There are a great number of statistical analytic programs and methods that are used in every day life to calculate the relative risk of an activity to determine the performance of a particular stock on the stock exchange or to work out horse racing or to forecast a number in a lottery event.
Much of the present statistical analytical tools, such as Binomial, Poisson, Hyper geometric, Normal, Exponential, Student t, Chi Squared, F, Beta and Lognormal Distributions; Inverses of Normal, Student t, Chi Squared, F, Beta and Lognormal Distributions; Lists of Binomial Coefficients, Factorials and Permutations; Calculations of Gamma and Beta Functions can be applied to event level data populations and they are not much of use when the data of population contains much of random variables and high level of uncertainty of probability.
All of the above said statistical analytical methods will evaluate only the degree of probability that is to say the degree of chance of occurrence of event in population field. I have been studying various statistical analytical methods as described above as a hobby & used many of above statistical methods in forecasting, particularly in forecasting results in lottery games by using the past results. This went on for many years without getting any proper satisfactory level of forecasting. Later I tried it on many computer statistical analytical applications, mainly in Excel spread sheet applications and linear regression methods & found that you cannot predict any thing simply by feeding data of random variables as that of lottery outcomes otherwise the lottery operators would have vanished long back without any trace.
This new concept is a stumble upon & will simplify to a great extent when the population is much of random variables and unconditional. The main function of my concept is to stream line any random sequence with high uncertainty level of probability or no probability level into a conditional level and therefore very useful in much statistical analysis of probability and forecast, particularly in the use of probability density functions and uncertainty levels in the population groups. I therefore would like interested people and professionals in the field of statistics and probability theory to test the new concept, particularly in the applications of Monte Carlo simulation applications.
In my many years of research work in this field, I found a particular application in simplifying the procedures to a great extent. There are many interesting features in the new concept that they could be utilized in many such linear numerical statistical applications in evaluating results in high levels particularly in applications of high uncertainty linear random variable populations. I strongly feel that my stumble upon this method of application will be interesting subject for many research people on statistical analysis, particularly in Monte Carlo simulation applications.
L
This new concept is a stumble upon & will simplify to a great extent when the population is much of random variables and unconditional. The main function of my concept is to stream line any random sequence with high uncertainty level of probability or no probability level into a conditional level and therefore very useful in much statistical analysis of probability and forecast, particularly in the use of probability density functions and uncertainty levels in the population groups. I therefore would like interested people and professionals in the field of statistics and probability theory to test the new concept, particularly in the applications of Monte Carlo simulation applications.
I
Let us take events of a lottery of daily draw. Let the following numbers be the results of daily draw of a single digit lottery
1, 5, 8, 3, 6, 7. ……… If you look at the numbers, you will find that the events are totally at random in occurrence and absolutely with no relevance in between them. You cannot predict the next lottery number however expert you may be in statistics. There is a total uncertainty in forecasting next number. The BEST method in forecasting the next event is ‘conditional probability method ‘. In this method, another parallel format of event for each occurrence of numbers is taken in account and future event is predicted against the occurrence of the number in the conditional format. This method is known as ‘linear regression method ‘ In simple terms predicting the future value by using existing values. The predicted value is a Y value for a given X value. The known values are existing x-values and y-values, and the new value is predicted by using linear regression. You can use this function to predict future sales, inventory requirements, or consumer trends, in forecasting gambling, horse racing and many more. Given below are STEPS, which will make you to understand the NEW CONCEPT and how to use it in forecasting future events without much fuss and in utmost probability levels.
STEP -1
Select some random variable serial wise and lay those in a column K as below and in the left side column are alphabets denoting the corresponding integer on the right side. Let us select six random variables.
STEP - 2
Subtract the lower integer from the top integer of column K and display the results in the next column as shown below. The procedure goes as 1 – 5 ( A – B ) = - 4, 5 – 8 ( B – C ) = - 3, ….. so on. Continue this procedure until you get single cell display at the end, as shown in figure 2.
STEP – 3
Add all the numbers of each row and display it in the column # A shown as above as
In row A = 1 + 0 = 1, in row B = 5 + ( - 4 ) = 1, in row C = 8 + ( - 3 ) + ( - 1 ) = 4………so on
Continue this process till you gets a format on the left side and I call it as FORMATTED TRIANGLE and the first column as FORMATTED COLUMN or as # A (brown in color)
STEP - 4
The formatted triangle, as mentioned above is the main fundamental feature of the formatting and in the coming lines many interesting properties or you can say as interesting FEATURES are found in the FORMATTED TRIANGLE. Now we shall proceed further in evolving many interesting
features that the formatted triangle contains. Let us first take the formatted triangle, shown as above
Feature1). The top two digits, A & B will be same in value
Feature no. 2). The difference of third integer from 2nd, and 4th to 3rd will
- be same. B – C = C – D, as seen in the next column as -3, -3
Figure - 2
Figure – 1
( Formatted triangle)
Figure – 1 is formatted triangle as described above. When the digits displayed in the column # A is again further formatted, as shown in figure – 2, the same replica of figure – 1 is seen . That is say that the totals of each row of triangle in figure – 1, will be same as of column # A. If you take the examples in STEP-2, the formatted triangle displayed in Figure -2 is not the replica of
Figure - 1
Feature no 4) The first column # A of formatted triangle is again formatted, it will be the same replica of the first triangle.
Take the integers of column # A from figure – 1 as shown above and the end integers of same row. The display will be as below. Subtract the end nos. from column # A and observe the result.
For next feature , let us take the formatted olumn #A and include ‘ 0 ‘ on the top cell as shown below and repeat the formatting as explained in STEP -2, figure – 2.
In the above example, the column is the display of original random variables selected and the subsequent columns are the display of column A, the end nos. and last one is the total of col. A and the end nos. of each row. Let us take the column of the ‘total’ for further evolution and exploring new features as below.
Now we will triangle format the total column as explained in STEP – 2
VIEW - 1
Feature no) 13). Periodicity of alphabetical order is seen in the order of formulas.
If you look at the formulas, VIEW – 2, the periodicity of display order is seen as column wise as A, A, A, A, …….B, 2B, 3B, 4C, ……..C, 2C, 4C, 7C, 11C, ….and so on
The formatted column #A, some more fundamental properties numbering 14, 15, 16, & 17) and the formulas may be of much helpful in many statistical applications.
Feature no18) Periodicity of alphabetical order is also seen in the display of above formulas as described in feature no 13). In evolving further such features in bigger populations, computer application is needed to identify such equations as described above and also it is a matter of working this new concept on the computer surely many of similar more features could be found with the help of the computer in working with large population of data.
STEP – 8
Before going further, it is important to understand the above concepts and the said features by working with different small samples on paper, preferably on Microsoft Excel work sheet on computer and test the features.
USE OF THE NEW CONCEPT IN PROBABILITY, FORECAST
How this concept can be incorporated in evaluating probability & forecast, particularly when the population contains random and uncertainty level ? let us take some examples and work out implementing some of the said features. Sample 1s taken from STEP -7, WIEW – 1.
The numbers displayed in the column A is selected randomly and triangle formatted as described in STEP – 2.
The numbers displayed in #A column are formatted by adding integers on the left format row wise. As said that the two columns A & #A will have conditional probability, we will take the two columns separately and work out.
The easy way is to look in the 9th row ( I row ), add up the 1, 3, 5, 7 and 9th cells
Important :- the selection of the random variables must always be ODD in number
There are several ways in selecting the proper conditional serial format with column A
1). The column can be selected with any formatted column, arising there by after triangle formatting the column A as described in many examples in the above STEPS. in this way you get many options of conditional formatted series in evaluating the forest of X to a greater level of accuracy. Some times all or majority of cells in #A will coincide with the corresponding cells of column A.
2). As the column #A is formatted one with unknown event in the last column as ( - 1 - 100 ). And the above cells are known & conditional with well defined periodicity, the forecasting the last event can well be evolved with many applications of statistical analysis, most preferably with Monte Carlo simulations.
3). The features of 14), 15). 16), & 17) with formulas having well defined periodicity, and the Zero start format, described in STEP – 5, are very useful in evaluating the propagation of future trails in the conditional series.
STEP - 9
. There are several features hidden in the formatted columns like that of #A. we will explore some of the unique features by formatting the #A in different way.
Example taken is column #A. as below.
the above example it can be seen that several well defined formatted columns could be generated from single column #A. larger the integers in col. #A. larger will be the generated # columns. If the last cell of col. #A is substituted with variable X. all the end cells of each subsequent columns will have different values with X+ or X- .
Important : - in selecting any two columns in forecasting applications, the top two paired nos. in the columns should be lined in a row.
In conclusion, there are many such features that somebody can explore by using the computes and by selecting large populations. May be, some of the features thus found are more interesting and more potent in the applications of many probability forecasts.
Source: https://sites.google.com/site/newconceptssite/how-to-maximize-the-probability---forecasting-of-events-in-gambling-3
Much of the present statistical analytical tools, such as Binomial, Poisson, Hyper geometric, Normal, Exponential, Student t, Chi Squared, F, Beta and Lognormal Distributions; Inverses of Normal, Student t, Chi Squared, F, Beta and Lognormal Distributions; Lists of Binomial Coefficients, Factorials and Permutations; Calculations of Gamma and Beta Functions can be applied to event level data populations and they are not much of use when the data of population contains much of random variables and high level of uncertainty of probability.
All of the above said statistical analytical methods will evaluate only the degree of probability that is to say the degree of chance of occurrence of event in population field. I have been studying various statistical analytical methods as described above as a hobby & used many of above statistical methods in forecasting, particularly in forecasting results in lottery games by using the past results. This went on for many years without getting any proper satisfactory level of forecasting. Later I tried it on many computer statistical analytical applications, mainly in Excel spread sheet applications and linear regression methods & found that you cannot predict any thing simply by feeding data of random variables as that of lottery outcomes otherwise the lottery operators would have vanished long back without any trace.
This new concept is a stumble upon & will simplify to a great extent when the population is much of random variables and unconditional. The main function of my concept is to stream line any random sequence with high uncertainty level of probability or no probability level into a conditional level and therefore very useful in much statistical analysis of probability and forecast, particularly in the use of probability density functions and uncertainty levels in the population groups. I therefore would like interested people and professionals in the field of statistics and probability theory to test the new concept, particularly in the applications of Monte Carlo simulation applications.
In my many years of research work in this field, I found a particular application in simplifying the procedures to a great extent. There are many interesting features in the new concept that they could be utilized in many such linear numerical statistical applications in evaluating results in high levels particularly in applications of high uncertainty linear random variable populations. I strongly feel that my stumble upon this method of application will be interesting subject for many research people on statistical analysis, particularly in Monte Carlo simulation applications.
L
This new concept is a stumble upon & will simplify to a great extent when the population is much of random variables and unconditional. The main function of my concept is to stream line any random sequence with high uncertainty level of probability or no probability level into a conditional level and therefore very useful in much statistical analysis of probability and forecast, particularly in the use of probability density functions and uncertainty levels in the population groups. I therefore would like interested people and professionals in the field of statistics and probability theory to test the new concept, particularly in the applications of Monte Carlo simulation applications.
I
Let us take events of a lottery of daily draw. Let the following numbers be the results of daily draw of a single digit lottery
1, 5, 8, 3, 6, 7. ……… If you look at the numbers, you will find that the events are totally at random in occurrence and absolutely with no relevance in between them. You cannot predict the next lottery number however expert you may be in statistics. There is a total uncertainty in forecasting next number. The BEST method in forecasting the next event is ‘conditional probability method ‘. In this method, another parallel format of event for each occurrence of numbers is taken in account and future event is predicted against the occurrence of the number in the conditional format. This method is known as ‘linear regression method ‘ In simple terms predicting the future value by using existing values. The predicted value is a Y value for a given X value. The known values are existing x-values and y-values, and the new value is predicted by using linear regression. You can use this function to predict future sales, inventory requirements, or consumer trends, in forecasting gambling, horse racing and many more. Given below are STEPS, which will make you to understand the NEW CONCEPT and how to use it in forecasting future events without much fuss and in utmost probability levels.
STEP -1
Select some random variable serial wise and lay those in a column K as below and in the left side column are alphabets denoting the corresponding integer on the right side. Let us select six random variables.
STEP - 2
Subtract the lower integer from the top integer of column K and display the results in the next column as shown below. The procedure goes as 1 – 5 ( A – B ) = - 4, 5 – 8 ( B – C ) = - 3, ….. so on. Continue this procedure until you get single cell display at the end, as shown in figure 2.
STEP – 3
Add all the numbers of each row and display it in the column # A shown as above as
In row A = 1 + 0 = 1, in row B = 5 + ( - 4 ) = 1, in row C = 8 + ( - 3 ) + ( - 1 ) = 4………so on
Continue this process till you gets a format on the left side and I call it as FORMATTED TRIANGLE and the first column as FORMATTED COLUMN or as # A (brown in color)
STEP - 4
The formatted triangle, as mentioned above is the main fundamental feature of the formatting and in the coming lines many interesting properties or you can say as interesting FEATURES are found in the FORMATTED TRIANGLE. Now we shall proceed further in evolving many interesting
features that the formatted triangle contains. Let us first take the formatted triangle, shown as above
Feature1). The top two digits, A & B will be same in value
Feature no. 2). The difference of third integer from 2nd, and 4th to 3rd will
- be same. B – C = C – D, as seen in the next column as -3, -3
Figure - 2
Figure – 1
( Formatted triangle)
Figure – 1 is formatted triangle as described above. When the digits displayed in the column # A is again further formatted, as shown in figure – 2, the same replica of figure – 1 is seen . That is say that the totals of each row of triangle in figure – 1, will be same as of column # A. If you take the examples in STEP-2, the formatted triangle displayed in Figure -2 is not the replica of
Figure - 1
Feature no 4) The first column # A of formatted triangle is again formatted, it will be the same replica of the first triangle.
Take the integers of column # A from figure – 1 as shown above and the end integers of same row. The display will be as below. Subtract the end nos. from column # A and observe the result.
For next feature , let us take the formatted olumn #A and include ‘ 0 ‘ on the top cell as shown below and repeat the formatting as explained in STEP -2, figure – 2.
In the above example, the column is the display of original random variables selected and the subsequent columns are the display of column A, the end nos. and last one is the total of col. A and the end nos. of each row. Let us take the column of the ‘total’ for further evolution and exploring new features as below.
Now we will triangle format the total column as explained in STEP – 2
VIEW - 1
Feature no) 13). Periodicity of alphabetical order is seen in the order of formulas.
If you look at the formulas, VIEW – 2, the periodicity of display order is seen as column wise as A, A, A, A, …….B, 2B, 3B, 4C, ……..C, 2C, 4C, 7C, 11C, ….and so on
The formatted column #A, some more fundamental properties numbering 14, 15, 16, & 17) and the formulas may be of much helpful in many statistical applications.
Feature no18) Periodicity of alphabetical order is also seen in the display of above formulas as described in feature no 13). In evolving further such features in bigger populations, computer application is needed to identify such equations as described above and also it is a matter of working this new concept on the computer surely many of similar more features could be found with the help of the computer in working with large population of data.
STEP – 8
Before going further, it is important to understand the above concepts and the said features by working with different small samples on paper, preferably on Microsoft Excel work sheet on computer and test the features.
USE OF THE NEW CONCEPT IN PROBABILITY, FORECAST
How this concept can be incorporated in evaluating probability & forecast, particularly when the population contains random and uncertainty level ? let us take some examples and work out implementing some of the said features. Sample 1s taken from STEP -7, WIEW – 1.
The numbers displayed in #A column are formatted by adding integers on the left format row wise. As said that the two columns A & #A will have conditional probability, we will take the two columns separately and work out.
The easy way is to look in the 9th row ( I row ), add up the 1, 3, 5, 7 and 9th cells
Important :- the selection of the random variables must always be ODD in number
There are several ways in selecting the proper conditional serial format with column A
1). The column can be selected with any formatted column, arising there by after triangle formatting the column A as described in many examples in the above STEPS. in this way you get many options of conditional formatted series in evaluating the forest of X to a greater level of accuracy. Some times all or majority of cells in #A will coincide with the corresponding cells of column A.
2). As the column #A is formatted one with unknown event in the last column as ( - 1 - 100 ). And the above cells are known & conditional with well defined periodicity, the forecasting the last event can well be evolved with many applications of statistical analysis, most preferably with Monte Carlo simulations.
3). The features of 14), 15). 16), & 17) with formulas having well defined periodicity, and the Zero start format, described in STEP – 5, are very useful in evaluating the propagation of future trails in the conditional series.
STEP - 9
. There are several features hidden in the formatted columns like that of #A. we will explore some of the unique features by formatting the #A in different way.
Example taken is column #A. as below.
the above example it can be seen that several well defined formatted columns could be generated from single column #A. larger the integers in col. #A. larger will be the generated # columns. If the last cell of col. #A is substituted with variable X. all the end cells of each subsequent columns will have different values with X+ or X- .
Important : - in selecting any two columns in forecasting applications, the top two paired nos. in the columns should be lined in a row.
In conclusion, there are many such features that somebody can explore by using the computes and by selecting large populations. May be, some of the features thus found are more interesting and more potent in the applications of many probability forecasts.
Source: https://sites.google.com/site/newconceptssite/how-to-maximize-the-probability---forecasting-of-events-in-gambling-3
