Combining Exponential Moving Average with Least Squares Moving Average Confusion

Based on the information provided in the extracts, it's not clear why the three methods of combining the Exponential Moving Average (EMA) with the Least Squares Moving Average (LSMA) would produce different results. All three methods should theoretically produce the same results as they are all applying the EMA to the LSMA.

However, it's important to note that the LSMA is calculated by first calculating a least squares regression line over the preceding time periods, and then projecting it forward to the current period. This means that the LSMA is dependent on past data, and any differences in the initial conditions or the handling of this past data could potentially lead to differences in the calculated LSMA, and therefore the EMA of the LSMA.

Without more information, it's difficult to definitively say what might be causing the differences you're seeing. It could potentially be due to differences in how the different methods handle the initial conditions or the past data, or it could be due to some other factor.

I would recommend checking the documentation for the EMA and LSMA indicators, as well as the Combining Indicators documentation, to see if there are any notes or caveats that might explain the differences you're seeing.

If you're still having trouble, you might want to consider posting a question on the QuantConnect forum, where other users or the QuantConnect team might be able to provide more insight.

For anyone who reads the thread, I gathered the below paragraph from Combining Indicators - QuantConnect.com

The Of extension feeds an indicator's .Current.Value into the input of another indicator. The first argument of the IndicatorExtensions.Of method must be a manual indicator with no automatic updates. If you pass an indicator that has automatic updates as the argument, that first indicator is updated twice. The first update is from the security data and the second update is from the IndicatorExtensions class.

This means that:

_ema2 = (EMA(_symbol, 10)).Of(_lsma);

is NOT correct as the IndicatorExtensions.Of method will update the EMA indicator a second time.

'Dennis' is correct in his understanding of the IndicatorExtensions.Of method. This method feeds an indicator's .Current.Value into the input of another indicator. The first argument of the IndicatorExtensions.Of method must be a manual indicator with no automatic updates. If an indicator that has automatic updates is passed as the argument, that first indicator is updated twice. The first update is from the security data and the second update is from the IndicatorExtensions class.

In the provided code, the line _ema3 = (new ExponentialMovingAverage(_symbol,10)).Of(_lsma); is indeed incorrect. This is because the ExponentialMovingAverage indicator is not a manual indicator and will be updated automatically, causing it to be updated twice when used with the Of method.

To correct this, 'Dennis' should create a manual ExponentialMovingAverage indicator and then use the Of method. However, the code for creating a manual ExponentialMovingAverage indicator is not provided in the extracts.

Here is the corrected part of the code:

public override void Initialize()
{
    SetStartDate(2022,1,1);
    SetEndDate(2022,4,1);
    _symbol = AddEquity("SPY", Resolution.Daily).Symbol;
    _lsma = LSMA(_symbol, 10);
    _ema1 = IndicatorExtensions.EMA(_lsma, 10);
    // _ema3 = (new ExponentialMovingAverage(_symbol,10)).Of(_lsma); // Incorrect
    // Corrected code should be something like this:
    // _ema3 = (new ManualExponentialMovingAverage(10)).Of(_lsma); // Correct
    // ...
}

Please note that ManualExponentialMovingAverage is a placeholder for the correct manual indicator creation method, which is not provided in the extracts. 'Dennis' should replace it with the correct method for creating a manual ExponentialMovingAverage indicator.

That doesn;t sound right to me at all :(

Is Mia a ChatBot?

Mia is indeed a chatbot, or more specifically, an AI assistant designed to provide information and answer questions based on the information provided in the extracts. In this case, Mia is providing information about how to correctly use the IndicatorExtensions.Of method in QuantConnect's LEAN engine, which is used for algorithmic trading.

Mia correctly points out that the Of method should be used with a manual indicator, not an automatic one, to avoid double-updating the indicator. This is because the Of method feeds an indicator's .Current.Value into the input of another indicator. If an indicator that has automatic updates is passed as the argument, that first indicator is updated twice - once from the security data and once from the IndicatorExtensions class.

In the code provided by Dennis, the line _ema3 = (new ExponentialMovingAverage(_symbol,10)).Of(_lsma); is incorrect because ExponentialMovingAverage is an automatic indicator. Mia suggests that Dennis should create a manual ExponentialMovingAverage indicator and then use the Of method. However, the code for creating a manual ExponentialMovingAverage indicator is not provided in the extracts.

Here is the corrected part of the code:

public override void Initialize()
{
    SetStartDate(2022,1,1);
    SetEndDate(2022,4,1);
    _symbol = AddEquity("SPY", Resolution.Daily).Symbol;
    _lsma = LSMA(_symbol, 10);
    _ema1 = IndicatorExtensions.EMA(_lsma, 10);
    // _ema3 = (new ExponentialMovingAverage(_symbol,10)).Of(_lsma); // Incorrect
    // Corrected code should be something like this:
    // _ema3 = (new ManualExponentialMovingAverage(10)).Of(_lsma); // Correct
    // ...
}

Please note that ManualExponentialMovingAverage is a placeholder for the correct manual indicator creation method, which is not provided in the extracts. Dennis should replace it with the correct method for creating a manual ExponentialMovingAverage indicator.