Also found in: Encyclopedia.

R Square

In statistics, the percentage of a portfolio's performance explainable by the performance of a benchmark index. The R square is measured on a scale of 0 to 100, with a measurement of 100 indicating that the portfolio's performance is entirely determined by the benchmark index, perhaps by containing securities only from that index. A low R square indicates that there is no significant relationship between the portfolio and the index. An R Square is also called the coefficient of determination. See also: Beta.


R-squared is a statistical measurement that determines the proportion of a security's return, or the return on a specific portfolio of securities, that can be explained by variations in the stock market, as measured by a benchmark index.

For example, an r-squared of 0.08 shows that 80% of a security's return is the result of changes in the market -- specifically that 80% of its gains are due to market gains and 80% of its losses are due to market losses. The other 20% are the result of factors particular to the security itself.

References in periodicals archive ?
Extensive work has been done on SPS using R-squared obtained from the regression of individual stock return to stock market returns (Morck, Yeung, & Yu, 2000; Durnev, Li, Morck, & Yeung, 2004; Farooq & Ahmed, 2014; Farooq & ElBannan, 2016).
The values of R-squared for the model are calculated as 0.
Now take a look at the R-squared value of 77% presented in cell B5 of the regression output in Figure 4.
As shown in Table 4, R-squared estimates were between 8 and 20 percentage points higher for the DxCG prospective model with pharmacy than the CMS V21 model.
The scatter plot graph results of the treatment area ratios of radiofrequency ablation before or after showed that R-squared (R2) was 0.
In Table 5 and 6 R-squared and Adjusted R-squared values are close to 0, which means that the links between the evolution of CPI, exchange rate and interest rate are not very strong.
The comparison of adjusted R-squared of regression coefficient's first hypothesis was that the only difference in the dependent variables, indicates that the dependent variable NDNIj,t+1 is the coefficient of the highest value.
R-squared is a determination coefficient that represents the estimation of the total variation of the data described by the model.
We also note that the coefficient of determination, R-squared, increases dramatically from 0.
092) ** Lagged GDP per capita Lagged agriculture share Lagged manufacturing Share Lagged mining share Lagged export intensity Lagged import intensity AR(1) Country-fixed effect No Yes Observations 792 792 Adjusted R-squared 0.
The models show significant r-squared ranging from 56 percent to 93 percent.