Hi,

I am working on a project to review a policy on revoking certain user access previleges based on period of inactivity.

Currently the user inactivity period is set to 90 day, based on which the access previleges are revoked. However, as there is cost involved in providing these access previleges, there is a need to revisit this policy and free more licenses that can be used to process new access requests.

I have collecetd fortnightly inactivity data for the last 4 fortnights. Clearly the number of licenses that we would free by rewroking the policy to 60 day would increase by around 40% to 50%.

I am looking to demonstatre this thourgh one of the tests. To my mind the test that would best help in demonstrating this is 2-sample t Test where I can compare the average number of inactive users. However the problem is that my 'Y' is Average number of inactive users, which is discrete. The count that I get hovers around 600 to 1000 inactive users.

The proportion or Chi-Square tests don't seem relevant here. So, Is this count large enough for me to choose the 2-Sample t test? If yes, how do I justify this step?

Regards,

Shiva Kumar Bhasakaran.

Dear Shiva,

Just wanted to understand why you indicate that a 2-proportion test is not relevant here. Could you not do a 2-proportion test with the first case (90-day policy) and determine how many licenses would be freed (events) vs. total number of licenses (trials). Similarly, you can calculate for the second case (60-day policy) how many licenses would be freed (events) vs. total number of licenses (trials).

Using this information, you should be able to use the 2-proportion test and get an appropriate value of P based on the discrete distribution (in this case a Fisher's test).

As an approximation, you could use the 2-sample t test if the proportions you calculated above are not close to 0 or 1.

SJ

Hi Suresh sir,

This was useful thanks. I have done the following, kindly confirm if I am on the right track with respect to the tests and associated conclusions drawn.

Step 1:- To determine if reconcillication is a sustainable solution:

I have calculated the proportion of released licenses (events) Vs the total number of licenses (Trials). I have also calculated for the same month the proportion of new users set up (events) Vs the total number of licenses (Trials). I have applied the 2-Proportion test (Fisher's test is not available in this Minitab version) and the test result suggests that these proportions are 'equal'. So, reconcilliation may not be a sustainable exercise.

Step 2:- To determine if chanage in policy would help:

I have calculated the proportion of released licenses for 90 day policy (events) Vs the total number of licenses (Trials). I have also calculated for the same month the proportion of released license for 60 day policy (events) Vs the total number of licenses (Trials). I have applied the 2-Proportion test (Fisher's test is not available in this Minitab version) and the test result suggests that the number of licenses released is marginally high. So, change of policy could be a temporary solution but not a permenant solution.

Hi Suresh sir,

This was useful thanks. I have done the following, kindly confirm if I am on the right track with respect to the tests and associated conclusions drawn.

Step 1:- To determine if reconcillication is a sustainable solution:

I have calculated the proportion of released licenses (events) Vs the total number of licenses (Trials). I have also calculated for the same month the proportion of new users set up (events) Vs the total number of licenses (Trials). I have applied the 2-Proportion test (Fisher's test is not available in this Minitab version) and the test result suggests that these proportions are 'equal'. So, reconcilliation may not be a sustainable exercise.

Step 2:- To determine if chanage in policy would help:

I have calculated the proportion of released licenses for 90 day policy (events) Vs the total number of licenses (Trials). I have also calculated for the same month the proportion of released license for 60 day policy (events) Vs the total number of licenses (Trials). I have applied the 2-Proportion test (Fisher's test is not available in this Minitab version) and the test result suggests that the number of licenses released is marginally high. So, change of policy could be a temporary solution but not a permenant solution

Hi,

I am not sure I could comment on the temporary vs. permanent solution with this exercise. You can only state whether there is or is not a statistical difference between the two proportions.

For example, proportion of licenses with reconciliation is statistically similar to the proportion of licenses without reconciliation. Statistically, there is a difference between license policy of 60 days vs. 90 days.

You will have to determine if the change you detected is practically important and how you can establish a good control plan so that the process will work over the long term.

Best Regards,

SJ.