To investigate the effectiveness of a new fertilizer, the Agricultural Research Bureau applies different amounts of fertilizer to a random selection of 14 one hectare fields, and subsequently records the wheat yield produced by each field.

The data is captured in the table below. NB In this question, if you use Excel functions you should list the functions you used. If you use an analysis tool add-in you should cut and paste the output into your answer, and if you use and "old school" approach you should quote the relevant formulae.

Field	F (kg of fertilizer)	Y, (Yield - tonnes of wheat)
1	31.9	2.65
2	27.9	1.89
3	12.9	2.39
4	28.4	2.53
5	11.9	1.94
6	55.2	2.47
7	21.6	2.11
8	11.2	3.62
9	37.3	2.51
10	8.8	1.76
11	52	3.06
12	45.9	2.69
13	32.6	2.12
14	22.1	1.9

Accumulations are SF = 399.7, SY = 33.64, SF² = 14380.35, SY² = 84.2304, SFY = 988.303

1. Determine the mean, median and standard deviation of wheat yield for this sample.
2. Determine the Ordinary Least Squares regression line that uses the amount of Fertilizer to explain or predict Wheat Yield.
3. Interpret the slope coefficient.
4. Determine and interpret the standard error of the estimate.
5. Determine and interpret the coefficient of determination
6. Use your regression equation to predict the Wheat yield if 60 kg of fertilizer is used, and explain why this might be problematic.
7. scattergram of the data and study it carefully. Identify and describe any feature that may cause you to doubt whether your OLS linear regression model is appropriate. [NB There is no need to include the scattergram in your answer.]