ARCH, GARCH and ARIMA modelling Flowchart (Applied Econometrics - Financial)

 Following represents the ARCH, GARCH and ARIMA modelling flowchart.

 We must note one thing that if there is any existence of a serial correlation, we must opt for GARCH model.

Bonus: If you are using ARCH and GARCH through R, then these are the useful packages:

library(FinTS) for ARCH

library(rugarch) for GARCH

This is just a brief about ARCH and GARCH. Will discuss about this with an example, later (with reference to R, Eviews and Gretl).

Thank you

To be contd...

Aditya Pokhrel, Asst Director - NRB

MBA, MA Economics, MPA (rng)

What's Nuisance Variables ? (Applied Econometrics)

   NUISANCE VRIABLES

Generally in the experimental design we tend to consider only about the dependent and independent variables. We generally tend to neglect the concept of the nuisance variables. The most crucial part of the experimental design is the nuisance variable.

Say that, generally it is seen that the dependent variable readily depends upon on an indefinable property of the subjects, say age of any individual. So, this property would become the nuisance variable. We can set an assumption by designing the experiment that whether how much the nuisance variables affects the dependent variable.

We can also call that in the theory of the stochastic processes, say in the probability theory of the statistics, a nuisance variable is a random variable that is a fundamental to the probabilistic model, but that is of no particular interest in itself or is no longer of the interest.

One of its usage come from the Chapman Kolmogorov equation. Say, a model for a stochastic process which may be defined conceptually using the intermediate variables that are not observed in the practice. If there is the problem to derive the theoretical properties, such as mean, variance and co variances of the quantities which would be observed, then those intermediate variables are nuisance variables.

Basically, in the block experiments, where the terms in the particular model representing the block means, those are often called as "factors", are of no interest. Several approaches to the analysis of such experiments particularly where the  experimental design is the subject to the randomization, we must treat these factors as the random variables.

Furthermore, the nuisance variable is used simply to designate those variables that are marginalized over when finding a marginal distribution. Sometimes, this term is also used in the Bayesian analysis as an alternative to the nuisance parameter, provided that the Bayesian statistics allows parameters to be treated as having the probability distributions.

Hope this adds some knowledge in the experimental design of your research. 

Thank You

Aditya

What is DCC GARCH ? Basic Concepts - Applied Financial Econometrics

WHAT IS  DCC GARCH ?

Shadow Exchange Rate (How its calculated) - Economics of C/B Analysis

SHADOW EXCHANGE RATE (basic concepts useful for Economic analysis, Competitive exams and M. Phil Economics course)

The Shadow Exchange Rate is a numeraire which is used to calculate the foreign currency into the domestic currency. The use of this exchange rate is practiced because the market exchange rate may not reflect the economic value in the units of the domestic currency of a unit of the foreign exchange.

Say, if there is any distortions in the foreign exchange market and the official exchange rate doesn't reflect the true opportunity cost of the foreign exchange.

The various trade policies such as subsidies, export subsidies, export taxes, etc distort not only the individual prices of the goods, but also the prices of the foreign exchange foe the economy as a whole.

Say, if there are any serious distortions the border prices need to be converted into the domestic currency equivalent using a shadow exchange rate but not the official or the market exchange rate.

Lets understand, the need to determine the foreign exchange premium arises because in many of the countries, as a result of the national trade policies (such as tariff and subsidies). people pay premium(extra or less than the actual price)on the traded goods whether its imported or exports over what they pay for the non traded goods.

So, the case is this premium is not adequately reflected when the prices of the traded goods are converted to the domestic currency equivalent to the official exchange rate. The premium represents the additional amounts paid by the users of the traded goods. 

It's evident to all the all the costs and benefits in the economic analysis are valued on the basis of the opportunity costs or the willingness to pay. it is the relation between the willingness to pay for the traded goods as opposed to the non traded goods which establishes their relative value.

Thus, the mispriced traded goods are converted to the price of the non traded goods by the use of shadow exchange rate, likewise, lets say shadow exchange rate is a numeraire used for the accounting real prices of goods/services.

NUMERICAL DOMAINS

SER = OER * (1 + F * PREMIUM)

SCF = 1 / (1 + F * PREMIUM)

Now, ADB practice [(Mainali, 2021), TU] in estimating SCF\

SCF = [Imports (cif) + Exports (fob)] / [(Imports +Imports taxes- subsidies) + (Exports - Exports Taxes                                                                                                                                                   +Subsidies)]

which becomes, SCF = 1 + Net trade Taxes / Total Trade

Thank You

P.S Comments are lauded.

Aditya Raz Pokhrel

Asst. Director - Nepal Rastra Bank

MBA, MA Economics, MPA(rng)

Wanna read a Forest Plot ? (Meta Analysis contd...)Applied Econometrics

■ What is a Forest Plot?

Simply, A forest plot is a graph that compares information many individual, clinical or scientific studies studying the same thing.

If you guys are well acquainted with the prior knowledge of Meta Analysis (mine earlier blogs) then lets state:

Say, there are studies such as Ram et al., Sita et al., Siva et al., Abdul et al., Hanuman etal., etc. So in the plot we will also have a Summary measure of all these along with the odds ratio (odds ratio will be discussed later in the Qualitative analysis).

Now you need to break the ice. Here you go,

The Realtive Risk Ratio say, 95% C.I visually displays the study results. The right column of the plot displays the same results expressed numerically.

The horizontal lines in the figure denotes the length of the Confidence Interval. The longer the line, the wider the C.I and as such the less reliable the results are.

If all the horizontal lines crossed the vertical line, it shows that all the studies were in agreement and if the horizontal line doesn't cross the vertical it's an indication that were statistically significant differences betweem the studies.

The boxes on the intervals represent the effect estimates from the single studies. Usually, the bigger the box, the larger the sample size as well as more meaningful story.

Now, an outline of a diamond at the base of the forest plot represents a weighted average for all the studies but may also be in Odds Ratio. The lateral tips of a diamond represnt the Confidence Interval.

If the diamond touches the vertical line then the overall meta analysis results is not statistically significant. If the diamond is left of the (dotted) line, then there is a lapse of two episodes of interest in the treatment group (treatment group discussed in previous blogs - in RCT).

Similarly, if the diamond is to the right, there are more episodes of the outcome in the treatment group.

** Summary**

a) Names to the left: 1st author of the rinary studies

b) Solid Sqaures: RR or OR of the individual studies.

c) Solid Sqaure Size: Weight of the Study

d) Horizontal lines: 95% of C.I

e) Vertical lines: Line of no effect

f) Diamond: Overall treatment effect

g) Tips of Diamond: 95% of C.I

Thank you

P.S Comments and Suggestions are highly lauded.

Aditya Raz Pokhrel

Assistant Director,NRB

MBA, MA Economics, MPA(rng)

Useful MCQ's for banking (Economics of Banking)

 ● MCQ's

1. The widest possible view of money is:

Ans: The Central Bank Approach (C + DD + TD + NBFI - CUA)

2. The function of money is not:

Ans: Stabilization of Price level.

3. What is a Fiat Money ?

Ans: Legal Money

4. BOE is:

Ans: Quasi Money/Near Money

5. When the value of the commodity = Value of the money its called:

Ans: Full boided Money

6. Keyensia concept of the money focuses on:

Ans: Store of the value.

7.  Father of modern quantity theory of money:

Ans: M. Friedman.

8. What is Pigou's cash balance equation ?

Ans: M = KR / P

9. Real Balance Effect is also given by:

Ans: A.C Pigou

10. Degree of the elasticity in respect to the speculative demand for money under liquidity trap is:

Ans: Infinite

11. Deflation benefits mostly:

Ans: Pensioners

12. Is "Security holdings" liability of a commercial bank ?

Ans: No

13. Which is the country that introduced the concept of CRR ?

Ans: USA

14. The deposit creation formula is:

Ans: 1 / CRR

15. What is TOT (Terms of Trade)

Ans: Ratio of, Index of Export Prices to Index of Import prices.

16. In BOP, what is the "Foreign Travel"

Ans: Invisible

17. Nepal's monetray policy is made on the basis of which International system?

Ans: Exchange Rate Anchor

18. What is the elasticity of demand for foreign exchange for financing capital outflow?

Ans: Zero

19. If the elasticity of foreign demand for the country's exports is unity, the supply curve of the foreign excahnge will be:

Ans: Vertical

20. Did "Mercantalists" favor free Trade ? 

Ans: No

Note: NBFI: Non Banking Financial Institutio.

           CUA: Credit from Unrecognised Agents

Plz share this...

Thank you

To be contd...

Aditya Pokhrel

Assistant Director, NRB

MBA,MA Economics,MPA

What's Vector Auto Regression (VAR)

 o VAR

Generally, VAR is considered as an extension of a single equation (ARDL) model which we will discuss later (in upcoming blogs).

VAR can be considered as the hybrid of the ARDL and the structured model (simultaneous equation models) and VAR is used profusely in Econometrics.

Its known to all that most of the econometric model are structural in nature (relationship between variable are determined by the economic theory).

There are many conditions that in which the economic theory won't be sufficient to determine the right model, i.e. the specification of the model should be based on the Econometric approach too. Now, there's a confusion about the correctness of the theory.

Say, the data, rather than the Econometricians specify the dynamic structure of the data. Let, the data determine what is the correct model. So, with this spirit, the VAR model was developed.

We will discuss clearly about the Simultaneous Equation Models (in upcoming blogs), now in the Simultaneous Equation Models, the classification of the endogenous and exogenous variables was arbitrary and identification is achieving by imposing "0" restrictions on the coefficients of the variables on the equation. These two decisions were subjective and this was criticized by "Sims".

According to Sims,. if there's two Simultaneity  between the variables they should be treated equally. There should not be distinction between endogenous and exogenous i.e. all the variables should be treated as endogenous and this spirit led "Sims" to develop a VAR  model.

In VAR thus, there's no distinction between the endogenous and exogenous variables (if included the model will will be biased).

A variable which is exogenous in one model is endogenous in the other:

In VAR model we have to specify two things (2 dimensions):

i) We have to select the variables supposed to be interacting with each other (m).

ii) Determine the largest number of the lags (to ensure that the entre relationships between these variables are captured into the model (p).

Say, that we consider the two variables, money supply and interest rates (Ms and r).

Now, in the VAR model Ms is related not only on the past values of the Ms but also on the past values of r. Similar case is with the "r" as well.

Now, we specify the VAR with 2 variables as :

Mst = alpha + Sum(j to k; j=1)beta j * Mt-j + Sum(j to k; j=1) gamma j * R t-j + U1t _________ eq (a)

Rt = alphaprime + Sum(j to k; j=1) theta j * Mt-j + Sum(j to k; j=1) lamda j * R t-j +U2t______ eq (b)

These two system of the equations are used in the context of the Granger Causality (will discuss later in coming blogs).

U1t and U2t are assumed to be uncorrelated and U1t and U2t are the impulses/innovations/shocks.

TO BE CONTD...

Aditya Pokhrel

MBA, MA Economics, MPA.