vpFREE2 Forums

Does High Variance really matter? Utility theory and CLT

Most any formula that is based on variance is

likely to be an approximation, unless it was variance itself
that you want to compute.

Any opinion on whether variance calculations are based on the CLT?
That question was raised earlier. My impression is it isn't based on
the CLT, although variance is part of the CLT formula itself.

···

--- In vpFREE@yahoogroups.com, Steve Jacobs <jacobs@x> wrote:

the variance calculation is exact
central limit theory says for an infinite sample size the distribution
is normal
for a less than infinite sample size clt is an approximation, thus
calculations that depend on clt are approximations (typically
calculations that use variance are approximations)
jazbo presents actual distributions here:
http://66.223.68.238/videopoker/curves.html

Most any formula that is based on variance is
> likely to be an approximation, unless it was variance itself
> that you want to compute.
>>>>>>>>>>>>>>>>>
Any opinion on whether variance calculations are based on the CLT?
That question was raised earlier. My impression is it isn't based

on

···

--- In vpFREE@yahoogroups.com, "brumar_lv" <brumar_lv@y...> wrote:

--- In vpFREE@yahoogroups.com, Steve Jacobs <jacobs@x> wrote:
the CLT, although variance is part of the CLT formula itself.

jazbo is not presenting exact distributions he is posting the results
of "simulations" there is an important difference. CLT is the theorem
that allows you to make the Normal approximations.

Assuming that jazbo's results are based on computer simultion of
dealing 10,000 hands...these are the types of results that I would
look at to get a handle on ror, and not look at so called exact
solutions which may give the appearance of exactness but are highly
flawed.

--- In vpFREE@yahoogroups.com, "nightoftheiguana2000"
<nightoftheiguana2000@y...> wrote:

the variance calculation is exact
central limit theory says for an infinite sample size the

distribution

is normal
for a less than infinite sample size clt is an approximation, thus
calculations that depend on clt are approximations (typically
calculations that use variance are approximations)
jazbo presents actual distributions here:
http://66.223.68.238/videopoker/curves.html

>
> Most any formula that is based on variance is
> > likely to be an approximation, unless it was variance itself
> > that you want to compute.
> >>>>>>>>>>>>>>>>>
> Any opinion on whether variance calculations are based on the

CLT?

···

--- In vpFREE@yahoogroups.com, "brumar_lv" <brumar_lv@y...> wrote:
> --- In vpFREE@yahoogroups.com, Steve Jacobs <jacobs@x> wrote:
> That question was raised earlier. My impression is it isn't based
on
> the CLT, although variance is part of the CLT formula itself.

--- In vpFREE@yahoogroups.com, "jaydavidson118" <jaydavidson118@y...>
wrote:

jazbo is not presenting exact distributions he is posting the

results

of "simulations" there is an important difference

yes there is an important difference
jazbo has presented exact distributions not simulations

No, no, no...jazbo presented the results of many Simulations this is
not the same as identifying an exact distribution the describes the
nature of returns such as Binomial distibution or Poisson distribution
Do you understand the difference now?

--- In vpFREE@yahoogroups.com, "nightoftheiguana2000"
<nightoftheiguana2000@y...> wrote:

--- In vpFREE@yahoogroups.com, "jaydavidson118"

<jaydavidson118@y...>

···

wrote:
> jazbo is not presenting exact distributions he is posting the
results
> of "simulations" there is an important difference

yes there is an important difference
jazbo has presented exact distributions not simulations

well, there's a big chunk of math that you don't understand so for you
it doesn't exist

--- In vpFREE@yahoogroups.com, "jaydavidson118" <jaydavidson118@y...>
wrote:

No, no, no...jazbo presented the results of many Simulations this

is

not the same as identifying an exact distribution the describes the
nature of returns such as Binomial distibution or Poisson

distribution

···

Do you understand the difference now?

--- In vpFREE@yahoogroups.com, "nightoftheiguana2000"
<nightoftheiguana2000@y...> wrote:
>
> --- In vpFREE@yahoogroups.com, "jaydavidson118"
<jaydavidson118@y...>
> wrote:
> > jazbo is not presenting exact distributions he is posting the
> results
> > of "simulations" there is an important difference
>
> yes there is an important difference
> jazbo has presented exact distributions not simulations

Yes, you are right there is a big chunk of math that I don't
understand, unfortunately for you that chunk is obviously even bigger!

--- In vpFREE@yahoogroups.com, "nightoftheiguana2000"
<nightoftheiguana2000@y...> wrote:

well, there's a big chunk of math that you don't understand so for

you

it doesn't exist

--- In vpFREE@yahoogroups.com, "jaydavidson118"

<jaydavidson118@y...>

wrote:
>
> No, no, no...jazbo presented the results of many Simulations this
is
> not the same as identifying an exact distribution the describes

the

···

> nature of returns such as Binomial distibution or Poisson
distribution
> Do you understand the difference now?
>
> --- In vpFREE@yahoogroups.com, "nightoftheiguana2000"
> <nightoftheiguana2000@y...> wrote:
> >
> > --- In vpFREE@yahoogroups.com, "jaydavidson118"
> <jaydavidson118@y...>
> > wrote:
> > > jazbo is not presenting exact distributions he is posting the
> > results
> > > of "simulations" there is an important difference
> >
> > yes there is an important difference
> > jazbo has presented exact distributions not simulations

1. do you understand how to calculate the EXACT probabilities for one
hand of video poker?

here they are for full pay deuces wild max-er strategy:

rf 440202756/19933230517200
4d 4060462824/19933230517200
wrf 35796957696/19933230517200
5k 63818309856/19933230517200
sf 82122481680/19933230517200
4k 1294427430576/19933230517200
fh 423165297240/19933230517200
fl 330506232804/19933230517200
st 1127512239276/19933230517200
3k 5671888316712/19933230517200
zip 10899492585780/19933230517200

2. do you understand how to calculate the EXACT R(1) number for these
probabilities and do you understand that given R(1) you can EXACTLY
determine risk of ruin for any starting bankroll?

3. do you understand how to calculate the EXACT probabilities for two
hands of video poker?

4. do you understand how to calculate the EXACT probabilities for any
number of hands of video poker?