Term
|
Definition
| Developments in technology that can be applied to the financial services industry. |
|
|
Term
|
Definition
| A widely used expression that refers to all potential useful info generated in an economy. This includes data from traditional and non traditional sources. |
|
|
Term
| Non-Traditional Sources of Data |
|
Definition
| This can include data from corporate records, bank accounts, social media, equipment sensors, etc. |
|
|
Term
|
Definition
| The frequency in which data is communicated. High latency = infrequent; Low Latency = Frequent. |
|
|
Term
|
Definition
| The field concerning how we process and visual info from big data. |
|
|
Term
| The Processing of Big Data (5 types) |
|
Definition
1) Capturing of data and making it usable.
2) Curation of data to ensure quality.
3) Storage/archiving of data.
4) Searching of stored data to find needed information.
5) Transferring data from storage to where it is needed. |
|
|
Term
|
Definition
| A form of artificial intelligence designed to mimic the way the human brain works. |
|
|
Term
|
Definition
| A form of artifical intellegence in which the machine improves over time through experience. This is usefull for large sets of data. |
|
|
Term
|
Definition
| A form of ML where data inputs and outputs are labeled then the machine learns to model them. This leaning is then transfered to unknwon sets of data. |
|
|
Term
|
Definition
| Similar to supervised learning expect that data is not labeled for the machine. The machine has to learn how to describe the strucutre of the data set. |
|
|
Term
|
Definition
| A ML technique which used layers of neutral networks to identify patterns (with increasing complexity). Deep learning can be both supervised/unsupervised and include image/speach recongnition. |
|
|
Term
|
Definition
| A situation which occurs when a ML machine learns the input and output data too exactly and identifies false positives and patterns. |
|
|
Term
|
Definition
| A ML situation where the machine fails to identify actual paterns and relationships. |
|
|
Term
|
Definition
| The analysis of unstrctured data in voice or text forms. An example is analyzing the frequency of words within phrases. |
|
|
Term
| Natural Langauge Processing |
|
Definition
| The use of computers and AI to interpret the human language through speech and text recognition. |
|
|
Term
|
Definition
| A database that is shared on a network so that each paticipant has an identical copy. These ledgers much have a valid consensus mechanism to validate new entries to the ledger. |
|
|
Term
|
Definition
| A distributed ledger that records transactions sequentially in the block and links these blocks into a chain. The consensus mechanism is performed by miners who have to solve resource intensive problems. This keeps users from changing the history - further compounded by the fact that they would need to control a large portion of the chain to do so. |
|
|
Term
|
Definition
| A distributed ledger in which all network participants can vial all transactions. These ledgers have no central authority and its history is hard to manipulate - removing the need to trust another user on the ledger. |
|
|
Term
|
Definition
| A distributed ledger which contains users with different levels of access. |
|
|
Term
|
Definition
| An example of a distributed ledger in finance that serves as a medium of exchange and permits engaging in transactions without the need to a financial intermediary. These typically exist on permissionless networks. |
|
|
Term
|
Definition
| A contract that could be programmed to execute base on terms of an agreement between counterparties. |
|
|
Term
|
Definition
| Electronic proof of ownership of physical assets which could be maintained on a distributed ledger. These have the potential to replace paper deeds/ownership documents which are currently filed at government offices. |
|
|
Term
|
Definition
| The statistical measure of the degree in which two variables move together. |
|
|
Term
|
Definition
A collection of points on a graph where each point represents the values of the two variables (X/Y). An upwards sloping plot represents a positive correlation.
Drawbacks of this method include (i) outliers, (ii) false correlations, and (iii) the effects of non-linear relationships. |
|
|
Term
|
Definition
| The hypotesis that the researches would like to rejct. |
|
|
Term
|
Definition
Used to explain the variation in a dependent variable in term sof the variation in a single independent variable. Also known as the line of best fit, it estimates the equation of a line through a scatter plot of the data that best explains the obeserved value Y in terms of the values of X.
Assumptions include:
1) A linear relationship expexts between the D and I variables.
2) THe IV is oncorrelated with the residuals.
3) The expected return of the residual is o.
4) Variance for all residual terms in constant.
5) The residual term is idependently distributed.
6) The residual is normally distributed. |
|
|
Term
| Sum of Squared Errors (SSR) |
|
Definition
| A measure of the difference between the y-values perdicted by the regression and the average Y values. The regression line is the line that minimizes SSE. |
|
|
Term
|
Definition
| A variable that explains the difference between the projected and actual value. |
|
|
Term
|
Definition
| The measure of a securities excess risk adjusted for returns. = |
|
|
Term
| Standard Error Estimates (SEE) |
|
Definition
| MEasures the degree of variabliblity between the actual dependent variables and the dependent varaibles estimed by the regression model. |
|
|
Term
| Coefficient of Determination (R squared) |
|
Definition
| The percentage of the total variation in the dependent variable explained by the independed variable. A CoD of 60% means that the variation of the IV explains 60% of the variation in the DV. |
|
|
Term
|
Definition
| Measures the total variation on the dependent variable. Measures the difference between the actually observed variable and the mean of the dependent variable. |
|
|
Term
|
Definition
Assesses how well a set of independent variables, as a group, explains the variation in the dependent variable.
This is always and one tailed test. |
|
|
Term
| Partial Slope Coefficient |
|
Definition
| Represents the change in the dependent variable for a one unit change in that specific i.v., holding all other i.v.s constant. The slope coefficients in an MLR will change when adding additional variables unless they are not correlated. |
|
|
Term
|
Definition
The smallest level of significance for which the null hypothesis can be rejected.
If the P value is less than the significance level, the null can be rejected.
If the P is greater than the significance level, the null cannot be rejected. |
|
|
Term
|
Definition
| Assess how well a set of independent variables, as a group, explains the variation in the dependent variable. The F test is always a one tailed test. |
|
|
Term
|
Definition
Occurs when the variance of the residuals is not the same across all observations.
Unconditional Heteroskedasticity occurs when the Heteroskedasticity is not related to the level of the independent variables, which means that is doesn't systematically increase or decrease with changes in the values of the I.V.s.
Conditional Heteroskedasticity occurs when the Heteroskedasticity is related to the level of the I.V.s.
When Heteroskedasticity is present, standard errors are usually unreliable. This results in the T Stat being too large and the null will be rejected too often. F Tests will also be impacted. Conditional Heteroskedasticity causes more problems. Coeffects will be unaffected. |
|
|
Term
| Serial Correlation (Autocorrelation) |
|
Definition
A situation in which the residual terms are correlated with one another. This is a common problem with time series data.
PSC exists when a positive regression error in one time period increases the probability of observing another positive regression error for the next time period. NSC is the opposite.
Results in the standard error terms being too small leading to T stats that are too high. |
|
|
Term
|
Definition
Refers to a condition when two or more independent variables, or linear combinations of the variables, in an MR, are highly correlated with each other. This distorts the standard error term and the coefficient standard errors. The slope coefficients are rendered unreliable and the standard errors are too high.
This can be fixed by omitting one of the variables. |
|
|
Term
|
Definition
| A set of observations for a variable over successive periods of time (monthly returns for the past 10 years). The series has a trend if a consistent pattern can be seen by plotting the data on a graph. |
|
|
Term
|
Definition
A model which regresses the dependent variable against one or more lagged I.Vs. The model must be considered covariance stationery to be valid.
1) The expected value of the TS must be constant over time.
2) The time series volatility around its mean does not change over time.
3) The covariance of the time series with leading or lagged values of itself is constant. |
|
|
Term
|
Definition
| Used to compare the accuracy of AR models in forecasting out of sample value. THe model with the lowest out of sample RMSE will have the lowest forecast error and higher perdictive power. |
|
|
Term
| Coefficient Instability/NonStationary |
|
Definition
| Coefficients used in models may change over time due to shifts in economic factors. Shorter time series are more stable becuase of this. However longer time series come with more statistical stability. |
|
|
Term
|
Definition
| A model employed when the variance of the residuals in one period is dependent on the variance of the residuals in a previous period. Used to test for Autoregressive conditional heteroskedasticity. |
|
|
Term
|
Definition
| Compares the average price of a relative basket of goods to the basket of consumption in another country. |
|
|
Term
|
Definition
| States the changes in exchange rates should exactly offset the price effects of any realized inflation differential between the two countries. |
|
|
Term
|
Definition
| The same as Relative PPP except it used expected inflation as assumptions. |
|
|
Term
|
Definition
Measures the exchange of goods, services, investment income, and unilateral transfers. A surplus comes from selling more to other countries than they buy from us.
A deficit results in an increase in the supply of that countries currency as foreign buyers sell the local currency to convert revs into thier own currency. |
|
|
Term
|
Definition
| PPP holds at any point in time and output is held constant. An expansionary (restrictive) monetary policy leads to an increase (decrease) in prices and a decrease IincreaseO in the value of the domestic currency. Thus an x% increase in the money supply leads to a x% increase in price levels and a x% depreciation of the local currency. |
|
|
Term
| Dornbusch Overshooting Model |
|
Definition
| Assumes prices are sticky in the short term and do not immediately relfect changes in monetary policy (in otherwords, PPP does not hold in the ST). The model concludes that exhcnage rates will overshoot the long run PPP value in the ST. |
|
|
Term
| Classical Growth Theory of Economic Growth |
|
Definition
| In the long term, population growth increases whenever there are increases in per capita income above subsistence level due to an increase in capital or tech progress. The high growth is not permanent however as when GDP > subsistence level, a population explosion occurs which leads to diminishing returns to labor which reduces labor prod. and GDP per capita back to the subsistence level. |
|
|
Term
| Neo-Classical Growth Theory |
|
Definition
States the economy is at equilibrium when the output-to-capital ratio is constant. When this is achieved, the labor to capital and output per capita growth at the equilibrium growth rate.
1) Capital deepening impacts the level of output but not the LT growth rate.
2) An economy's growth rate will move towards its steady state regardless of the initial capital to labor ratio or level of tech.
3) Marginal product of capital is constant.
4) An increase in savings will only temp raise economic growth. Countries with higher savings rates will enjoy higher capital to labor ratios and higher productivity.
5) Open marks only provide a temp jump in growth. |
|
|
Term
|
Definition
| A situation where the capital per worker is increasing in the economy. This is also referred to as increase in the capital intensity. |
|
|
Term
|
Definition
Contends that tech growth emerges as a result of investments in both physical and human capital. There is no assumed steady growth rate so that increased investment can permanently increase growth for the entire economy.
1) Open markets provide a perm increase in growth.
2) R&D may have external benefits, and, therefore, should be subsidized by the government. |
|
|
Term
| Absolute Convergence Theory |
|
Definition
| States that less developed economies will achieve equal living standards over time. The NCM assumes that every country has access to the same tech which leads to similar growth rates but not per capita income. |
|
|
Term
|
Definition
| States that convergence in living standards will only occur for countries with the same savings rates, population growth, and production functions. Less developed countries will initially have higher growth rates. |
|
|
Term
|
Definition
| Assumes countries are part of clubs which share similar characteristics. Pooer countries in a club with richer economies can rapidly catch up. |
|
|
Term
| Regulatory Capture Theory |
|
Definition
| States that regardless of the original purpose behind the establishment, the body will at some point become influenced or controlled by members of that community which it regulates. |
|
|
Term
|
Definition
| The monitoring and regulation of the financial institutions in an economy to reduce system-wide risks and protect investors. |
|
|
Term
|
Definition
| Tells us how much sampling variation there is (from the actual population regression) if we were to continuously re-sample the coefficient. Tests reliability of sample coefficient estimates. |
|
|
Term
|
Definition
| form of government failure which occurs when a regulatory agency, created to act in the public interest, instead advances the commercial or political concerns of special interest groups that dominate the industry or sector it is charged with regulating. |
|
|
Term
|
Definition
| A provision that requires regulators to revisit the effectiveness of a new policy to gauge its effectiveness sometime in the future. |
|
|
