# Regression Slope Cross

HTS's **Regression Slope Cross indicator** is used for modeling the relationship between an independent variable (time in this case) and one or more dependent variables (the exchange rate for example). We assume the relation to be linear and use a least squares model to 'fit' a line to the selection of data points that best explains the trend the data may be showing. This is our most advanced Indicator.

## Contents

## HTS 3.0 Interface

## Formula

**Regression Slope Cross** works by measuring the above relationships. Our interpretation of this indicator is as follows:

An increasing trend (positive slope of the regression line) means the mean of the data is likely to keep increasing (a good buy signal). A decreasing trend (negative slope) means the mean of the data is likely to keep decreasing (which might be a good sell signal).

A confidence interval for the slope is also given at a certain confidence level alpha. This can be understood as follows. If alpha = 5% and the confidence interval for the slope is (+0.1) ± (0.05) we are 95% confident that the slope is between +0.05 and +0.15, or (.1 - .05) and (.1 + .05). In other words, the trend is significantly increasing over time!

The prediction interval is also given. Within this interval, we expect, with a probability of 1-alpha, to find a future observation.

Slope and intervals depend on the number of data points included in the dataset, the variability in the set, and of course if the data shows any trend. Generally speaking, the narrower the intervals, the more confident we can be.

## Settings

- Exchange Website to monitor (Pro Tip: It doesn't have to be the same exchange you are currently trading on).
- Currency Pair to monitor for trade signals.
- Update Speed
- Trade Signals
- Data Length (Smaller Length = more signals but not necessarily good signals | Longer Length = less signals but better trend reversal signals)

## Usage

This indicator is useful for generating strong trade signals for coins that have high volume and high volatility.