what would be the value of ΣD²?
4(2 marks)
For Participant 4, what is the value of the deviation in ranks (D) and its square (D²)?
5(2 marks)
Explain a situation, different from the one in the passage, where using Spearman's rank correlation would be more appropriate than Karl Pearson's coefficient.