In this article, we will show how to read and understand the whole report of the alpha analysis.
All screenshots in this report are based on using PE Ratio (TTM) as our alpha, and we split it into 5 quantiles and analyse 5D, 21D and 63D forward returns.
The report is separated into 2 parts:
We will go to each table/chart and explain its meaning and importance.
This table shows how data has been split into quantiles/bins and relevant statistics of factor values in each quantile/bin. In the screenshot below, we can clearly see that each quantile has roughly 20% entries because we bucketed into 5 quantiles.
This is perhaps the most important chart in this section. In the chart below, we can clearly see the average forward return declines as we move from the bottom quantile to the top quantile. In simpler terms, we can say that lower PE stocks on average have higher forward returns than higher PE stocks (the value factor).
Ideally, you would want the chart to be moving in a single direction – either upwards or downwards (as is the case with PE Ratio). This gives a good indication of alpha strength. You would also want a decent spread between the top and bottom quantiles, which brings us to the next table.
This provides a snapshot of the average forward return of the top and bottom quantiles and the return difference between the top and bottom quantiles across return periods.
In the screenshot below, it can be clearly seen that the spread between top and bottom quantile stocks for the PE Ratio is around 30-35 bps.
This gives you a time series of how the spread between the top and bottom quantile has moved along with standard deviation and 1-month moving average.
While analysing spread, looking at the average gives you an idea, you would ideally also want to see how the spreads have moved historically. You would want that spreads are consistently positive or consistently negative and are tight (do not exhibit a very high standard deviation). This helps you assess the robustness of your alpha. The screenshot below shows how spreads have moved historically (August 2022 to August 2025) for the PE Ratio.
Finally, you would want to see how your alpha works for different sectors. Is your alpha sector specific, or does it work across the universe? So, you can analyse average forward return for each quantile and each period for each sector.
The second section of the report deals with the analysis of the Information Coefficient.
Information Coefficient is another way of looking at a factor's predictability. The IC is computed as the Spearman Rank Correlation between factor values and forward returns.
Note that we use Spearman Rank Correlation, and hence, IC represents the correlation between stock rank (based on factor values) and forward return rank. The IC gives information on how well the factor sorts stocks across the whole distribution of data relative to future returns.
This table gives a summary of the IC for each return period. As can be seen in the screenshot below, PE Ratio has negative IC, implying that the rank of stocks based on PE Ratio is negatively correlated with the rank of stocks based on forward returns.
The second chart gives the IC summary for each sector. This helps you assess if your alpha is robust across sectors or concentrated in a few sectors.
Ideally, you would want a statistically significant IC with higher absolute values (can be negative as well). But you would also want a stable and consistent IC over time.
The charts below show how IC has moved over time for each time period. This gives you an idea of how stable the predictive power of your alpha is.
Don’t get confused with negative IC. This just means that your alpha implies a higher return for lower values of alpha. You can simply reverse this by using alpha = -1 * alpha in portfolio construction.