fanplotaccepts name value pair arguments to control chart colors and line sizes for the historical and forecast lines.

Support fordatetimefor the following calendar functions according to these guidelines:

• Functions that take date inputs and output dates. If any of the date inputs aredatetimearrays, then the date outputs are returned as adatetime. Otherwise, the dates are returned asdatenums.

• Functions that take date inputs, but do not output dates. In this case, the function should return the same output whether the date inputs aredatenumsordatetime.

• Functions that do not take in date inputs, but output dates. In this case, an extra optional input argumentoutputTypeis included that allows you to specify the output as a'datenum'or a'datetime'. The default behavior is'datenum'.

• accrfrac

• acrubond

• acrudisc

• beytbill

• bndconvp

• bndconvy

• bnddurp

• bnddury

• bndkrdur

• bndprice

• bndspread

• bndtotalreturn

• bndyield

• busdate

• busdays

• candle

• cdai

• cdprice

• cdyield

• cfamounts

• cfdates

• cfdatesq

• cfplot

• cfport

• cfprice

• cfspread

• cfyield

• cftimes

• cpncount

• cpndaten

• cpndatenq

• cpndatep

• cpndatepq

• cpndaysn

• cpndaysp

• cpnpersz

• dateaxis

• date2time

• datefind

• datemnth

• datewrkdy

• days252bus

• days360

• days360e

• days360isda

• days360psa

• days365

• daysact

• daysadd

• daysdif

• disc2zero

• discrate

• eomdate

• fanplot

• fbusdate

• floatdiscmargin

• floatmargin

• fvdisc

• fvvar

• fwd2zero

• highlow

• holidays

• isbusday

• kagi

• lbusdate

• linebreak

• lweekdate

• m2xdate

• nweekdate

• nyseclosures

• periodicreturns

• prbyzero

• prdisc

• priceandvol

• prmat

• prtbill

• pvvar

• pyld2zero

• renko

• ret2tick

• tbilldisc2yield

• tbillprice

• tbillrepo

• tbillval01

• tbillyield

• tbillyield2disc

• tbl2bond

• thirdwednesday

• tick2ret

• time2date

• tmfactor

• today

• totalreturnprice

• tr2bonds

• uicalendar

• volarea

• weeknum

• wrkdydif

• x2mdate

• xirr

• yearfrac

• ylddisc

• yldmat

• yldtbill

• zbtprice

• zbtyield

• zero2disc

• zero2fwd

• zero2pyld

Support forquarter. The purpose of this function is to return the quarter of a given date.

ugarchis removed in this release. Use thegarchobject from the Econometrics Toolbox™ instead.

Compatibility Considerations

For more information on migratingugarchcode togarch, seeLikelihood Ratio Test for Conditional Variance Models.

ugarchllfis removed in this release. Use thegarchobject from the Econometrics Toolbox instead.

Compatibility Considerations

For more information on migratingugarchllfcode togarch, seeSpecify GARCH Models Using garch.

ugarchpredis removed in this release. Use thegarchobject from the Econometrics Toolbox instead.

Compatibility Considerations

For more information on migratingugarchpredcode togarch, seeForecast a Conditional Variance Model.

ugarchsimis removed in this release. Use thegarchobject from the Econometrics Toolbox instead.

Compatibility Considerations

For more information on migratingugarchsimcode togarch, seeSimulate Conditional Variance Model.

frontconhas been removed. UsePortfolioinstead.

Compatibility Considerations

For more information on migratingfrontconcode toPortfolio, seefrontcon Migration to Portfolio Object.

portopthas been partially removed and no longer acceptsConSetorvarargininput arguments. In this release, a modifiedportoptonly solves a portfolio problem for long-only fully invested portfolios. UsePortfolioinstead.

Compatibility Considerations

For more information on migratingportoptcode toPortfolio, seeportopt Migration to Portfolio Object.

Support for two new functions to set up tracking error constraints for aPortfolioobject.

• setTrackingPortsets up tracking or benchmark portfolio for a tracking error constraint.

• setTrackingErrorsets up a maximum portfolio tracking error constraint.

Credit scorecard supports two new functions for reviewing and converting predictor types:

• predictorinfoprovides a summary of credit scorecard predictors and their properties.

• modifypredictorenables you to set properties for credit scorecard predictors to change a predictor type from numeric to categorical or vice versa.

In addition, thecreditscorecardobject has two new properties,NumericPredictorsandCategoricalPredictors具有公共GetAccessand privateSetAccess, that is, they cannot be set at the command line using the dot notation.

Support for MATLAB^®table input fortransprobandtransprobprep.

Support for simple interest for the following functions:

• zero2disc— Support added forCompounding=0for simple interest where there is no compounding.

• disc2zero— Support added forCompounding=0for simple interest where there is no compounding.

• zero2fwd— Support added forInputCompounding=0for simple interest where there is no compounding, and alsoOutputCompounding=0for simple interest. SeeFunctionality Being Changed forfwd2zero,zero2fwd,pyld2zero, andzero2pyld.

• fwd2zero— Support added forInputCompounding=0for simple interest where there is no compounding, and alsoOutputCompounding=0for simple interest. SeeFunctionality Being Changed forfwd2zero,zero2fwd,pyld2zero, andzero2pyld.

• date2time— Support added forCompounding=0for simple interest where there is no compounding.

• zero2pyld— Support added forInputCompounding=0for simple interest where there is no compounding. SeeFunctionality Being Changed forfwd2zero,zero2fwd,pyld2zero, andzero2pyld.

• pyld2zero— Support added forOutputCompounding=0for simple interest where there is no compounding. SeeFunctionality Being Changed forfwd2zero,zero2fwd,pyld2zero, andzero2pyld.

• zbtprice— Support added forOutputCompounding=0for simple interest where there is no compounding.

• zbtyield— Support added forOutputCompounding=0for simple interest where there is no compounding.

These functions now accept additional optional input arguments that are specified as name-value pairs:InputCompounding,OutputCompounding,InputBasis, andOutputBasis.

In addition, forpyld2zeroandzero2pyld, the settings for the default behavior for optional name-value pairs inputs have changed. For more information, see the reference pages forpyld2zeroandzero2pyld.

ugarchwill be removed in a future release. Use thegarchobject from the Econometrics Toolbox instead.

Compatibility Considerations

For more information on migratingugarchcode togarch, seeLikelihood Ratio Test for Conditional Variance Models.

ugarchllfwill be removed in a future release. Use thegarchobject from the Econometrics Toolbox instead.

Compatibility Considerations

For more information on migratingugarchllfcode togarch, seeSpecify GARCH Models Using garch.

ugarchpredwill be removed in a future release. Use thegarchobject from the Econometrics Toolbox instead.

Compatibility Considerations

For more information on migratingugarchpredcode togarch, seeForecast a Conditional Variance Model.

ugarchsimwill be removed in a future release. Use thegarchobject from the Econometrics Toolbox instead.

Compatibility Considerations

For more information on migratingugarchsimcode togarch, seeSimulate Conditional Variance Model.

frontconhas been removed. UsePortfolioinstead.

Compatibility Considerations

For more information on migratingfrontconcode toPortfolio, seefrontcon Migration to Portfolio Object.

portopthas been partially removed and no longer acceptsConSetorvarargininput arguments. In this release, a modifiedportoptonly solves a portfolio problem for long-only fully invested portfolios. UsePortfolioinstead.

Compatibility Considerations

For more information on migratingportoptcode toPortfolio, seeportopt Migration to Portfolio Object.

• Enhancements toautobinningfor theAlgorithmname-value pair argument, where a new option'Monotone'is supported.Monotoneis an optimal binning algorithm that ensures monotonicity in the weight of evidence (WOE) of the resulting bins.

• Credit scorecards support model validation usingvalidatemodelthat provides the following three techniques:

  • Receiver Operating Characteristic (ROC)

  • Cumulative Accuracy Profile (CAP)

  • Kolmogorov-Smirnov (KS)

• Credit scorecards support probability of default usingprobdefault.

Theautobinningfunction for credit scorecards has an incompatibility with the previous release. The latest version ofautobinningsupports, by default, new binning behavior where the default for the'Algorithm'argument is now a new name-value pair argument for'Monotone'. In addition, the algorithms'EqualFrequency'and'EqualWidth'now support'SortCategories'option for categorical data. By default, categorical data is sorted by'odds'before binning.

Compatibility Considerations

To recover the previous behavior, useautobinningwith the following name-value pairs:

• For the syntaxsc = autobinning(sc)in R2014b, starting in R2015a, the syntax is equivalent to using:

  sc = autobinning(sc,'Algorithm','EqualFrequency','AlgorithmOptions',{'SortCategories','None'})

• For the syntaxsc = autobinning(sc,'Algorithm','EqualWidth')in R2014b, starting in R2015a, the syntax is equivalent to using:

  sc = autobinning(sc,'Algorithm','EqualWidth','AlgorithmOptions',{'SortCategories','None'})

• For the syntaxsc = autobinning(sc,'Algorithm','EqualFrequency')in R2014b, starting in R2015a, the syntax is equivalent to using:

  sc = autobinning(sc,'Algorithm','EqualFrequency','AlgorithmOptions',{'SortCategories','None'})

Life tables compute the probabilities, hazards, and survivor counts associated with people who are alive at a specified age and have the likelihood of death within a given period in the future. Four main parametric mortality models are supported for life studies: Gompertz, Gompertz-Makeham, Siler, and Heligman-Pollard.

• lifetableconv— Convert life table data from either raw form or generated form into different formats and series.

• lifetablefit— Calibrate parametric life table models based on life table data.

• lifetablegen— Generate life table data from parametric models.

New example showing how to use Parallel Computing Toolbox™ with SDE functions to improve performance. For details, seeImproving Performance of Monte Carlo Simulation with Parallel Computing.

frontconwill be removed in a future release. UsePortfolioinstead.

Compatibility Considerations

To turn off thefrontconwarning, seeTurning off the Warning Messages for frontcon.

For more information on migratingfrontconcode toPortfolio, seefrontcon Migration to Portfolio Object.

portoptwill be partially removed in a future release and will no longer acceptConSetorvararginarguments. In a future release,portoptwill solve the portfolio problem for long-only fully invested portfolios. UsePortfolioinstead.

Compatibility Considerations

To turn off theportoptwarning, seeTurning off the Warning Messages for portopt.

For more information on migratingportoptcode toPortfolio, seeportopt Migration to Portfolio Object.

Modeling support for credit scorecard development that includes the following new functions:

• creditscorecardcreates thecreditscorecardobject.

• autobinningapplies automatic binning for single or multiple predictors.

• bininforeturns bin information for a given predictor.

• modifybinslets you modify bins for a given predictor.

• bindatabins a dataset using the existing binning rules and performs Weight of Evidence (WOE) transformation.

• plotbinsplots histogram counts for predictor variables.

• fitmodelfits a logistic regression model using Weight of Evidence (WOE) data.

• setmodelsets the predictors and coefficients of a linear logistic regression model fitted outside thecreditscorecard对象,并返回一个更新creditscorecardobject.

• displaypointsreturns scorecard points information, such as points per bin or points per predictor.

• formatpointslets you modify point information, such as scaling or rounding.

• scoredetermines the score for each row of a dataset.

For more information, seeUsing creditscorecard Objects,Credit Scorecard Modeling Workflow, andCase Study for a Credit Scorecard Analysis.

Support forfmincongradients when usingsetSolverfor CVaR portfolio optimization provides increased performance for CVaR optimizations.

Certain SDE models that use a constant parameter or a deterministic function of time have a performance improvement.

Support for financial fan charts usingfanplot. Usefanplotto plot the combination of historical and forecast data to visualize possible outcomes.

The following SDE functions accept parameters you can specify as a single input argument that is identified as a deterministic function of time if the function accepts a scalar timetas its only input argument.

• bm

• cev

• cir

• diffusion

• drift

• gbm

• heston

• hwv

• sdeld

• sdemrd

In addition,ts2funcaccepts a new parameter value argument forDeterministicto support deterministic functions of time.

The default option for thecuttingplanesolver for aPortfolioCVaRobject has changed. Thecuttingplanedefault option forMasterSolverOptionshas changed from

optimoptions('linprog','Algorithm','Simplex','Display','off')

optimoptions('linprog','Algorithm','Dual-Simplex','Display','off')

下面的随机微分方程(SDE) functions have moved from Econometrics Toolbox to Financial Toolbox™:

• bm

• cev

• cir

• diffusion

• drift

• gbm

• heston

• hwv

• interpolate

• sde

• sdeddo

• sdemrd

• simByEuler

• simBySolution

• simulate

• ts2func

The following sample data sets and examples from thematlab/toolbox/econ/econdemosdirectory have moved tomatlab/toolbox/finance/findemos:

• Demo_AmericanBasket

• Example_BarrierOption

• Example_BlackScholes

• Example_CEVModel

• Example_CIRModel

• Example_CopulaRNG

• Example_LongstaffSchwartz

• Example_StratifiedRNG

• Data_GlobalIdx2.mat

Monte Carlo simulation performance enhancements to the approximate solution function (simBySolution) of GBM and HWV models with constant parameters.

New portfolio objectPortfolioMADfor mean-absolute deviation (MAD) portfolio optimization.

optimoptionssupport when using solver options forPortfolio,PortfolioCVaR, andPortfolioMADobjects for portfolio optimization.

Compatibility Considerations

There are two possible incompatibility impacts:

• When usingPortfolioorPortfolioCVaRobjects and the associatedPortfolio.setSolverorPortfolioCVaR.setSolvermethods, the default solver options now reference anoptimoptionsobject, instead of anoptimsetstructure. If you now use default solver options and operating on them assuming this is anoptimsetstructure, some of those operations may no longer work.

• ThePortfolioorPortfolioCVaRobjects and the associatedPortfolio.setSolverorPortfolioCVaR.setSolvermethods let you pass name-value pair arguments of solver options. In the past, setting solver options that were unused by the solver of choice would simply have no effect, becauseoptimsetwould accept the options, and the solver would simply ignore them. In contrast,optimoptionsobjects generate an error if you attempt to set an invalid option.

optimoptionsis the default and recommended method to set solver options, however,optimsetis also supported.

The following functions are moved from Financial Instruments Toolbox™ to Financial Toolbox:

• cdai

• cdprice

• cdyield

• tbilldisc2yield

• tbillprice

• tbillrepo

• tbillval01

• tbillyield

• tbillyield2disc

Graphical representation for cash flows usingcfplot.

Support forftstoolimport of Excel^®XLSX files on Linux^®and Mac OS X.

New solver option ('cuttingplane') forPortfolioCVaRobject for conditional value-at-risk (CVaR) portfolio optimization. For more information, seesetSolver.

The'totals'input argument totransprobbytotalsis typically generated bytransprob. Becausetransprobincludes an'algorithm'field in this structure since R2011b, you no longer need to specify the'algorithm'argument using a name-value pair when callingtransprobbytotals. If you specify an'algorithm'argument as a name-value pair when callingtransprobbytotals, you now receive an error.

Compatibility Considerations

Specifying the'algorithm'as a name-value pair argument totransprobbytotalsnow causes an error. If you started using this functionality in R2011b or later, most likely you don't have to take any action. If you have used this functionality before R2011b, make sure you remove the'algorithm'name-value pair from calls totransprobbytotals, and that the'totals'input argument totransprobbytotalscontains an'algorithm'field indicating the desired algorithm. In most cases, the latter can be achieved by recreating the'totals'structure with a call totransprobwhich automatically adds the'algorithm'field since R2011b.

Any time you enter a cell array of date strings that are in different date formats using the MATLAB functionsdatenum,datestr, anddatevec, these functions previously returned an error. In R2013a, this behavior has changed. In Financial products this change can cause an unexpected date format to generate an incorrect value. For example, the following use ofdatevecreturned an error before R2013a because of the inconsistent date formats, but in R2013a this code does not return an error.

datevec({'10-Oct-2012','10-1-2012'}),

Compatibility Considerations

As a best practice, you should convert date strings to date numbers before using any functions in Financial Toolbox that use dates as inputs. For more information, seeNo strict-match requirements for month formats when converting date stringsin the MATLAB release notes.

New portfolio objectPortfolioCVaRfor conditional value at risk (CVaR) portfolio optimization.

Support for calculating spread measures for floating-rate bonds usingfloatdiscmarginandfloatmargin.

Support for calculating bond horizon return usingbndtotalreturn.

Performance improvement for calculating cash flows usingcfamounts.

Support is added toxirrfor a global search heuristic to enhance the robustness ofxirr.

A new demo shows how to set up mean-variance optimization problems using the portfolio object. Run the demo at the MATLAB command line by entering:

showdemo portfolioexamples

The portfolio object supports one-way turnover constraints using the new methodssetOneWayTurnoverandgetOneWayTurnover.

The portfolio object supports estimating an efficient portfolio that maximizes the Sharpe ratio using the new methodestimateMaxSharpeRatio.

Updatedcfamountsnow supports time-varyingCouponRateandFacescheduling, including support for sinking fund bonds.

Support is added for credit quality thresholds withtransprobtothresholdsandtransprobfromthresholds. Support is added for data preprocessing fortransprobusingtransprobprep. Support is added for user-defined ratings and nonsquare transition matrices withtransprobgrouptotalsandtransprobbytotals. For more information, seeCredit Risk Analysis.

A new demo shows how to forecast corporate default rates. This includes backtesting and stress testing examples. Run the demo at the MATLAB command line by entering:

showdemo Demo_DefaultRatesForecasts

Many warning and error IDs have changed from their previous versions. These warnings or errors typically appear during a function call.

Compatibility Considerations

If you use warning or error IDs, you might need to change the strings you use. For example, if you turned off a warning for a certain ID, the warning might now appear under a different ID. If you use atry/catchstatement in your code, replace the old identifier with the new identifier. There is no definitive list of the differences, or of the IDs that changed.

Thetotalsinput totransprobbytotalsis typically generated bytransprob. Becausetransprobnow includes analgorithmfield in this structure, you no longer need to specify thealgorithmargument when callingtransprobbytotals.

Compatibility Considerations

In a future release, specifying thealgorithmargument totransprobbytotalswill error. Currently, it is still permissible to specify thealgorithmargument, although it usually has no effect.

New portfolio object and methods support mean-variance portfolio optimization with general linear constraints, transaction costs, and turnover constraints. For more information, seePortfolio Optimization ToolsandPortfolio Optimization Objects.

The command to run the demo showing how to use Statistics Toolbox™ functions to support credit ratings is updated. Run the demo at the MATLAB command line by entering:

showdemo creditratingdemo

Support for estimation of transition matrices based on credit-migration history using both cohort and duration methods. For more information, seetransprob,transprobbytotals, andEstimation of Transition Probabilities.

portoptis enhanced for improved speed. Specifically, a broader class of problems now uses the faster linear complementarity programming (LCP) algorithm to obtain portfolios on the efficient frontier.

一个新的演示展示了如何使用统计工具箱的乐趣ctions to support credit ratings. Run the demo at the MATLAB command line by entering:

echodemo demo_creditrating

cfamountsis enhanced to support new parameter/value pairs for swap functionality.

Support for theBasisday-count convention for BUS/252. BUS/252 is the number of business days between the previous coupon payment and the settlement data divided by 252. BUS/252 business days are non-weekend, non-holiday days. Theholidays.m文件定义的节日s.

The currentholidaysfunction covers holidays and non-trading days from 1950 to 2050. Usingnyseclosures, you can determine all known and anticipated closures from January 1, 1885 to December 31, 2050.

Support for the following enhancements to bond pricing functions:

• Provide the ability to specify the compounding frequency separately from the coupon frequency.

• Enable specification of a discounting basis. A discounting basis has two purposes in Price/YTM calculations:

  • Computing the accrued interest

  • Computing the discount factors

• Support the specification of a formula for computing the interest in the last coupon period.

The enhanced bond pricing functions are:

Added support forbndkrdurto calculate key rate duration for bonds to determine the sensitivities of a bond to nonparallel changes in the yield curve. For more information, seeCalculating Key Rate Durations for Bonds.

Added support forvararginargument forportoptandfrontcon.

The following functions now support day count conventions for thebasisargument based on ISDA (International Swap Dealers Association) actual/365:

• accrfrac

• acrubond

• acrudisc

• bndconvp

• bndconvy

• bnddurp

• bnddury

• bndprice

• bndspread

• bndyield

• cfamounts

• cfdates

• cftimes

• cpncount

• cpndaten

• cpndatenq

• cpndatep

• cpndatepq

• cpndaysn

• cpnpersz

• datemnth

• daysadd

• daysdif

• disc2zero

• discrate

• fvdisc

• fwd2zero

• prbyzero

• prdisc

• prmat

• pyld2zero

• time2date

• yeardays

• yearfrac

• ylddisc

• yldmat

• zbtprice

• zbtyield

• zero2disc

• zero2fwd

• zero2pyld

ret2tickandtick2retsupport financial time series objects.

The following covariance methods now support a financial time series object:

• corrcoef

• cov

• isempty

• nancov

• nanmax

• nanmedian

• nanmin

• nanstd

• nansum

• nanvar

• var

Added support for the following chart types for financial reporting:

• kagi

• renko

• linebreak

• priceandvol

• volarea

The following functions now support day count conventions for thebasisargument to support 30/360 International Securities Market Association (ISMA) convention as a variant of 30/360E with annual compounding:

• accrfrac

• acrubond

• acrudisc

• bndconvp

• bndconvy

• bnddurp

• bnddury

• bndprice

• bndspread

• bndyield

• cfamounts

• cfdates

• cftimes

• cpncount

• cpndaten

• cpndatenq

• cpndatep

• cpndatepq

• cpndaysn

• cpnpersz

• datemnth

• daysadd

• daysdif

• disc2zero

• discrate

• fvdisc

• fwd2zero

• prbyzero

• prdisc

• prmat

• pyld2zero

• time2date

• yeardays

• yearfrac

• ylddisc

• yldmat

• zbtprice

• zbtyield

• zero2disc

• zero2fwd

• zero2pyld

Thecreateholidaysfunction now supportshttp://www.FinancialCalendar.comtrading calendars. This function can be used from the command line or from the Trading Calendars graphical user interface. Usingcreateholidays, you can createholiday.mfiles, in conjunction withFinancialCalendar.comdata, that can be used instead of the standardholidays.mthat ships with Financial Toolbox software.

The new diagonal covariance matrix estimation feature makes it possible to estimate large-scale factor models by treating the residual errors as being jointly independent. The following functions supportCovarFormat, a new input argument:

• ecmlsrmle

• ecmmvnrmle

• ecmmvnrfish

• ecmmvnrobj

• ecmmvnrstd

• mvnrfish

• mvnrmle

• mvnrobj

• mvnrstd

Two new functions,arith2geomandgeom2arith, support portfolio analysis.

The following functions now support the International Securities Market Association (ISMA) convention for thebasisargument:

• accrfrac

• acrubond

• acrudisc

• bndconvp

• bndconvy

• bnddurp

• bnddury

• bndprice

• bndspread

• bndyield

• cfamounts

• cfdates

• cftimes

• cpncount

• cpndaten

• cpndatenq

• cpndatep

• cpndatepq

• cpndaysn

• cpnpersz

• datemnth

• daysadd

• daysdif

• disc2zero

• discrate

• fvdisc

• fwd2zero

• prbyzero

• prdisc

• prmat

• pyld2zero

• time2date

• yeardays

• yearfrac

• ylddisc

• yldmat

• zbtprice

• zbtyield

• zero2disc

• zero2fwd

• zero2pyld

The following new functions are added to compute common investment performance and risk-adjusted metrics:

• sharpe, computes the sharpe ratio.

• inforatio, computes information ratio and tracking error.

• portalpha, computes risk-adjusted alpha and return.

• lpm, computes sample lower partial moments.

• elpm, computes expected lower partial moments.

• maxdrawdown, computes the drop from maximum to minimum return over a period of time.

• emaxdrawdown, computes the returns that are transformed into a linear Brownian motion with drift.

Financial Time Series Tool (ftstool) is a new graphical user interface to support working with financial time seriesFINTSobjects.ftstoolinteroperates with the Financial Time Series Graphical User Interface (ftsgui) and Interactive Charts (chartfts).

As of this release the functionality previously available in Financial Time Series Toolbox has been incorporated into Financial Toolbox software. Financial Toolbox documentation has been modified to include the documentation previously available in the Financial Time Series User's Guide.

Because use of Financial Time Series Toolbox required the purchase and installation of Financial Toolbox software, all customers previously licensed for Financial Time Series Toolbox will continue to have access to it.

The suite of time series frequency conversion functions (todaily,toweekly,tomonthly,tosemi, andtoannual) has been extensively modified. Consult the function references in the Financial Toolbox User's Guide for specifics.

Continuous compounding is no longer available forpyld2zero. Compounding for this function is now consistent with compounding for the functionzero2pyld. An error message is generated if you attempt to use continuous compounding with these functions.

The new functions in Version 3.0 of Financial Toolbox software fall into these four categories:

Multivariate Normal Regression Without Missing Data

Multivariate Normal Regression With Missing Data (Expectation Conditional Maximization)

Least Squares Regression With Missing Data (Expectation Conditional Maximization)

Financial Model Transformation Function

Version 2.5 introduces a set of financial statistical computation routines that compute values, such as mean and covariance, when there are missing data elements within a larger data set. These routines implement the Expectation Conditional Maximization (ECM) algorithm with various options that depend on the percentage of missing at random (MAR) data within the data set. The table below lists the functions that implement the ECM algorithm in Financial Toolbox software.

The following ECM functions have been added at this release.

Expectation Conditional Maximization