# 商业管理分析作业代写 Data Management and Analytics

## MIS 609 Data Management and Analytics

### Slide 6:  商业管理分析作业代写

Thanks, XXX. After previous data processing, we were able to combine both datasets into one dataset, with the time frame ranging from the year 1961 to 2018, while our independent variable is the average monthly days with a temperature higher than the 90th pentile.  Or the monthly count of extremely hot days, and our dependent variable is the actual wheat yield, measured by tons per hectare.

We were then able to build a scatter plot with given data, create a trend line as well as use Power Bi’s built-in DAX function to calculate the correlation coefficient value. Both the scatter plot and the coefficient value are shown here. Which we can see a quite obvious trend where the more extremely hot days there are.  The higher the wheat production is, with a positive 0.64 correlation coefficient.

### Slide 7:

In order to further validate our model. Excel regression analysis was performed to measure the statistical significance of our model. The regression output is shown on the screen, and we noticed an extremely small P-value for the USA AVG T90 variable.  Meaning the model we built is statically significant. This matches the result we get by looking at the previous scatter plot.  商业管理分析作业代写

### Slide 8:  商业管理分析作业代写

Thus, our findings can be concluded in three points. First, two variables show a moderate positive relationship, indicated by the 0.64 correlation coefficient. Secondly, the model we built is statistically significant with lower P-values, and the model indicated that for every extra extreme hot day in a month, the wheat yield is likely to grow by 0.14 tons. Thus, the conclusion can be made that from the data. It seems that with more extremely hot days in a month, there will be higher wheat yield in the USA.

However, limitations also exist in this research. First of all, agriculture is such a complex field that multiple factors influence the final yield.  And by focusing on only one of the variables, the research didn’t exclude influence from other factors. Also, with the time-series data we noticed that there are more extremely hot days in later years, as well as higher wheat yields. We also know in later years, applications of newer agricultural technologies might also play an important role in increasing yield, which this research didn’t count in.  商业管理分析作业代写

Last but not least, the research focused on the USA only while regional data.  Such as the state data of Indiana might offer a more delicate result, while a global view can also help to analyze global climate change’s impact on agriculture. Thus, this research can only be viewed as preliminary research and further research is required to analyze other factors.

### Slide 9:

Regarding the work distribution, I performed XXXXX. The total estimated workload is XXX and XXX performed XXX, the total estimated workload is XXX