Week1 Assignment Approach

Overview

I will build a workflow around VOO (Vanguard S&P 500 ETF) historical market data from Yahoo Finance. The goal is to 1. acquire the dataset from an accessible source 2. load it into R in a clean, well-documented way 3. perform a small set of transformations that make the data analysis-ready for later weeks.

Related article (anchor for motivation and context):

Vanguard triumphs over State Street to take largest ETF crown (Financial Times, https://www.ft.com/content/641e9fd7-c989-4831-917b-23b3250be7db)
This article discusses VOO’s scale and why low-cost index ETFs have become dominant.

Dataset and source

Dataset: VOO (Vanguard S&P 500 ETF) historical daily price series
Source: Yahoo Finance VOO historical data: https://finance.yahoo.com/quote/VOO/history/

What the dataset contains

VOO historical market data provides a daily time series with the following columns: Date, Open, High, Low, Close, Adj.Close, Volume. The “Close” is adjusted for splits, while “Adj.Close” is adjusted for dividends and splits, which makes it better for return calculations.

VOO itself is an index ETF designed to track the performance of the S&P 500 Index.

Motivation for selecting this dataset

I chose VOO because:

• It is widely used in real investing (and personally relevant, I hold some): VOO is a core S&P 500 index ETF, so its returns and risk profile are a practical baseline for many finance questions (e.g., long-term growth, volatility).
• It supports many “data management” skills early: even though the dataset is conceptually simple (a daily time series), it still requires correct handling of dates, missing trading days, and the distinction between adjusted vs. unadjusted prices.
• It’s easy to extend later: I can later join additional data (dividends, macro indicators, CPI, risk-free rate) or compare to other tickers (SPY, IVV, or individual stocks) without changing the base workflow.

Planned approach (how I will tackle the problem)

• Acquire data: pull VOO historical data programmatically
• Scope the dataset: start with a clear time window (e.g., last 10 years) and core fields (e.g., Date, Adj.Close).
• Clean + transform: standardize column names, parse dates, sort by time, and use Adj.Close for return calculations.
• Create simple features: compute daily returns and a few rolling metrics (moving average, volatility) with basic sanity checks.
• Document assumptions: note why Adj.Close is used, and any filtering/limitations for transparency and reproducibility.

Anticipated data challenges

• Access stability / scraping risk: Yahoo Finance pages and endpoints can change. To mitigate, I’ll use a package-based retrieval method.
• Trading calendar gaps: weekends and holidays will create gaps in the Date series; features like rolling windows must be computed on trading days only.
• Time period selection bias: results can change materially depending on start/end dates; I’ll justify the chosen window and note limitations.

Conclusion / next steps

After producing a clean, transformed daily dataset for VOO, my next step will be to extend the analysis in later weeks by:

• comparing VOO vs SPY/IVV, or individual stocks.
• adding risk-free rates (to compute excess returns / Sharpe-like measures).