Это все подвиды Trade Randomization
Trade Randomization (TR)
This method randomizes various elements of the raw trades, and actually creates a new historical simulation, and resulting equity curve based on the randomized trades. The following options are available to control trade randomization:
(На основе доходностей актива создаются новые исторические данные и кривая эквити строится на этих новых сгенерированных данных)
Trade Scramble
The first method of Trade Randomization is Trade Scramble. The starting dates of all of the raw trades are randomized, and a simulation is performed based on the randomized start dates.
(Случайно выбираются начальные даты каждого трейда)
Trade Scramble and Randomize
Same as Trade Scramble above, but additionally, the bar by bar returns of each raw trade are randomized. This randomization does not impact the resulting Net Profit of the raw trade, but it does impact the equity curve and therefore may influence how new positions are sized.
(Дополнительно рандомизируется барные доходности(внутри каждого трейда))
Trade Synthesize
Same as Trade Scramble, above, but the bar by bar returns of each raw trade are synthesized. Each bar by bar return is synthesized by selecting a random bar by bar return from the complete list of bar by bar returns for all raw trades.
(Еще немного перемешиваем - теперь барные доходности берутся из других открытых позиций)
Allow Trade Recycling
Applies to: All TR Methods
This option specifies whether or not to allow raw trades to be re-sampled during the Trade Randomization process. Enabling this option allows an additional level of randomization, because a raw trade could be selected more than once when creating the randomized simulation, and some raw trades might not be selected at all.
(Выборка с возвращением или без)
Allow Trade Return Recycling
Applies to: All TR Methods except Trade Scramble
If enabled, it allows the raw trade's bar by bar returns to be re-sampled during the process of randomizing the trade's bar by bar returns. This results in an additional level of randomization.
(Выборка ьарных доходностей внутри трейда с возвращением или без)
Maintain Date Clustering
Applies to: All TR Methods
This option forces the randomized entry dates to be drawn from the actual entry dates of the raw trades, instead of being completely randomized within the testing period. Enabling this setting can help more accurately simulate strategies that have low exposure.
(Убирает рандомизацию по датам)
Maintain Win/Loss Sequence
Applies to: All TR Methods
This option forces the randomized trades to maintain the same win/loss sequence of the trades in the raw trade list. This can help the Monte Carlo simulations to more accurately model the events and trends that occurred during the testing period.
(Сохранять или нет последовательность Win/Loss)