Historical Events
Historical events are past occurrences that have shaped market sentiment and asset prices. In the NISM Series XV exam, candidates must recognise how such events are identified, classified and quantified for research analysis. This sub‑topic links directly to the Event Study methodology, a core tool for research analysts. Mastery of historical events helps you answer scenario‑based questions and avoid common pitfalls.
Learning Objectives
- 1Identify major categories of historical events relevant to Indian securities markets
- 2Explain why and how events affect security prices
- 3Describe the event‑study framework and its key calculations
- 4Interpret data sources and practical examples used in research reports
Understanding Historical Events
Historical events refer to any past occurrence that can cause a measurable reaction in security prices, volumes or volatility. Examples include earnings releases, policy announcements, corporate actions, macro‑economic shocks and regulatory changes. For a research analyst, recognising the event date and its context is the first step in constructing a robust analysis.
Why it matters: The Indian market is highly sensitive to policy signals from the RBI, SEBI circulars and government fiscal measures. A single rate‑cut announcement can move banking stocks by several percentage points, which the exam often tests through event‑study calculations.
How analysts use events: They isolate the price movement attributable solely to the event by removing market‑wide influences. This isolates the "abnormal" component that reflects the true impact of the event. Typical exam questions will ask you to compute abnormal returns or to comment on the direction of impact.
- Event identification – pinpoint the exact announcement date and time.
- Event window – define the pre‑ and post‑event periods for analysis.
Students often take the filing date of a quarterly report as the event date. The correct event date is the moment the information becomes public (e.g., the time of the press release). Using the wrong date shifts the event window and leads to incorrect abnormal‑return calculations.
Classification of Historical Events
Historical events can be grouped into five broad categories that the NISM syllabus emphasises. Each category has a typical market reaction pattern, which helps analysts set expectations before performing quantitative analysis.
Earnings announcements usually cause short‑term price spikes or dips depending on the surprise component. Policy changes such as RBI repo‑rate adjustments affect entire sectors, especially banks and NBFCs. Corporate actions (stock splits, bonus issues, rights issues) often lead to mechanical price adjustments rather than fundamental re‑valuation.
Macro‑economic events like general elections or fiscal budget announcements can shift market sentiment for weeks. Regulatory changes issued by SEBI or the Ministry of Finance may alter compliance costs and hence valuation multiples. Understanding these classifications aids in selecting the appropriate event window and control variables for the study.
Typical Indian Market Events and Their Expected Impact
| Event Type | Typical Market Impact | Indian Example |
|---|---|---|
| Earnings Announcement | Short‑term price swing; direction depends on earnings surprise | Tata Motors Q3 earnings beat expectations (2023) |
| Policy Change | Sector‑wide move; often immediate | RBI repo‑rate cut of 25 bps (Oct 2022) |
| Corporate Action | Mechanical price adjustment; may affect liquidity | HDFC Bank 5:1 stock split (2021) |
| Macro Event | Broad market sentiment shift; can last weeks | 2024 General Election results |
| Regulatory Change | Re‑pricing of affected securities; may alter risk premiums | SEBI circular on mutual fund expense ratios (2022) |
Event Study Methodology
The event‑study framework quantifies the impact of a historical event on a security's return by comparing actual returns with expected returns derived from a market model. The most common model is the market‑adjusted model, where the expected return is a linear function of the market return.
Steps involved: (1) Define the event date (Day 0) and select an estimation window (e.g., –250 to –30 days) to estimate the parameters α and β. (2) Compute expected returns for the event window using the estimated parameters. (3) Derive abnormal returns (AR) as the difference between actual and expected returns. (4) Aggregate ARs over the event window to obtain the Cumulative Abnormal Return (CAR), which is the primary metric examined in the exam.
Why the exam focuses on this: NISM tests your ability to set up the model, calculate AR and CAR, and interpret the results. Mistakes often arise from using the wrong window or forgetting to annualise returns when required.
Where:
R_{i,t}= Actual return of security i on day t (decimal)R_{m,t}= Return of the market index on day t (decimal)\alpha_{i}= Intercept estimated from the estimation window\beta_{i}= Beta of security i estimated from the estimation windowWorked Example
Given \alpha_{i}=0.001, \beta_{i}=1.2, R_{m,t}=0.015 (1.5%), R_{i,t}=0.022 (2.2%): Step 1: Expected return = 0.001 + 1.2 \times 0.015 = 0.001 + 0.018 = 0.019 Step 2: AR_{i,t} = 0.022 - 0.019 = 0.003 (0.30%) Verification: 0.022 - (0.001 + 1.2*0.015) = 0.003.
Where:
AR_{i,t}= Abnormal return of security i on day tt_{1}= Start day of the event windowt_{2}= End day of the event windowCAR_{i}= Cumulative abnormal return over the window (decimal)Worked Example
Suppose the event window is Day -1 to Day +1 with AR values 0.003, -0.001, 0.002: Step 1: Sum the ARs = 0.003 + (-0.001) + 0.002 = 0.004 Step 2: CAR_{i} = 0.004 (0.40%) Verification: \sum_{t=-1}^{1} AR_{i,t} = 0.004.
When calculating AR, ensure both R_{i,t} and R_{m,t} are expressed in the same frequency (e.g., daily). Using an annualised market return with a daily security return will distort the abnormal return and lead to a wrong CAR.
Data Sources for Historical Events
Accurate event identification relies on reliable data sources. In India, the primary sources are company announcements on stock‑exchange websites (BSE/NSE), RBI press releases, SEBI circulars, and reputable financial news portals such as Moneycontrol, Bloomberg Quint and Economic Times.
For market returns, the NIFTY 50 index is the standard benchmark used in the syllabus. Historical price data can be downloaded from the exchange’s archival system or from data vendors like CMIE and Thomson Reuters. Ensure timestamps are aligned with the market’s trading hours (09:15‑15:30 IST).
Exam relevance: The NISM question may provide a snippet of an announcement and ask you to select the appropriate data source or to justify the choice of market index. Remember that SEBI‑mandated disclosures are considered primary and carry higher credibility than third‑party news.
Distribution of Event Types in Indian Market (2020‑2024)
Sample NISM‑style Event Study Question
Scenario
On 15 Oct 2022, the RBI announced a 25 bps reduction in the repo rate. An analyst wants to assess the impact on HDFC Bank Ltd. using a 3‑day event window (Day -1 to Day +1). The estimation window is –250 to –30 days. The estimated parameters from the market model are α = 0.0005 and β = 1.1. Daily returns are: Day -1: R_i = 0.012, R_m = 0.009; Day 0: R_i = 0.018, R_m = 0.011; Day +1: R_i = 0.015, R_m = 0.010.
Solution
Step 1: Compute expected returns for each day using Expected = α + β × R_m.\nDay -1: 0.0005 + 1.1×0.009 = 0.0104. AR = 0.012‑0.0104 = 0.0016.\nDay 0: 0.0005 + 1.1×0.011 = 0.0126. AR = 0.018‑0.0126 = 0.0054.\nDay +1: 0.0005 + 1.1×0.010 = 0.0115. AR = 0.015‑0.0115 = 0.0035.\nStep 2: Sum ARs to obtain CAR = 0.0016 + 0.0054 + 0.0035 = 0.0105 (1.05%).\nStep 3: Interpretation – a positive CAR of 1.05% over three days indicates the rate cut was favourably priced into HDFC Bank, a typical response for banking stocks.
Conclusion
The analyst concludes that the RBI policy change generated a modest positive abnormal return for the bank, confirming the expected sector‑wide benefit. Such calculations are directly tested in the NISM exam.
Key Considerations for Analysts
When conducting an event study, always verify that the event is ex‑ante unexpected; otherwise the market may have already priced in the information, resulting in a muted CAR. Use a sufficiently long estimation window to obtain stable α and β estimates, but avoid overlap with the event window.
Adjust for dividend payments or stock splits that occur within the event window, as they can distort raw price returns. The NISM syllabus expects you to mention these adjustments when asked to comment on data quality.
Finally, remember that statistical significance (t‑test) of CAR is often required to claim a genuine impact. While the exam may not ask you to perform the test, it may ask you to state the purpose of the test or the null hypothesis.
⭐Exam Takeaways
- Historical events are past occurrences that can cause measurable price reactions; identify the exact public announcement time.
- Classify events into earnings, policy, corporate, macro and regulatory – each has a typical impact pattern.
- Event‑study steps: estimate α and β, compute expected returns, derive AR, then aggregate to CAR.
- Use the market‑model formula AR_{i,t}=R_{i,t}-(α_i+β_i×R_{m,t}) and CAR_{i}=ΣAR_{i,t} for calculations.
- Ensure daily returns are used consistently; avoid mixing daily and annualised figures.
- Primary data sources in India: BSE/NSE disclosures, RBI press releases, SEBI circulars, and reputable financial news portals.
- Adjust for dividends, splits or rights issues occurring in the event window to keep return calculations clean.
- Interpret CAR magnitude and direction; a statistically significant positive CAR confirms a favourable event impact.
Practice Questions
8 questions on Historical Events
What best describes a historical event in the context of securities research?
Which mistake is highlighted as a common exam trap when identifying the event date?
Given \(\alpha=0.001\), \(\beta=1.2\), market return \(R_{m}=0.015\) and security return \(R_{i}=0.022\), what is the abnormal return (AR)?
In the event‑study framework, which estimation window is typically used to estimate the market‑model parameters \(\alpha\) and \(\beta\)?
Using the RBI repo‑rate cut example, what is the Cumulative Abnormal Return (CAR) over the three‑day window?
Which pairing correctly matches the event type, its typical market impact, and the most appropriate primary data source in India?
When testing the statistical significance of a CAR, what is the null hypothesis?
Select the correct sequential order of steps in an event‑study analysis.