Questions tagged [econometrics]
The use of mathematical methods, especially statistical, in order to analyze economic phenomena, understand the economic relations between them, and develop economic theories. A subset of economics.
50
questions with no upvoted or accepted answers
5
votes
0
answers
389
views
Fourth moment of ARCH(2)
I am studying the ARCH(2) process given by
$$X_t = \sqrt{h_t} \varepsilon_t$$
where
$$h_t = \alpha_0 + \alpha_1 X_{t-1} ^2 + \alpha_2 X_{t-2} ^2$$
and $\varepsilon_t$ follows $N(0,1)$. ...
4
votes
0
answers
620
views
Annualization of higher-order co-moments (coskewness and cokurtosis arrays)
I'm developing a dynamic portfolio optimization procedure based on the implementation of the Modified sharpe ratio. The mentioned ratio depends, among other factors, on the skewness and kurtosis of ...
3
votes
0
answers
82
views
The original standard error estimation of Fama and French (2015) paper
I have a question about the estimation method of the original paper of Fama and French (2015) regarding the five factor model and the t statistics. Are they using non-robust standard errors or are ...
3
votes
0
answers
87
views
What is the relationship between the estimated GARCH(1,1) conditional volatility and the true conditional volatility
Suppose that the data has been generated by a GARCH(1,1) model, i.e.
\begin{align}
y_t &= h_t \epsilon_t, \; \epsilon_t \sim N(0,1) \\
h_t &= \alpha_0 + \alpha_1 \epsilon_{t-1}^2 + \...
3
votes
0
answers
732
views
Can a stat arb alpha be a global macro alpha?
In academic literature, "statistical arbitrage" is opposed to (deterministic) arbitrage.[1] In deterministic arbitrage, a sure profit can be obtained from being long some securities and short others. ...
2
votes
0
answers
85
views
Stambaugh inference for Investment Analysis when History Lengths Differ
This pertains to Stambaugh in the JFE (vol. 45, 1997 pp 285-331), and I have a question about Proposition 1 results (page 292). (link)
To set the background, let's take the smallest relevant ...
2
votes
0
answers
54
views
What is selling intensity, loss intensity, and how can I calibrate them?
Thought asking around on a problem I'm currently facing.
I have a hypothetical multi-asset portfolio of equities and bonds, on which I'm trying to measure it's liquidity risk in stressed periods. I've ...
2
votes
0
answers
124
views
Should we include the industry variables when we control for year*industry fixed effects?
In panel data, we control for firms and years fixed effects even we also have some time-variant firm-level regressors.
I am wondering whether it also happens at the industry level. If it is the case, ...
2
votes
1
answer
209
views
Looking for a good introduction to modelling ARCH-type models
I am starting to think about my dissertation topic for my undergraduate degree.
I am interested in comparing volatility of stock indices during COVID-19 to the years leading up to the pandemic. I have ...
2
votes
0
answers
84
views
Applying GRS-test on non-normal residuals with autocorrelation
Is it valid to apply GRS-test (Gibbons, Ross and Shanken 1989) on non-normal and autocorrelated residuals?
I got residuals using 10 test-assets regressed on 3-factor and carhart.
If it is valid, how ...
2
votes
0
answers
47
views
Cointegration between prices and dividends. How do I get the following expression?
Actually, I have two questions:
1.
Let us assume that expected returns are constant. Then, we have the following expression for how the prices should be determined, provided that the operators are ...
2
votes
0
answers
42
views
Tools related to Granger Causality
I would like to know if there are some tools that can measure that one time series is "faster" than the second one. I talk about really similar time series related to high frequency trading (hundreds ...
2
votes
0
answers
127
views
Why is utility concave?
I have read that the utility function is usually concave. I assume this requirement arises in order to meet the diversification effect:$$f(\lambda_1c_1+\lambda_2c_2)\ge \lambda_2 f(c_1)+\lambda_2f(c_2)...
2
votes
0
answers
92
views
Econometrics - Granger Causality
Suppose we have two time series, if one has autocorrelations and the other is non stationary how do we test whether they Granger cause a returns series?
1
vote
0
answers
44
views
Testing one asset pricing model against another a la Cochrane: why this works
I am reading section section 14.6 of John Cochrane's lectures notes for the course Business 35150 Advanced Investments. On p. 239-240, he discusses testing one asset pricing model against another. I ...
1
vote
0
answers
16
views
If investors face different tax rates, how can an asset pricing model be built so that it satisfies the incentive constraints of both investors?
The CAPM and other models have been expanded to include the impact of corporate/personal taxes. However, what if these tax rates differ for an investor pool holding the same equity stake (which by ...
1
vote
0
answers
188
views
How to build Fama-French model factors SMB and HML to compare sustainable index to conventional benchmark?
My goal is to analyze and compare the performance between socially responsible indices and conventional ones. I am comparing for each region (Europe, UK, World, US) a sustainable index to a ...
1
vote
0
answers
31
views
Cross-checking Treasury's Major Foreign Holders Report
I was looking for bad things waiting to happen on the Ides of March, and the next Major Foreign Holders of Treasury Securities report came up as a candidate. It is due on March 15th, 2021. The report ...
1
vote
0
answers
44
views
Examining individual portfolio allocation changes over time
I am currently working with a pretty large panel dataset containing the investment holdings of many individuals over time (i.e., for each individual I know the positions per stock over time). I was ...
1
vote
0
answers
70
views
Can you approximate stochastic volatility processes using GARCH processes?
Let me specific. Suppose that you have the following process:
\begin{align}
z_t &= \sigma_t \epsilon_t \\
\sigma_t &= \sigma \exp \left( \frac{v_t}{2} \right)
\end{align}
where $v_t$...
1
vote
0
answers
219
views
CAPM and the Fama-MacBeth (1973)
I need to conduct the Fama-MacBeth (FM) procedure for my thesis to test the ability of the six-factor model to predict future expected returns. In univariate regressions of expected excess returns on ...
1
vote
0
answers
46
views
Correlation coefficient without cash flows?
I'm an intern at a company and one of our tasks is to calculate the the probability of default of both participants of a Swap(a Client and a Bank), for which we first need the correlation coefficient ...
1
vote
0
answers
1k
views
How to normalize stock exchange indexes
I am doing an academic research in behavioral finance and I need to calculate my abnormal return based on the normalized returns of the stock exchange index being the S&P 500. In other words, I ...
1
vote
0
answers
68
views
Log transformation of TS-stationary time series
I usually see the $log$ transformation of prices: $$p_{new}\left(t\right) = ln\left(\frac{p_t}{p_{t-1}}\right), t \in [2...N]$$.
Let's our series be a trend stationary time series like: $$p\left(t\...
1
vote
0
answers
91
views
Statistical distribution of MACD
I was (unsuccessfully) trying to find results on what the distribution of the MACD values for a stationary time series with IID returns would be. Are there any such results or any that go in a similar ...
1
vote
0
answers
36
views
Using CFNAI index for identifying sample periods
I'm doing my Thesis on Asset pricing models and I would like to find out the effects of business cycles on the performance of asset pricing models for industry portfolios.
My initial idea was to ...
1
vote
0
answers
112
views
Fractional cointegration in R
I'm looking for a package (or some code that anyone has written) that will help me to estimate a VECM for fractionally cointegrated series. I.e. like the ca.jo ...
1
vote
0
answers
130
views
Evaluating Fama French 3 factor model Using Fama Macbeth
Hi Can someone please explain me how the cross sectional calculation can be done.
For an example, I'm having a vector like this.
Vector 1: This is the vector where all the excess returns for n ...
1
vote
0
answers
81
views
Why does an increase in eviction court filings result in an increase in REIT returns?
I'm a data mining developer working for a company that wholesales eviction record data on a national level. I was recently assigned a project to build a program to mine all county courts in Oklahoma ...
1
vote
0
answers
149
views
What's the slowest frequency over which bid-ask bounce effect are observed?
I am using minute-by-minute stock prices series constructed on transaction data. The stocks are among the most highly liquid.
I observe that the price series contain negative autocorrelation. I ...
1
vote
0
answers
412
views
Comparing two models using Wald Test
I would like to use a Wald test to compare two models.
To give a basic example, let:
$Y_{t}=\alpha+{\phi_1x}_{t-1}+{\beta}_{1}x_{t-1}+{\beta}_{2}x_{t-1}+{\beta}_{3}x_{t-1}+\epsilon_t (A)$
$Y_{t}=\...
1
vote
0
answers
35
views
Machine Learning Munging - order of transforms? + adding in econometric tests?
I have a list of possible transforms, and I've read some confusing/contradictory stuff about the preferred order in which these operations are performed. Maybe 1) the order is sometimes amorphous, ...
1
vote
0
answers
238
views
How to decide if the ARCH coefficient is necessary in the GJR-GARCH model?
I did some analysis for CAC 40, the French market benchmark, for the period 2005-2014, and I tried to fit the data with a GJR(1,1) model in MATLAB.
Then some warning showed
Lower bound ...
1
vote
0
answers
180
views
MLE estimate of normal distribution
Probably a naive question. I am quoting this from Greene's econometrics book:
"The occasional statement that the properties of the MLE are only optimal in large samples is not true, however. It can ...
1
vote
0
answers
37
views
Standard errors clustered along the time dimension in pooled panel logit model
I'm trying to estimate a logit model on pooled panel data set (unit of observation is firm-year). My dependant variable is default indicator and I have several macro variables as independant variables....
1
vote
0
answers
89
views
How to value a portfolio of non-mature consumer loans?
I'm looking for the best way to value a portfolio of consumer loans that have NOT reached maturity and for which I do observe the payment/default history to date?
I'm working with a large database of ...
1
vote
0
answers
710
views
Autoregressive distributed lag models ADL(p,q) howto in preferably matlab (stata/R/python/C# etc)
Could anyone provide me the details of how to determine the lag order of the distributed lags for an ADL(p,q) model in Matlab or another statistical package (and very much preferably in combination ...
1
vote
0
answers
139
views
Max Likelihood via Marquardt Optimisation
I asked a related question here:
How to apply Levenberg Marquardt to Max Likelihood Estimation
I tried the approach suggested it works for some of the parameters but not the variances.
I spoke to ...
0
votes
0
answers
12
views
Error (singularity) in the GRS test applied on portfolios that were used for constructing the Fama-French factors
In the context of the Fama-French 3-factor model, we have six portfolios used for creating the SMB and HML factors: SL, SM, SH, BL, BM, BH. (The notation is: S~small, B~big, L~low, M~medium, H~high). ...
0
votes
0
answers
87
views
Through-the-cycle rating transition matrix
Suppose we know the observed transition matrix for annual migrations between credit ratings, $T_{ij,t}$, for $N$ years. How is the through-the-cycle (TTC) transition matrix defined?
Sometimes the ...
0
votes
0
answers
36
views
Shanken's correction for Fama-MacBeth (1973) generalization of the CAPM
Fama & MacBeth (1973) tested the CAPM against an alternative that the dependence between the expected excess return $E(r_{i,t}^∗)$ and the relative systematic risk $\beta_𝑖$ is nonlinear (namely, ...
0
votes
0
answers
40
views
How does truncating data deal with long right tails of data? Why is a long right tail bad?
For reference, my coworker graphed the unemployment rate with an HP Filter on. He told me he truncated the data to 95% to deal with this issue but I'm not 100% sure what this means and why its ...
0
votes
0
answers
24
views
Global Country Index for Insurance
I am trying to create a global country index for insurance. So this would be insurance by country. Anybody who is an expert in econometrics can give me some guidance on how to do this? How would I go ...
0
votes
0
answers
69
views
What are the example of "repeated cross-section" and "two cross-sectional dimensions"?
Borusyak, 2021 has a sentence
In Section 5 we consider extensions to repeated cross-sections, data
defined by two cross-sectional dimensions (e.g. regions and age
groups), triple-differences designs, ...
0
votes
0
answers
41
views
Why we need to control for import and exchange rate change when examining asset growth?
Dasgupta , 2019 examines the impact of antitrust laws on asset growth, total net external financing, debt-to-equity ratio. In his regression, I saw that he controls for imports as a percentage of GDP, ...
0
votes
0
answers
55
views
What is the Id in the ARIMA model in Notes on financial risk of Privault?
I hope this is the right place to ask this question. I am studying the time series from Privault's Notes on Financial Risks. In the ARIMA model part I can't understand what is "I_d", it is ...
0
votes
3
answers
446
views
maximum likelihood pdf
I am looking at the topic maximum likelihood, and I cannot understand why we set the pdf of $y_{t}$ equal to 1. It is with regards to a OLS example.
The information i got is this:
Model: $y_{t}=\...
0
votes
0
answers
75
views
Trading Signals with Different Lags
I have a momentum signal that gives best predictive power at 3 months and a valuation signal that gives best predictive power at one year. If I combine for a 3 month horizon by "interpolating" the ...
0
votes
0
answers
68
views
Good introduction to estimating stochastic diffusion processes?
So, in an advanced Econometrics course, the current topic relates to estimating transition densities and diffusion processes by MLE, such as this R package doc describes, for ex., and I have to admit ...
0
votes
0
answers
57
views
Multi-Variate linear modeling: how to calculate mathematically vs brute force genetic optimization
I have a hand full of daily economic data. I am currently using a brute force approach. Genetic optimization is only used when k is very large. This method is beautiful to me, but isn't valuable ...