Welcome Guest
Log In | Register )
You last visited December 4, 2016, 3:15 pm
All times shown are
Eastern Time (GMT-5:00)

How to calculate "HITS" based on a numbers hit dates?

Topic closed. 9 replies. Last post 5 years ago by SergeM.

Page 1 of 1
PrintE-mailLink
Avatar
Virginia Beach, Virginia
United States
Member #110060
April 25, 2011
115 Posts
Offline
Posted: March 27, 2012, 4:13 pm - IP Logged

Does anyone know how to calculate these "Draws between draws" to create a suggested hit date. I totaled the numbers,  "384 + 465 + 398 + 9 + 51 + 139 + 62 + 155 + 92 + 20" and divided the total by 10. Converted the draws into days and months.

My question is how would you handle the outlier numbers like 384, 465, 9 and 20? Is there a better way using this data to create a hit date?

 

NumberDraw DateHow many draws agoDraws between drawsTime between draws

716          Saturday, May 01,        2010(EVE)                     1391                          384              6m 10d
671          Monday, December 20, 2010(DAY)                    926                            465              7m 19d
617          Thursday, July 07, 2011(DAY)                           528                            398              6m 17d
716          Monday, July 11, 2011(EVE)                              519                            9                 4d
167          Saturday, August 06, 2011(DAY)                       468                            51               26d
617          Friday, October 14, 2011(EVE)                           329                            139              2m 8d
167          Monday, November 14, 2011(EVE)                     267                            62               1m
671          Tuesday, January 31, 2012(DAY)                       112                            155              2m 17d
176          Saturday, March 17, 2012(DAY)                         20                              92                1m 17d
671          Tuesday, March 27, 2012(DAY)                          0                               20                 10d

    Avatar
    Virginia Beach, Virginia
    United States
    Member #110060
    April 25, 2011
    115 Posts
    Offline
    Posted: March 27, 2012, 7:55 pm - IP Logged

    Does anyone know how to calculate these "Draws between draws" to create a suggested hit date. I totaled the numbers,  "384 + 465 + 398 + 9 + 51 + 139 + 62 + 155 + 92 + 20" and divided the total by 10. Converted the draws into days and months.

    My question is how would you handle the outlier numbers like 384, 465, 9 and 20? Is there a better way using this data to create a hit date?

     

    NumberDraw DateHow many draws agoDraws between drawsTime between draws

    716          Saturday, May 01,        2010(EVE)                     1391                          384              6m 10d
    671          Monday, December 20, 2010(DAY)                    926                            465              7m 19d
    617          Thursday, July 07, 2011(DAY)                           528                            398              6m 17d
    716          Monday, July 11, 2011(EVE)                              519                            9                 4d
    167          Saturday, August 06, 2011(DAY)                       468                            51               26d
    617          Friday, October 14, 2011(EVE)                           329                            139              2m 8d
    167          Monday, November 14, 2011(EVE)                     267                            62               1m
    671          Tuesday, January 31, 2012(DAY)                       112                            155              2m 17d
    176          Saturday, March 17, 2012(DAY)                         20                              92                1m 17d
    671          Tuesday, March 27, 2012(DAY)                          0                               20                 10d

    This may be useful to someone. It seems that  in math, the Median is used to remove outlier numbers.


    Median

    The median is “the item in the middle”. But doesn’t the average (arithmetic mean) imply the same thing? What gives?

    Humor me for a second: what’s the “middle” of these numbers?

    • 1, 2, 3, 4, 100

    Well, 3 is the middle of the list. And although the average (22) is somewhere in the “middle”, 22 doesn’t really represent the distribution. We’re more likely to get a number closer to 3 than to 22. The average has been pulled up by 100, an outlier.

    The median solves this problem by taking the number in the middle of a sorted list. If there’s two middle numbers (even number of items), just take their average. Outliers like 100 only tug the median along one item in the sorted list, instead of making a drastic change: the median of 1 2 3 4 is 2.5.

    Arithmetic mean

    Pros:

    • Handles outliers well — often the most accurate representation of a group
    • Splits data into two groups, each with the same number of items

    Cons:

    • Can be harder to calculate: you need to sort the list first
    • Not as well-known; when you say “median”, people may think you mean “average”

      United States
      Member #124493
      March 14, 2012
      7023 Posts
      Offline
      Posted: March 28, 2012, 1:05 am - IP Logged

      interesting stuff... when you say draws between draws...do you mean skips?  i think most people would categorize it as "skips"...

      i dont even really worry about the date i just look for a symmetric skip...using skip i cant remove outlier...if a skip of 100 occurred i would expect possibly a skip of 100 again...i do use dates  as a timer though.

      i suck at algebra.Thumbs Down

        Avatar
        Appleton, Wi
        United States
        Member #118178
        October 24, 2011
        199 Posts
        Offline
        Posted: April 1, 2012, 8:02 pm - IP Logged

        Googler,

           Made a graph of days, 0 to 1400 on the X-axis and Hits, 0 to 750 on the Y-axis to see if any patterns could be recognized, but no luck, with only 10 points to plot.

           My math background not strong enough to answer your question but think a few more data points will be needed to make any useful predictions. What do you think? Oogle

          time*treat's avatar - radar

          United States
          Member #13130
          March 30, 2005
          2171 Posts
          Offline
          Posted: April 1, 2012, 8:29 pm - IP Logged

          Can be harder to calculate: you need to sort the list first

          Harder than what? If you're clever enough to graph the data, you're clever enough to sort the data.


          Not as well-known; when you say “median”, people may think you mean “average”

          Not important. Hit your numbers a few times, people will learn whatever definitions they need to.

          In neo-conned Amerika, bank robs you.
          Alcohol, Tobacco, and Firearms should be the name of a convenience store, not a govnoment agency.

            Avatar
            Appleton, Wi
            United States
            Member #118178
            October 24, 2011
            199 Posts
            Offline
            Posted: April 2, 2012, 12:26 am - IP Logged

            OK. Sequence of next hits something like this: 716  617  167  176  671 from 3-27-2012.

              Avatar
              Virginia Beach, Virginia
              United States
              Member #110060
              April 25, 2011
              115 Posts
              Offline
              Posted: April 3, 2012, 1:18 am - IP Logged

              Sorry, I don't know about skips.

              Draws between Draws is used on another site. Say that 234 hits today and again in 10 days. That 10 days is 20 Draws between Draws. The sit list each time that a number hits by Draws between Draws, and other ways. Being that the hit date varies, I was trying to decide if I should remove the outlier number to predict the next hit date. After I convert 10 Draws between Draws into days, I put the days into a Date Calculator on the web. This method gives you a suggested hit date. It has worked (luck)Clown for me a few days back.

                Avatar
                Virginia Beach, Virginia
                United States
                Member #110060
                April 25, 2011
                115 Posts
                Offline
                Posted: April 3, 2012, 1:36 am - IP Logged

                Can be harder to calculate: you need to sort the list first

                Harder than what? If you're clever enough to graph the data, you're clever enough to sort the data.


                Not as well-known; when you say “median”, people may think you mean “average”

                Not important. Hit your numbers a few times, people will learn whatever definitions they need to.

                I understand sorting this list from low to high.   "384 + 465 + 398 + 9 + 51 + 139 + 62 + 155 + 92 + 20"  I'm not sure if I should remove the outlier numbers like 9, 465, 398 because they will skew my result. There are several solutions to will give me a hit date, I just don't know which way would be the correct method.

                1) I remove the outliers. 

                2) Include numbers that aren't outliers, for a total of 10. I add, then divide the 10 to arrive at a suggested hit date.

                  time*treat's avatar - radar

                  United States
                  Member #13130
                  March 30, 2005
                  2171 Posts
                  Offline
                  Posted: April 3, 2012, 1:45 am - IP Logged

                  I understand sorting this list from low to high.   "384 + 465 + 398 + 9 + 51 + 139 + 62 + 155 + 92 + 20"  I'm not sure if I should remove the outlier numbers like 9, 465, 398 because they will skew my result. There are several solutions to will give me a hit date, I just don't know which way would be the correct method.

                  1) I remove the outliers. 

                  2) Include numbers that aren't outliers, for a total of 10. I add, then divide the 10 to arrive at a suggested hit date.

                  Is there something that would have predicted those outlier numbers?

                  If you add the heights of every person, you can calculate an "average height" -- yet relatively few real people will be that height. The outliers tell you where the limits are. You also aren't getting any/many repeats. Wink

                  In neo-conned Amerika, bank robs you.
                  Alcohol, Tobacco, and Firearms should be the name of a convenience store, not a govnoment agency.

                    SergeM's avatar - slow icon.png
                    Economy class
                    Belgium
                    Member #123700
                    February 27, 2012
                    4035 Posts
                    Offline
                    Posted: April 3, 2012, 7:23 am - IP Logged

                    HINT:  average number of not drawn in endless time: '999'

                    You have a dice with 1000 faces! You get [500 - bet] when you are right.
                    If you pay 50% of the combinations and you will have guessed right,
                    then you didn't win anything.

                     

                      Jack-in-the-Box