Glossary entry (derived from question below)
English term or phrase:
response distribution
Russian translation:
процент ответов
Added to glossary by
Dmitry Murzakov
Mar 5, 2015 11:07
9 yrs ago
2 viewers *
English term
Russian Federation
Your FinMarkets Translator
Native in: Russian
Works in: English to Russian, Russian to English
response distribution
English to Russian
Tech/Engineering
Mathematics & Statistics
День добрый!
Текст про бинарные опцоны. Фраза в последнем предложении.
Typically, what happens is the trader has 10 or 20 losing trades and decides that it must be a scam because he has not had a winner, and theoretically, the trader has a 50-50 win/loss ratio. The trader might then go out and review the brokerage as being a scam and proceeds to the next option brokerage. Psychologically, he believed that after 10 losses, his probabilities of having a winner were greater because the probability of losing was now less than before. This is also known as the gambler's fallacy (that is, in the trader's mind, since he had more losers than normal, the losing chances would diminish in the future). In reality, his sampling size was too small to make an accurate determination.
Going back to the win/loss ratio of 50-50, how large does a trader's sample size need to be before he can make a statistical determination? Using the Sample Size Calculator by RaoSoft available at http://www.raosoft.com/samplesize.html, I input the following parameters:
■ 5% margin of error
■ 99% confidence level
■ Population size is unlimited, so we will use 20,000
■ Response distribution is 50%
■ RESPONSE DISTRIBUTION IS 50%
Спасибо!
Текст про бинарные опцоны. Фраза в последнем предложении.
Typically, what happens is the trader has 10 or 20 losing trades and decides that it must be a scam because he has not had a winner, and theoretically, the trader has a 50-50 win/loss ratio. The trader might then go out and review the brokerage as being a scam and proceeds to the next option brokerage. Psychologically, he believed that after 10 losses, his probabilities of having a winner were greater because the probability of losing was now less than before. This is also known as the gambler's fallacy (that is, in the trader's mind, since he had more losers than normal, the losing chances would diminish in the future). In reality, his sampling size was too small to make an accurate determination.
Going back to the win/loss ratio of 50-50, how large does a trader's sample size need to be before he can make a statistical determination? Using the Sample Size Calculator by RaoSoft available at http://www.raosoft.com/samplesize.html, I input the following parameters:
■ 5% margin of error
■ 99% confidence level
■ Population size is unlimited, so we will use 20,000
■ Response distribution is 50%
■ RESPONSE DISTRIBUTION IS 50%
Спасибо!
Proposed translations
(Russian)
| 4 | процент ответов |
Alexander Konosov
|
| 4 | плотность вероятности распределения значений отклика |
DLyons
|
| 3 | распределение ответов |
Oleg Lozinskiy
|
Change log
Dec 20, 2020 18:52: Alexander Konosov changed "Field" from "Science" to "Tech/Engineering"
Proposed translations
1 hr
Alexander Konosov
Russian Federation
Russian Federation
Native in Russian
Russian Federation
Excellence based on Engineering exp
Native in: Russian (Variant: Standard-Russia) 
Works in: English to Russian, Russian
Related KudoZ points
:
36
Selected
процент ответов
См. аналогичный, изначально русскоязычный калькулятор для расчета размера выборки по ссылке http://socioline.ru/rv.php. Цитата:
Процент ответов . Применяемая формула предполагает, что на заданный вопрос существует два варианта ответа "да" или "нет", "белый" или "черный" и так далее. Чем более равноценны оба варианта ответов, чем ближе пропорция к 50/50, тем большую выборку надо брать. Поэтому если это соотношение заранее неизвестно (а это как правило так и бывает до начала исследований), то надо ставить 50 %. По умолчанию именно такой вараинт и установлен в формуле калькулятора.
--------------------------------------------------
Note added at 1 hr (2015-03-05 12:46:30 GMT)
--------------------------------------------------
И аналогичное описание этого параметра для Вашего калькулятора:
About Response distribution: If you ask a random sample of 10 people if they like donuts, and 9 of them say, "Yes", then the prediction that you make about the general population is different than it would be if 5 had said, "Yes", and 5 had said, "No". Setting the response distribution to 50% is the most conservative assumption. So just leave it at 50% unless you know what you're doing.
Процент ответов . Применяемая формула предполагает, что на заданный вопрос существует два варианта ответа "да" или "нет", "белый" или "черный" и так далее. Чем более равноценны оба варианта ответов, чем ближе пропорция к 50/50, тем большую выборку надо брать. Поэтому если это соотношение заранее неизвестно (а это как правило так и бывает до начала исследований), то надо ставить 50 %. По умолчанию именно такой вараинт и установлен в формуле калькулятора.
--------------------------------------------------
Note added at 1 hr (2015-03-05 12:46:30 GMT)
--------------------------------------------------
И аналогичное описание этого параметра для Вашего калькулятора:
About Response distribution: If you ask a random sample of 10 people if they like donuts, and 9 of them say, "Yes", then the prediction that you make about the general population is different than it would be if 5 had said, "Yes", and 5 had said, "No". Setting the response distribution to 50% is the most conservative assumption. So just leave it at 50% unless you know what you're doing.
4 KudoZ points awarded for this answer.
Comment: "Спасибо, Александр!"
36 mins
Oleg Lozinskiy
Russian Federation
Russian Federation
Native in Russian
Russian Federation
There's No Limit to Perfection
Native in: Russian
Works in: English to Russian, Russian to English, English
Related KudoZ points
:
36
8 hrs
плотность вероятности распределения значений отклика
In this context, it means the "probability distribution function of (the values of) the response variable".
--------------------------------------------------
Note added at 9 hrs (2015-03-05 20:13:05 GMT)
--------------------------------------------------
This is admittedly using a sledgehammer to crack a nut. The point though is that the term should certainly be applicable to not just a binary variable (yes/no, 0/1) but at least to a variable taking values in N (e.g. height in mm). And conceivably taking values in R!
--------------------------------------------------
Note added at 9 hrs (2015-03-05 20:13:05 GMT)
--------------------------------------------------
This is admittedly using a sledgehammer to crack a nut. The point though is that the term should certainly be applicable to not just a binary variable (yes/no, 0/1) but at least to a variable taking values in N (e.g. height in mm). And conceivably taking values in R!
Something went wrong...