Once you have that distribution (more on this later), you can compute Let $f(\alpha)$ denote that distribution. Rather than compute a "confidence interval" based on a sampling distribution (which, as noted by others, is not possible), you can compute a probability distribution for $\alpha$ based on whatever you may know from any source. Since this is a real business situation, you must bring whatever additional information you can to the problem. As noted in the comments, the fraction could be anywhere between 0 and 1, Your "sample" of 5000 tells you nothing directly about this fraction. You are uncertain about the fraction $\alpha$ of Word users who open the file. Let me state the problem a bit more formally. Nevertheless a decision must be made - which may be simply to acquire more information for the time being. The optimal decision should take this uncertainty into account.Īs others have noted, sampling theory does not apply here and a confidence interval cannot be computed.
#OPENOFFICE CALCULATE P VALUE HOW TO#
PM me if you want some quick suggestions on how to get started.As I understand it, there is a business decision that depends on the total number of file openings which in turn depends on the unknown fraction of Word users who open the downloaded file. It is not necessarily the easiest program to use but you could try using R for what you want to do. This is saying that the figures are statistically different at the probability level of 0.04787. On the other hand I ran a chi-squared test in the stats program R and got I may just be misunderstanding the test in Calc but it does look strange. Where exactly that O comes from I have no idea. I just ran a chi square test in Calc with these figuresĪnd got a O.0. This is means the result you're getting is supposed to be the probability of getting that set of observed numbers if the null hypothesis, no difference, is true. This is the probability which suffices the observed data of the theoretical Chi-square distribution.
#OPENOFFICE CALCULATE P VALUE SERIES#
Returns the probability of a deviance from a random distribution of two test series based on the chi-squared test for independence. I have already seen a thread about error messages associated with this function, but it looked as though that problem had been resolved by the end of that thread.ĭoes anyone have any advice or information for me on this? I would really like some help as soon as possible! I am also getting error messages, answers of zero, and answers that seem unusually small when I use the CHITEST function on sets of cells in what seems (from my understanding of all the tutorials and Help pages) to be the appropriate fashion. calculate (observed-expected)^2/(expected) for each pair of observed & expected values, then sum the results), I get a different number than what the CHITEST provides, indicating that CHITEST does not provide Chi-squared values. When I carry out a Chi-squared test by hand on the same set of data ( i.e. What exactly does the CHITEST function produce? The Help/How-To pages explain that it is "a measure of χ2 'goodness of fit'" or "the chi-squared distribution of the data" this sounds to me as though this formula might produce a Chi-squared value. It seems that this should not be difficult however, I cannot seem to find a Calc function that does this, and as I have no programming or statistical background, I am having a hard time making a formula up myself. What I would like to find is a formula that will return a Chi-squared value when sets of observed and expected values are entered. [Formerly "CHITEST function - please explain!")
0 kommentar(er)
