Test

What Is a Test?

In technical analysis and trading, a test is when a stock’s price approaches an established support or resistance level set by the market. If the stock stays within the support and resistance levels, the test passes. However, if the stock price reaches new lows and/or new highs, the test fails. In other words, for technical analysis, price levels are tested to see if patterns or signals are accurate.

A test may also refer to one or more statistical techniques used to evaluate differences or similarities between estimated values from models or variables found in data. Examples include the t-test and z-test.

Understanding Tests

Popular technical indicators that traders and investors use to test support and resistance levels include trend lines, moving averages, and round numbers.

For example, many investors pay close attention to the price action of major stock indexes, such as the Standard & Poor's 500 Index (S&P 500), Dow Jones Industrial Average (DJIA), and Nasdaq Composite when they test their 200-day moving average or a long-term trendline. More advanced techniques used to test support and resistance levels include using pivot points, Fibonacci retracement levels, and Gann angles.

The historical price chart below shows the S&P 500 testing its 200-day moving average:

Traders should monitor volume closely when a stock’s price approaches key support and resistance areas. If the volume is increasing, there is a higher probability that the price will fail when it tests these levels due to increased interest in the issue. Declining volume, on the other hand, suggests the test may pass as the stock may not have enough participation to break out to a new level.

Range-Bound Market Test

When a stock is range-bound, price frequently tests the trading range’s upper and lower boundaries. If traders are using a strategy that buys support and sells resistance, they should wait for several tests of these boundaries to confirm price respects them before entering a trade.

Once in a position, traders should place a stop-loss order in case the next test of support or resistance fails.

Trending Market Test

In an up-trending market, previous resistance becomes support, while in a down-trending market, past support becomes resistance. Once price breaks out to a new high or low, it often retraces to test these levels before resuming in the direction of the trend. Momentum traders can use the test of a previous swing high or swing low to enter a position at a more favorable price than if they would have chased the initial breakout.

A stop-loss order should be placed directly below the test area to close the trade if the trend unexpectedly reverses.

Statistical Tests

Inferential statistics uses the properties of data to test hypotheses and draw conclusions. Hypothesis testing allows one to test an idea using a data sample with regard to a population parameter. The methodology employed by the analyst depends on the nature of the data used and the reason for the analysis. In particular, one seeks to reject the null hypothesis, or the notion that one or more random variables have no effect on another. If this can be rejected, the variables are likely to be associated with one another.

There are several tools used to conduct hypothesis testing, some of which include:

• A t-test is a type of inferential statistic used to determine if there is a significant difference between the means of two groups, which may be related in certain features. It is mostly used when the data sets, like the data set recorded as the outcome from flipping a coin 100 times, would follow a normal distribution and may have unknown variances. A t-test is used as a hypothesis testing tool, which allows testing of an assumption applicable to a population. Z-tests are closely related to t-tests, but t-tests are best performed when an experiment has a smaller sample size.
• The Wilcoxon test, which can refer to either the Rank Sum test or the Signed Rank test version, is a nonparametric statistical test that compares two paired groups.
• Chi-square (χ²) is a test that measures how a model compares to actual observed data. The data used in calculating a chi-square statistic must be random, raw, mutually exclusive, drawn from independent variables, and drawn from a large enough sample. For example, the results of tossing a fair coin meet these criteria.
• The Bonferroni test is a statistical test used to reduce the instance of a false positive.
• A Scheffé test is a kind of post-hoc, statistical analysis test that is used to make unplanned comparisons.