Quantitative Finance Stack Exchange is a question and answer site for finance professionals and academics. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I am trying to understand how changes in economic indicators like Unemployment Rate, Inflation Rate, and Consumer Sentiment affect the portfolio values.

For that I want to measure the correlation between a given economic indicator and S&P SPDRs. I am using scipy stats package and Pearson correlation for that.

I see unintuitive correlations like

  1. corr(fin SPDR, Consumer Sentiment) > 0.75 , corr(consumer staples SPDR, Consumer Sentiment) = -0.5 [ p-value << 0.01 ]

  2. corr(housing starts, tech SPDR) = -0.37 , corr(Housing Starts, consumer staples SPDR) = -0.57

I would think that when the consumer sentiment is high, the consumer staples should also reflect this positivity. But I see negative correlation.

I am not sure if the problem is due to time lag between the economic indicator turning positive and its positive benefits experienced by the companies in a given sector.

Correlations were conducted on SPDR prices and various economic indicators over last 10 years of time.

Could anyone who has done analysis on correlations between economic indicators and market prices help me make sense of these results?

share|improve this question
Economic indicators are either forward looking, coincident, or reflect historical data, thus correlations between an equity index and such indicators are a huge function of how you lag the indicators. By the way has it occurred to you that the lag itself is dynamic and changes unpredictably, meaning, the lag that produces the highest positive or negative correlation with a major equity index? Otherwise everyone would trade off such indicators. I can show you countless examples where higher NFPs went along with lower subsequent index returns. Call it "reality"... – Matt Wolf Jul 12 '13 at 3:59
I was thinking that the time lag may may vary based on the stage of the economic cycle. I was wondering if the time lag between indexes and economic indicators could be learnt by Machine Learning or some sort of statistical ways rather than hard coding them. BTW, is there any primer on which indicators are forward looking vs lagging. – Shyam Maddali Jul 13 '13 at 18:52
Just for reference, Wiki has nice demarcation of some the well know indicators en.wikipedia.org/wiki/Economic_indicator – Shyam Maddali Jul 14 '13 at 6:32
Are you using real-time data? – Joshua Ulrich Jul 29 '13 at 22:05
I am using data from Fred, which is updated when the vintages are released. – Shyam Maddali Oct 15 '13 at 17:20

Beside the lag issue, I do not believe that the negative correlation between Consumer Staples and sentiment is counter-intuitive. The S&P SPDR XLP ETF (Consumer Staples) offers a broad exposure to defensive mega-cap consumer names. Spending on consumer staples is usually characterized by an inelastic demand. Whether the economic climate is strong or week, people still need to purchase tooth-paste, milk or dish-washing liquid.

As consumer sentiment decreases in light of chilly economic winds that are likely to affect consumer discretionary spending, investors would tend to seek a more stable and defensive portfolio tilt, hence the increasing interest in the Consumer Staples ETF.

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.