|
|
a fortiori
Latin for "even stronger". Can be used to compare two theorems or proofs. Could be interpreted to mean "in the same way."
|
A trait
is a relatively permanent disposition of an individual. Traits are inferred
from behaviour and are considered to be continuous dimensions on which individual differences
can be arranged quantitatively (e.g. extraversion, introversion).
Traits are to be distinguished from states.
|
A-D equilibrium
abbreviation for Arrow-Debreu equilibrium.
|
AAEA
American Agricultural Economics Association. See their web site at http://www.aaea.org.
|
Ability to pay principle
A notion claiming that those who can afford to pay the tax should bear a greater weight of paying the tax.
|
abnormal returns
Used in the context of stock returns; means the return to a portfolio in excess of the return to a market portfolio. Contrast excess returns which means something else. Note that abnormal returns can be negative. Example: Suppose average market return to a stock was 10% for some calendar year, meaning stocks overall were 10% higher at the end of the year than at the beginning, and suppose that stock S had risen 12% in that period. Then stock S's abnormal return was 2%.
|
absolute risk aversion
An attribute of a utility function. See Arrow-Pratt measure.
|
absorptive capacity
A limit to the rate or quantity of scientific or technological information that a firm can absorb. If such limits exist they provide one explanation for firms to develop internal R&D capacities. R&D departments can not only conduct development along lines they are already familiar with, but they have formal training and external professional connections that make it possible for them to evaluate and incorporate externally generated technical knowledge into the firm better than others in the firm can. In other words a partial explanation for R&D investments by firms is to work around the absorptive capacity constraint.
This term comes from Cohen and Levinthal (1990).
|
abstracting from
a phrase that generally means "leaving out". A model abstracts from some elements of the real world in its demonstration of some specific force.
|
Abstractness
The information contained in a
prototype is an abstraction across several instances of the concept.
|
accelerator principle
That it is the growth of output that induces continuing net investment. That is, net investment is a function of the change in output not its level.
|
acceptance region
Occurs in the context of hypothesis testing. Let T be a test statistic. Possible values of T can be divided into two regions, the acceptance region and the rejection region. If the value of T comes out to be in the acceptance region, the null hypothesis being tested is not rejected. If T falls in the rejection region, the null hypothesis is rejected.
The terms 'acceptance region' and 'rejection region' may also refer to the subsets of the sample space that would produce statistics T in the acceptance region or rejection region as defined above.
|
Accessibility and availability
Accessibility ?
Construct accessibility is the readiness with which a stored construct is utilized
in information processing; that is, construct accessibility is concerned with
stored constructs, their utilization in information processing, and the likelihood
of such utilization.
|
Accounting costs
The explicit costs of production; these include monetary payments to cover the costs of fixed or variable inputs (i.e., fixed costs and variable costs). Some examples include utilities, rent, wages of labor, property taxes, the cost of raw materials, etc. Unlike economic costs, they do not include implicit (opportunity) costs.
|
Accounting Profit
The profit made from the total revenue received from the sale of the goods less the (explicit) costs of producing these goods. It is calculated as Total Revenue â?? Explicit Costs.
|
ACIR
Advisory Council on Intergovernmental Relations, in the U.S.
|
active measures
In the context of combating unemployment: policies designed to improve the access of the unemployed to the labor market and jobs, job-related skills, and the functioning of the labor market. Contrast passive measures.
|
adapted
The stochastic process {Xt} and information sets {Yt} are adapted if {Xt} is a martingale difference sequence with respect to {Yt}.
|
AEA
American Economics Association
|
AER
An abbreviation for the American Economic Review.
|
affiliated
From Milgrom and Weber (Econometrica, 1982, page 1096): Bidders' valuations of a good being auctioned are affiliated if, roughly: "a high value of one bidder's estimate makes high values of the others' estimates more likely."
There may well be good reasons not to use the word correlated in place of affiliated. This editor is advised that there is some mathematical difference.
|
affine
adjective, describing a function with a constant slope. Distinguished from linear which sometimes is meant to imply that the function has no constant term; that it is zero when the independent variables are zero. An affine function may have a nonzero value when the independent variables are zero. Examples: y = 2x is linear in x, whereas y = 2x + 7 is an affine function of x. And y = 2x + z2 is affine in x but not in z.
|
affine pricing
A pricing schedule where there is a fixed cost or benefit to the consumer for buying more than zero, and a constant per-unit cost per unit beyond that. Formally, the mapping from quantity purchased to total price is an affine function of quantity. Using, mostly, Tirole's notation, let q be the quantity in units purchased, T(q) be the total price paid, p be a constant price per unit, and k be the fixed cost, an example of an affine price schedule is T(q)=k+pq. For alternative ways of pricing see linear pricing schedule and nonlinear pricing.
|
AFQT
Armed Forces Qualifications(?) Test -- a test given to new recruits in the U.S. armed forces. Results from this test are used in regressions of labor market outcomes on possible causes of those outcomes, to control for other causes.
|
AGI
An abbreviation for Adjusted Gross Income, a line item which appears on the U.S. taxpayer's tax return and is sometimes used as a measure of income which is consistent across taxpayers. AGI does not include any accounting for deductions from income that reduce the tax due, e.g. for family size.
|
agricultural economics
"Agricultural Economics is an applied social science that deals with how producers, consumers, and societies use scarce resources in the production, processing, marketing, and consumption of food and fiber products." (from Penson, Capps, and Rosson (1996), as cited by Hallam 1998).
|
AIC
abbreviation for Akaike's Information Criterion
|
AJS
An abbreviation for the American Journal of Sociology.
|
Akaike's Information Criterion
A criterion for selecting among nested econometric models. The AIC is a number associated with each model: AIC=ln (sm2) + 2m/T where m is the number of parameters in the model, and sm2 is (in an AR(m) example) the estimated residual variance: sm2 = (sum of squared residuals for model m)/T. That is, the average squared residual for model m. The criterion may be minimized over choices of m to form a tradeoff between the fit of the model (which lowers the sum of squared residuals) and the model's complexity, which is measured by m. Thus an AR(m) model versus an AR(m+1) can be compared by this criterion for a given batch of data. An equivalent formulation is this one: AIC=T ln(RSS) + 2K where K is the number of regressors, T the number of obserations, and RSS the residual sum of squares; minimize over K to pick K.
|
alienation
A Marxist term. Alienation is the subjugation of people by the artificial creations of people 'which have assumed the guise of independent things.' Because products are thought of as commodities with money prices, the social process of trade and exchange becomes driven by forces operating independently of human will like natural laws.
|
Allais paradox
The Allais paradox is the most prominent example for behavioral inconsistencies related
to the von Neumann Morgenstern axiomatic model of choice under
uncertainty.
The Allais paradox shows that the significant majority of real decision makers
orders uncertain prospects in a way that is inconsistent with the postulate that
choices are independent of irrelevant alternatives. Basically, it is this postulate
that allows to represent preferences over uncertain prospects as a linear functional
of the utilities of the basic outcomes, viz. as the expectation of these utilities.
Consider the following choice situation (A) among two lotteries:
? lottery L1 promises a sure win of $30,
? lottery L2 is a 80% chance to win $45 (and zero in 20% of the cases).
Typically, L1 is strictly preferred to L2 (such observed behavior is called a
revealed preference).
Now, consider another choice situation (B):
? lottery K1 promises a 25% chance of winning $30,
? lottery K2 is a 20% chance to win $45.
Here, the typical choice is K2 over K1 although situation B differs
from situation A only in that in each lottery, three quarters of the original
probability of winning a positive amount are cancelled.
Assume the typical subject decides among lotteries in the following way.
To each of the basic outcomes, a number is assigned that indicates its attractiveness;
say u(0)=0, u(45)=1, and u(30)=v (0 0.8;
while the revealed preference of K2 over K1 in situation B shows that
1/4 v < 1/5, or v < 0.8.
In cognitive psychology, this inconsistency is explained as a
certainty effect. In situation A, L2 differs from
L1 by a winning probability that is 20% lower, just as
lottery K2 differs from K1 in situation B (where 4/5 x 25 = 20).
Empirically, it seems that cancelling a fixed proportion of winning probability has a higher
cognitive impact in a lottery where winning was extremely likely than in
a lottery where winning was "a rather unlikely event, anyway."
By accounting for a misperception of probabilities according to a non-linear weighting
function (of the utilities of the elementary outcomes), expected utility can be rescued also
in view of the Allais paradox (see prospect theory).
The Allais paradox, devised in the 1950's, was the first piece in a
series of systematic evidence challenging the traditional concept of von Neumann Morgenstern
expected utility, leading to the development of generalized models of ("boundedly rational")
choice behavior under uncertainty.
|
Allocation
The accepted purview of economics is the allocation of scarce resources.
Allocation comprises production and exchange, reflecting a fundamental division
between processes that transform commodities (i.e., production) and those
that transfer control (i.e., exchange). In general, optimal allocation ensures
that scarce resources are driven to their best use.
For both production and consumption, exchange is essential to the efficient use
of resources. It allows decentralization and specialization in production;
as to consumption, agents with diverse endowments or preferences
(tastes) need exchange to obtain maximal benefits, given their resources. If the preferences of
two agents differ (formally, if agents have different rates of substitution among
the commodities concerned), then there exists a trade benefitting both. Such trades
of private goods take place on markets.
The advantages of barter extend widely, e.g. to trade among nations and among
legislators ("vote trading"), but it suffices here to emphasize markets with
enforceable contracts for trading private property unaffected by
externalities.
In such markets, voluntary exchange involves trading bundles of commodities
or obligations to the mutual advantage of all parties to the transaction.
|
Allpay auction
Simultaneous bidding game where the bidder that has submitted the highest
bid is awarded the object, and all bidders pay their own bids. A subvariant is
the second price all pay auction, also war of attrition, where each
bidder pays his own bid but the winner only pays the second highest bid.
For example, campaign spending and political lobbying processes are second-price
all pay auctions; liekwise, timing decisions on the private provision of public goods
have the structure of second price all pay auctions.
|
almost surely
With probability one. In particular, the statement that a series {Wn} limits to W as n goes to infinity, means that Pr{Wn->W}=1.
|
alternative hypothesis
"The hypothesis that the restriction or set of restrictions to be tested does NOT hold." Often denoted H1. Synonym for 'maintained hypothesis.'
|
Americanist
A member of a certain subfield of political science.
|
AMEX
American Stock Exchange, which is in New York City
|
Amos
A statistical data analysis program, discussed at http://www.smallwaters.com/amos.
|
analytic
Often means 'algebraic', as opposed to 'numeric'. E.g., in the context of taking a derivative, which could sometimes be calculated numerically on a computer, but is usually done analytically by finding an algebraic expression for the derivative.
|
Anchoring and adjustment
People who have to make judgements under uncertainty use this heuristic by starting with a
certain reference point (anchor) and then adjust it insufficiently to reach a final
conclusion. Example: If you have to judge another personīs productivity, the anchor for
your final (adjusted) judgement may be your own level of productivity. Depending on your
own level of productivity you might therefore underestimate or overestimate the productivity
of this person.
|
annihilator operator
Denoted []+ with a lag operator polynomial in the brackets. Has the effect of removing the terms with an L to a negative power; that is, future values in the expression. Their expected value is assumed to be zero by whoever applies the operator.
|
Annuity formula
If annuity payments over time are (0,P,P,...P) for n periods, and the constant interest rate r>0, then the net present value to the recipient of the annuity can be calculated this way: NPV(A) = (1-(1+r)-n)P/r
|
ANOVA
Stands for analysis-of-variance, a statistical model meant to analyze data. Generally the variables in an ANOVA analysis are categorical, not continuous. The term main effect is used in the ANOVA context. The main effect of x seems to mean the result of an F test to see if the different categories of x have any detectable effect on the dependent variable on average. ANOVA is used often in sociology, but rarely in economics as far as this editor can tell. The terms ANCOVA and ANOCOVA mean analysis-of-covariance. When I understand ANCOVA and main effect better, I'll make separate entries for them. From Kennedy, 3rd edition, pp226-227: 'Analysis of variance is a statistical technique designed to determine whether or not a particular classification of the data is meaningful. The total variation of the dependent variable (the sum of squared differences between each observation and the overall mean) can be expressed as the sum of the variation between classes (the sum of the squared differences between the mean of each class and the overall mean, each times the number of observations in that class) and the variation within each class (the sum of the squared difference between each observation and its class mean). This decomposition is used to structure an F test to test the hypothesis that the between-class variation is large relative to the within-class variation, which implies that the classification is meaningful, i.e., that there is a significant variation in the dependent variable between classes. If dummy variables are used the capture these classifications and a regression is run, the dummy variable coefficients turn out to be the class means, the between-class variation is the regression's 'explained' variation, the within-class variation is the regression's 'unexplained' variation, and the analysis of variance F test is equivalent to testing whether or not the dummy variable coefficients are significantly different from one another. The main advantage of the dummy variable regression is that it provides estimates of he magnitudes of class variation influences on the dependent variables (as well as testing whether or not the classification is meaningful). 'Analysis of covariance is an extension of analysis of variance to handle cases in which there are some uncontrolled variables that could not be standardized between classes. These cases can be analyzed by using dummy variables to capture the classifications and regressing the dependent variable on these dummies and the uncontrollable variables. The analysis of covariance F tests are equivalent to testing whether the coefficient of the dummies are significantly different from one another. These tests can be interpreted in terms of changes in the residual sums of squares caused by adding the dummy variables. Johnston (1972, pp 192-207) has a good discussion. In light of the above, it can be concluded that anyone comfortable with regression analysis and dummy variables can eschew analysis of variance and covariance techniques.' [Except that one needs to understand the academic work out there, not just write one's own. -ed.]
|
APT
Arbitrage Pricing Theory; from Stephen Ross, 1976-78. Quoting Sargent, "Ross posited a particular statistical process for asset returns, then derived the restrictions on the process that are implied by the hypothesis that there exist no arbitrage possibilities."
The APT includes multiple risk factors, unlike the CAPM.
|
AR
Stands for "autoregressive." Describes a stochastic process (denote here, et) that can be described by a weighted sum of its previous values and a white noise error. An AR(1) process is a first-order one, meaning that only the immediately previous value has a direct effect on the current value: et = ret-1 + ut where r is a constant that has absolute value less than one, and ut is drawn from a distribution with mean zero and finite variance, often a normal distribution. An AR(2) would have the form: et = r1et-1 + r2et-2 + ut and so on. In theory a process might be represented by an AR(infinity).
|
AR(1)
A first-order autoregressive process. See AR for details.
|
Arbitrage
Arbitrage plays a critical role in the analysis of securities markets,
bringing prices to fundamental values and keeping markets efficient.
|
ARCH
Stands for Autoregressive Conditional Heteroskedasticity. It's a technique used in finance to model asset price volatility over time. It is observed in much time series data on asset prices that there are periods when variance is high and periods where variance is low. The ARCH econometric model for this (introduced by Engle (1982)) is that the variance of the series itself is an AR (autoregressive) time series, often a linear one. Formally, per Bollerslev et al 1992 and Engle (1982): An ARCH model is a discrete time stochastic process {et} of the form: et = ztst where the zt's are iid over time, E(zt)=0, var(zt)=1, and st is positive and time-varying. Usually st is further modeled to be an autoregressive process. According to Andersen and Bollerslev 1995/6/7, "ARCH models are usually estimated by maximum likelihood techniques." They almost always give a leptokurtic distrbution of asset returns even if one assumes that each period's returns are normal, because the variance is not the same each period. Even ARCH models, however, do not usually generate enough kurtosis in equity returns to match U.S. stock data.
|
ARIMA
Describes a stochastic process or a model of one. Stands for "autoregressive integrated moving-average". An ARIMA process is made up of sums of autoregressive and moving-average components, and may not be stationary.
|
ARMA
Describes a stochastic process or a model of one. Stands for "autoregressive moving-average". An ARMA process is a stationary one made up of sums of autoregressive and moving-average components.
|
Arrovian uncertainty
Measurable risk, that is, measurable variation in possible outcomes, on the basis of knowledge or believed assumptions in advance. Contrast Knightian uncertainty.
|
Arrow-Debreu equilibrium
Means, in practice, competitive equilibrium of the kind shown in Debreu's Theory of Value. The Arrow-Debreu reference may be to a particular paper: "Existence of an Equilibrium for a Competitive Economy", Econometrica. Vol 22 July 1954, pp 265-290. I haven't checked that out.
|
Arrow-Pratt measure
An attribute of a utility function.
Denote a utility function by u(c). The Arrow-Pratt measure of absolute risk aversion is defined by: RA=-u''(c)/u'(c) This is a measure of the curvature of the utility function. This measure is invariant to affine transformation of the utility function, which is a useful attributed because such transformation do not affect the preferences expressed by u().
If RA() is decreasing in c, then u() displays decreasing absolute risk aversion. If RA() is increasing in c, then u() displays increasing absolute risk aversion. If RA() is constant with respect to changes in c, then u() displays constant absolute risk aversion.
|
ASQ
An abbreviation for the journal Administrative Science Quarterly which tends to be closer to sociology than to economics.
|
ASR
An abbreviation for the journal American Sociological Review.
|
asset pricing models
A way of mapping from abstract states of the world into the prices of financial assets like stocks and bonds. The prices are always conceived of as endogenous; that is, the states of the world cause them, not the other way around, in an asset pricing model. Several general types are discussed in the research literature. The CAPM is one, distinguished from three that Fama (1991) identifies: (a) the Sharpe-Lintner-Black class of models, (b) the multifactor models like the APT of Ross (1976), and (c) the consumption based models such as Lucas (1978). An asset pricing model might or might not include the possibility of fads or bubbles.
|
asset-pricing function
maps the state of the economy at time t into the price of a capital asset at time t.
|
asymptotic
An adjective meaning 'of a probability distribution as some variable or parameter of it (usually, the size of the sample from another distribution) goes to infinity.' In particular, see asymptotic distribution.
|
asymptotic normality
A limiting distribution of an estimator is usually normal. (details!)
This is usually proven with a mean value expansion of the score at the estimated parameter value? (details)
|
asymptotic variance
Definition of the asymptotic variance of an estimator may vary from author to author or situation to situation. One standard definition is given in Greene, p 109, equation (4-39) and is described there as "sufficient for nearly all applications." It's
asy var(t_hat) = (1/n) * limn->infinity E[ {t_hat - limn->infinity E[t_hat] }2 ]
|
asymptotically equivalent
Estimators are asymptotically equivalent if they have the same asymptotic distribution.
|
asymptotically unbiased
"There are at least three possible definitions of asymptotic unbiasedness: 1. The mean of the limiting distribution of n.5(t_hat - t) is zero. 2. limn->infinity E[t_hat] = t. 3. plim t_hat = t." Usually an estimator will have all three of these or none of them. Cases exist however in which left hand sides of those three are different. "There is no general agreement among authors as to the precise meaning of asymptotic unbiasedness, perhaps because the term is misleading at the outset; asymptotic refers to an approximation, while unbiasedness is an exact result. Nonetheless the majority view seems to be that (2) is the proper definition of asymptotic unbiasedness. Note, though, that this definition relies upon quantities that are generally unknown and that may not exist." -- Greene, p 107
|
Attitude
An attitude is "a psychological tendency that is expressed by evaluating a particular
entity with some degree of favor or disfavor"
(Eagly & Chaiken, 1993, p. 1).
This tendency can be expressed by different types of evaluative responses. Social
psychologists commonly differentiate between affective, cognitive and behavioral
responses. Affective responses towards an attitude object manifest themselves in
verbal expressions of feelings and physiological changes in the organism (e.g.
increase of arousal). Cognitive responses refer to expressions of beliefs (e.g.
expectancy-value judgments) and nonverbal reactions such as response latencies.
Behavioral responses manifest in behavioral intentions and actions. Attitude theory
and research deals with the structure, function, formation and change of attitudes,
and is also concerned with the relationship between attitudes and behavior.
The model of reasoned action
(Fishbein & Ajzen, 1975),
for example, provides
a comprehensive approach to all of these aspects. In this model, the internal
structure of an attitude is described in terms of beliefs (expectations), that
relate the attitude object (a behavioral alternative) to evaluated attributes.
The function of attitudes is to guide the formation of behavioral intentions.
Attitude formation and change is viewed as a process of deliberative evaluation
and belief updating. Attitudes are thought to impact behavior indirectly via
behavioral intentions. More recent approaches, however, assume that a deliberative
calculation of expectancy and values is not a necessary condition for either
intention formation or attitude formation and change. There is ample evidence
for example, that liking of an attitude object can be enhanced simply by
increasing its presentation frequency
(Zajonc, 1980)
Furthermore, attitudes,
if they are frequently activated from memory, tend to become activated automatically
in the presence of the attitude object and then directly impact behavioral decisions
(Fazio, 1990).
|
attractor
a kind of steady state in a dynamical system. There are three types of attractor: stable steady states, cyclical attractors, and chaotic attractors.
|
Auction
Competitive exchange process in which each trader from one market side submits a
bid, the most favorable one of which is selected by the complementary market side for
the transaction. Most commonly, the bidders form the potential buyers of a commodity,
and the bid-taker is a monopolistic seller. Also common is the converse constellation,
where a monopsonic buyer elicits price offers from competing sellers
( procurement auction).
In a narrow sense, auctions form a variety of familiar and less familiar selling and
buying mechanisms for goods reaching from objects of art and collectibles to natural
resources like minerals and agricultural products, to treasury bonds, construction and
supply contracts, oil drilling rights and broadcasting licenses. Also take-over battles
for firms or conglomerates are an explicit auction.
In a broader sense, auctions provide an explicit description of price formation
processes that arise from strategic interaction in markets. More general auction mechanisms
with competition on both market sides, so-called double auctions, form exchange
institutions that map competing price bids (buying demands) and price asks
(selling offers) into an allocation of the goods among the traders. Given the vector of
bids and asks (and some matching rule), the terms of trade for various quantities of
one or several goods are endogenously determined. A prototypical example for double
auctions are institutionalized markets of financial assets and financial derivatives.
Auctions are models of 'thin markets', making precise the sense in which markets 'find
prices' that can 'reveal' an underlying economic value. This is shown distinctively by the
fact they are the unique exchange mechanism adopted whenever competitive market
prices do not exist but the object sold is of particular uniqueness and size,
such as in privatizations of government enterprises, in the the sale of complex procurement
contracts, or seldom goods of arts; or when the resource in question does not have a price
other than the terms of trade which are revealed through strategic interaction of traders,
such as financial assets like stock, options, corporate or government bonds.
In a sense, strategic equilibria of competitive bidding games have many efficiency properties
that generalize those of competitive market equilibrium. As it is the highest
(buying) asks and the lowest (selling) offers that are selected for the transaction, the
resulting allocation of commodites and quantities is efficient ex post. Under appropriate
conditions, equilibrium outcomes from double auctions are even efficient in an interim sense
(see efficiency). Under reasonable informational assumptions, the equilibrium
bids of common value auctions (see below) converge to the competitive equilibrium price
as the number of bidders grows large (see also competitive market equilibrium).
Auctions are modelled as bidding games of incomplete
information. The bidders' (players')
strategies are bid functions converting their private information
about the objects in sale, and previous bids observed, into a money amount that is bid.
Such bidding games provide unified descriptions of many competitive processes from
diverse contexts. Together with the most common auction formats, we mention some
examples below.
|
augmented Dickey-Fuller test
A test for a unit root in a time series sample. An augmented Dickey-Fuller test is a version of the Dickey-Fuller test for a larger and more complicated set of time series models.
(Ed.: what follows is only my best understanding.) The augmented Dickey-Fuller (ADF) statistic, used in the test, is a negative number. The more negative it is, the stronger the rejection of the hypothesis that there is a unit root at some level of confidence. In one example, with three lags, a value of -3.17 constituted rejection at the p-value of .10.
|
Austrian economics
A school of thought which "takes as its central concern the problem of human coordination, through which order emerges not from a dictator, but from the decisions and judgments of numerous individuals in a world of highly disperced and sometimes only tacit knowledge." -- Cass R. Sunstein, "The Road from Serfdom" The New Republic Oct 20, 1997, p 42.
Well-known authors along this line include Carl Menger, Ludwig von Mises, and Friedrich von Hayek. See Deborah L. Walker's essay for a clear account.
|
autarky
The state of an individual who does not trade with anyone.
|
autocorrelation
the jth autocorrelation of a covariance-stationary process is defined as its jth autocovariance divided by its variance.
In a sample, the kth autocorrelation is the OLS estimate that results from the regression of the data on the kth lags of the data.
Below is Gauss code to calculate autocorrelations from a sample. /* This functions calculates autocorrelation estimates for lag k */
proc autocor(series, k);
local rowz,y,x,rho;
rowz = rows(series);
y = series[k+1:rowz];
x = series[1:rowz-k];
rho = inv(x'x)*x'y; /* compute autocorrelation by OLS */
retp(rho);
endp;
|
autocovariance
The jth autocovariance of a stochastic process yt is the covariance between its time t value and the value at time t-j. It is denoted gamma below, and E[] means expectation, or mean: gammajt = E[(yt - Ey)(yt-j-Ey)] In that equation the process is assumed to be covariance stationary. If there is a trend, then the second Ey should be the expected value of at the time t-j.
|
autocovariance matrix
Defined for a vector random process, denoted yt here. The ij'th element of the autocovariance matrix is cov(yit, yj,t-k).
|
Automaticity
Information processing that occurs without conscious control.
Mental processes fall on a continuum from more automatic to more controllable. At the most automatic end is preconscious automaticity, followed by post-conscious automaticity and goal-directed automaticity. Next are spontaneous processes, which are activated without consciousness but processed only with effort. Ruminative processes are slightly more controlled, they are conscious but not deliberately directed by goals. At the most controlled end, intentional thoughts are characterized by people having choices, especially if they make the hard (more effortful) choice, and paying attention to that choice to enact it.
Automatic processing can develop in response to stimuli and environments that people habitually encounter, as a way to save cognitive effort. Automatic responses, especially preconscious automaticity, can be defined with several criteria (Bargh, 1984). First, automatic processes are unintentional; they do not require a goal to be activated. Second, they are involuntary, always occuring in the presence of the relevant cue. Third, they are effortless, using no cognitive capacity. Fourth, they are autonomous, running to completion without any conscious monitoring. Finally, they are outside awareness, meaning they are activated and operated without consciousness.
|
autoregressive process
See AR.
|
Availability
traditionally refers to whether or not a construct is stored in memory
(Bruner, 1957).
Recently, there has been an increasing tendency to use the term accessibility and
availability interchangeably. Some overlap in the application of these terms was
introduced in
Tversky & Kahnemanīs (1973)
description of the
availability heuristic,
where availability referred to the ease of retrieving construct instances. In the
availability heuristic, however, availability also referred to the ease of
constructing instances of novel classes and events, which is distinct from
the traditional meaning of accessibility
(see Higgins & King, 1981).
|
Availability heuristic
This heuristic is used to evaluate the frequency or likelihood of an event on the basis of
how quickly instances or associations come to mind. When examples or associations are easily
brought to mind, this fact leads to an overestimation of the frequency or likelihood of this
event. Example: People are overestimating the divorce rate if they can quickly find examples
of divorced friends.
|
avar
abbreviation or symbol for the operation of taking the asymptotic variance of an expression, thus: avar().
|
Average Cost
The per-unit cost of producing a product, measured as the total cost of production divided by the number of units produced. It is frequently represented on a graph as a U-shaped curve (average costs initially decrease before eventually increasing).
|
Average Fixed Cost
The per-unit share of total fixed costs; it is calculated as the total fixed cost of production divided by the number of units produced. Because fixed costs do not depend upon the quantity produced, average fixed costs decline as more is produced.
|
Average Revenue
Total Revenue divided by the number of units that are produced.
|
Average Total Cost
The sum of variable and fixed costs divided by the number of units produced. It is calculated as Total Costs divided by the number of units produced.
|
Average Variable Cost
Total variable costs divided by the number of units produced.
|