Estimate Probability of Excel Data Analysis Results

[izzy93]

Not sure where to post this question, but here goes

In excel I have calculated the average annual rain for the period 1990-2012 to be 50.2mm . How do you estimate the probability that this measured average (1990-2012) is consistent with the long term mean annual rain for the period 1948-2012 (assuming a gaussian distribution) which I calculated to be 51.6mm?

Is there some sort of function or is this simpler than I'm imagining...

any help much appreciated

thanks

 

[Simon Bridge]

How would you normally compare two sets of statistics?

 

[izzy93]

Hi, I've come up with a solution I think. Going to use the NORM.DIST function

thanks for the reply though

 

[Office_Shredder]

izzy,

The typical test for this is the Student's t-test
http://en.wikipedia.org/wiki/Student's_t-test#Independent_two-sample_t-test

which determines whether the difference in means between two samples is statistically significant.

 

[CellCoree]

As a scientist, the first thing I would do is check the data and make sure that it is normally distributed. This can be done by creating a histogram in Excel and visually inspecting the shape of the data. If it appears to be normally distributed, then we can use statistical tests to estimate the probability of the results.

One way to do this is by conducting a t-test, which compares the means of two samples. In this case, we would compare the mean annual rain for the period 1990-2012 to the mean annual rain for the longer period of 1948-2012. The t-test will give us a p-value, which represents the probability of obtaining the measured average of 50.2mm if the true mean is 51.6mm. If the p-value is less than 0.05, it would suggest that the measured average is significantly different from the true mean.

Another approach would be to calculate a confidence interval for the mean annual rain for the longer period and see if the measured average falls within this range. If it does, then we can say with a certain level of confidence that the measured average is consistent with the long-term mean.

It is important to note that these methods assume that the data is normally distributed and that the samples are independent. If these assumptions are not met, then alternative methods may need to be used. It is also important to consider any potential sources of bias in the data collection or analysis process.

In summary, estimating the probability of Excel data analysis results requires careful consideration of the data and appropriate statistical tests. It is always best to consult with a statistician or data analyst for assistance in making these estimations.