Table of Contents

Getting Started

Welcome to the Estimator:
Introduction to the Asset Allocation Suite:
Conventions in the Estimator:
Running an Estimator Problem:
Instances:
Sample Cases:
NFA Ribbon:
Preferences:

Worksheets

Introduction to the Worksheets:
Asset Returns Worksheet:
Historical Worksheet:
Forecasts Worksheet:
Components Worksheet:
Effects Worksheet:
Results Worksheet:
Charts Worksheet:

Estimation Inputs

Return Series:
Importing Returns from Outside Sources:
Importing CSV Returns:
Bloomberg:
Financial Modeling Prep (FMP):
Loading:
Benchmarks Return Series:
Assets Wizard:
Forecasts:
Forecast Contrasts:
Market Portfolio:
Period:
Series Adjustment Value:
Risk Scaling Factor:
Asset Groups:

Adjusting Data

Historic Data Adjustment:
Missing Data Algorithm:
Forecast Data Adjustment:

Estimator Output

Moving to the Optimizer:
Reporting:
Saving Files:
Copying and Pasting:
Multiple and Partial Correlations:

Charts

Asset Correlations:
Asset Ranges:
Assets Risk and Return:
Growth of Asset(s):
Histogram:
Historical Returns:
Rolling Correlations:

Troubleshooting

Error Handling:
Troubleshooting Tools:
Debugging Log:
Known Issues:
Add-In Not Loaded:

Welcome to the Estimator

The Estimator is the best way to create well-formed and consistent optimization inputs for the New Frontier Optimizer that properly combine multiple sources of information. The Estimator is comprised of historical data importing tools, a robust missing data algorithm, noise reduction with various shrinkage estimator, and a flexible system for combining the cleaned and adjusted historical inputs with exogenous views.

In addition to this help manual, New Frontier has a recorded training presentation available in our training library. Contact your relationship manager for more information.

Introductory Topics:

Introduction to the Asset Allocation Suite

The three modules of the Asset Allocation System facilitate the construction of realistic, effectively diversified portfolios with well-managed risk. The software provides a complete system for making asset allocation decisions.

For more information pertaining to Michaud optimization, the rebalance test, Trade Advisor, or LifeCycle's calculation methods, talk to your relationship manager or view the Optimizer and LifeCycle help manuals.

Conventions in the Estimator

Background color indicates the purpose of individual cells within the Estimator. White cells can be changed. Cells shaded a light yellow contain calculated information or information that cannot be changed manually. For example, since the Historical Worksheet picks up the Asset Names and Descriptions from the Asset Returns Worksheet, those columns are in light yellow on the Historical Worksheet.

Numbers appear in blue, black, and red. Protected, light yellow cells, contain black numbers. White, editable cells contain blue numbers. Red numbers indicate negative values.  Red "N/A" indicates missing data. Light blue on the Asset Returns Worksheet indicates that a particular asset is not included in the current investment universe or is only included as a benchmark return series. Similarly, light blue contrasts are currently inactive; while bold contrasts are active.

Running an Estimator Problem

Running an estimation problem in the Estimator involves the following basic steps:

Instances

Multiple Instances of Excel

Opening the Estimator through the Start Menu starts an instance of Excel, accesses Estimator, and loads the default case.  Double clicking on a saved Estimator file (*.nfei) or return series (*.nfrs) similarly opens an instance of Excel, accesses Estimator, and loads your saved file.  If you perform both of these actions, or repeat these actions, two instances of Excel with Estimator will be open.  Opening separate instances of Excel means that closing one instance will not close the others, that you can run two instance of Estimator simultaneously, and that you cannot use New Frontier’s copy and paste tools between the two.  The same advantages and limitations apply to Optimizer and LifeCycle instances operating within separate instances of Excel.

One Instance of Excel

To open multiple instances of LifeCycle, Optimizer, or Estimator within the same instance of Excel, use the launch tool.  With only one instance of Excel open, New Frontier copy and paste works.  However, only one application can run at a time.

 

From Estimator

From Optimizer

From LifeCycle

Launch Estimator

Copies current Estimator case into a new Estimator instance

Launches Estimator with the default case

Launches Estimator with the default case

Launch Optimizer

Copies Estimator data  into a new Optimizer instance

Copies current Optimizer case into a new Optimizer instance

Launches Optimizer with the default case

Launch LifeCycle

Launches LifeCycle with the default case

 

There are three ways to launch.  Each copies the Optimizer data (frontier and portfolios) into LifeCycle.  The LifeCycle case  depends on the option chosen:

  • LifeCycle - Blank Case: LifeCycle case with minimal data

  • LifeCycle - Choose File: Prompts for a *.nfli or *.nflc file

  • LifeCycle - Sample Case: uses the Endowment LifeCycle sample case

Copies the entire LifeCycle information file except for the efficient frontier

New

New Estimator copies the current data into a new Estimator.  

Opens a blank, eight asset Optimizer case

Opens a blank LifeCycle case

Sample Cases

New Frontier provides some sample cases for your use in the samples directory. The default location for the samples directory is C:/Program Files/NewFrontier/8.0/samples.  The Estimator can open Estimator cases (*.nfei) and return series (*.nfrs).  

Michaud 1998 book

The Michaud 1998 book case consists of data used by Richard Michaud when he prepared Efficient Asset Management. The default inputs and results that populate the Optimizer when it is first opened come from this case. The data consists of six country equity indices and two bond indices: Canada, France, Germany, Japan, United Kingdom, United States, a U.S. bond index and a Eurobond index. The non-U.S. equity indices are all MSCI data and the U.S. equity index is the S&P 500.  The dataset is meant to illustrate a reasonable global asset allocation but is not for investment purposes.

Michaud 2008 paper

The Michaud 2008 case offers the data used by Richard Michaud and Robert Michaud in "Estimation Error and Portfolio Optimization" (Journal Of Investment Management, Q1 2008). Following Jobson and Korkie (1981), the optimizations are illustrated based on the risk and returns of twenty U.S. stocks randomly chosen from 100 largest capitalization stocks in the S&P 500 index with continuous monthly returns from January 1997 through December 2006. The list of stocks, their annualized average returns, standard deviations and correlations over the period and further details are given in the appendix to the paper.  

Vanguard Data

New Frontier includes data for several index funds provided by Vanguard with the Asset Allocation System. Because Vanguard uses a passive, full-replication approach to managing their index funds, the funds may be expected to serve as good proxies for the underlying indices. The equity funds track their CRSP, FTSE, and MSCI index counterparts. The fixed income index funds track the appropriate Bloomberg Barclays Capital indices.

The four Vanguard cases are named according to the frequency of the data provided: annual, monthly, quarterly, and weekly. This leads to slightly different correlations and therefore slightly different results. In addition, the weekly case lacks inflation adjustment since the CPI isn't available on a weekly basis.  

These cases also contain sample contrasts to explore.

The following funds have been included in the investment universe:

  1. CPI (seasonally adjusted, as reported by the Bureau of Labor Statistics)

  2. Vanguard Short-Term Bond Index

  3. Vanguard Intermediate-Term Bond Index

  4. Vanguard Long-Term Bond Index

  5. Vanguard Inflation-Protected Securities Index

  6. Vanguard High-Yield Corporate Index

  7. Vanguard REIT Index

  8. Vanguard European Stock Index

  9. Vanguard Pacific Stock Index

  10. Vanguard Emerging Markets Index

  11. Vanguard Growth Index

  12. Vanguard Value Index

  13. Vanguard Small-Cap Growth Index

  14. Vanguard Small-Cap Value Index

 

NFA Ribbon

File Section

Run Section

Edit Section

The Estimation Options and Series Adjustment Sections are for historic data adjustment.

Workbook Section

Report accesses the Report Designer.

Help opens this help manual, which you have evidently figured out already.

Preferences

The Preferences Window permits you to adjust the settings for your applications. All preferences carry over to all of New Frontier's applications. So, the default seed selected in the Estimator also applies to the Optimizer, etc.  Click the Preferences Button from the ribbon. The Preferences Window appears. Choose one of the panes by selecting the appropriate option in the tree to the left.

General Pane

Bloomberg Pane

Once Bloomberg account information is entered here, the Estimator can import data from Bloomberg. This requires an Estimator case with Bloomberg global ids entered as the ticker, a valid Bloomberg account, and an internet connection.  

Misc Data Sources Pane (FMP)

The Estimator can import FMP returns once the FMP API key has been entered here. Remember to set the ticker source to FMP for each ticker in the Asset Returns Worksheet.

Debug Pane

The Debug Pane permits the user to enable debugging. Debugging should only be enabled when a specific problem has been identified, as it creates logs for each action that save to the specified folders.

Reset Pane

The Reset Pane provides the option to return the preferences to the defaults selected by New Frontier.  Invoking this option will carry over to your preferences in all modules of the Asset Allocation System.

Introduction to the Worksheets

The Estimator opens with five visible worksheets for inputs and results:

Asset Returns Worksheet

The Asset Returns Worksheet displays the return series for all of the assets included in the investment universe. This worksheet permits you to load, enter, or import return series data and adjust it in preparation for running the Estimator. All checkmarked asset return series will be included in the output return, standard deviation, and correlation estimates. The return series name can be entered in the Return Series Name Field. The benchmark return series, selected in the drop down menu in the ribbon appears in light blue in the leftmost asset column.

Exclude/include an asset from the estimation by removing the checkmark above the asset return series column.  

Relevant Topics:

Historical Worksheet

The Historical Worksheet manages the analysis of the historical return series.  

Relevant Topics:

Forecasts Worksheet

Use the Forecasts Worksheet add information to the analysis that is not in the historical data.  

Relevant Topics:

Components Worksheet

The Components and Effects Worksheets provide diagnostics to understand the complete effects of both single-asset forecasts and Contrast Forecasts on the Result Means of all assets in the case.

As a set of single-asset forecasts and contrast forecasts develops, each new forecast or contrast tends to have rippling effects across the entire set of assets, often unintentionally and unpredictably. The Components and Effects worksheets are diagnostic tools designed to assess the impact of each individual single-asset forecast or contrast across all the assets, so that the impacts of changes can be better understood and unpredictable movements in the result estimates can be managed by adjusting their principal causes.

Both worksheets have important information that can be useful in diagnosing problems with a set of Bayes priors. The Components worksheet mainly deals with the impact of changes to the mean of a forecast, and the Effects worksheet shows the impact across all of the assets of including each forecast versus not including it, as a generalization of the “forecast effect” row, which shows only the effect of the forecast on its own value.

Before Running Bayes on a new case, or in a case saved in a previous version of the Estimator, the tables may be populated with N/A. Numerical values will appear after Running Bayes, since the calculation of these tables depend on the interaction of the Bayes calculations.

Components Worksheet

The Components Worksheet breaks out the full list of Bayes priors, starting first with the Full Mean, which is the Result Mean after the Bayes procedure, and matches the “Result Mean” on various other worksheets. Next are three columns showing the contributions of Historical, Single Prior, and Contrast to the Full Mean. The sum of these three columns are exactly equal to the full mean column. Next are a group of columns corresponding to each single-asset forecast as well as each Contrast Forecasts. These columns have been scaled by dividing by their Forecast means (in percent), so that the columns, when multiplied by their forecast means, add up to the category total. This scaling means that each column shows the impact of raising its forecast mean by 1%. This can be very useful for discovering hidden impacts on other assets or finding the source(s) of unexpected result means after running Bayes.

The Mathematics

The components analysis is derived by separating the formulas for the result mean into components corresponding to the respective parts of the whole, which sum to attain the result mean.

Result Mean = Inv(Whist + WPrior + WContrast) * (Whist * Mhist + WPrior * Mprior + WContrast * MContrast), where

Whist = Inv(CovHist), and CovHist and Mhist are the Historical Covariance Matrix and Mean Vector outputs from the Missing Data Algorithm;

WPrior = Inv(CovPrior) on the rows and colums with single-asset priors, zero otherwise; and CovPrior and MPrior are the square diagonal Matrix of Prior Variances and the Vector of Prior Means;

WContrast = ContrastMatrix’ * Inv(CovContrast) * ContrastMatrix, ContrastMatrix is the aggregate matrix of contrast coefficients, and CovContrast and MContrast are the diagonal Matrix of Contrast Variances and the Vector of Contrast Means.

Let Winv = Inv(Whist + WPrior + WContrast), then we have

Result Mean = Winv * Whist * Mhist + Winv * WPrior * Mprior + Winv * Wcontrast * MContrast.

The last line shows the decomposition of the result mean into three components (separated by the plus signs) corresponding Historical Data, Single-asset Priors, and Contrasts.

These terms can be further broken down by isolating each element of the final Mean vector corresponding to each single-asset forecast or Contrast, thus producing the unscaled components shown on the charts. The scaled components are calculated by dividing each component by its corresponding prior mean in percent, to obtain that element’s contribution to the result mean of each asset in the case when raising the prior mean by 1%.

Example:

 

Components chart
Components chart for the Vanguard Case with an added forecast for Short Term Bonds with Mean 4.5% and Standard Deviation of 2%

In the above example, we have one single-asset Forecast, on Short Term Bonds with Mean 4.5% and Standard Deviation of 2%, added on the Forecasts Worksheet, as well as the two Contrast Forecasts in the sample case. The single asset forecast has the effect of raising the result mean by 0.58% for its own asset (Short Term Bonds), by raising the Forecast Mean by 1%. This value is highlighted in gray in the middle section of the chart, surrounded by heavy cell borders. Perhaps surprisingly, raising the forecast mean by 1% also has the effect, for example, of raising the result estimate for long bonds by 1.60%, and reducing the result estimate for Small Cap Growth by -0.68%. This type of example illustrates how useful this information can be in diagnosing unexpected outcomes in result means.

Similarly, we can see the impact of the two Contrast Forecasts on the case. Raising the Market Forecast Contrast Mean by 1% would cause all of the result means to increase, but some more than others. The Short Term Bond forecast is the least affected with almost no change, but the Emerging Markets Stock Forecast is raised by 0.91%. The Small to Large US Contrast Forecast has ripple effects outside of the assets in its contrast coefficients - raising its Contrast Forecast Mean by 1% will, for example, raise the Result Mean for Real Estate by 0.50%.

Whereas the Components Worksheet shows the impact of adjusting the Forecast Mean for any forecast, the Effects Worksheet shows the impact of including or excluding the entire forecast.

Effects Worksheet

As a set of single-asset forecasts and contrast forecasts develops, each new forecast or contrast tends to have ripple effects across the entire set of assets, sometimes unpredictably so. The Components and Effects worksheets are diagnostic tools designed to assess the impact of each individual single-asset forecast or contrast, so that the impacts of changes can be better understood and unpredictable movements in the result estimates can be managed by adjusting their principal causes.

Both worksheets have important information that can be useful in diagnosing problems with a set of Bayes priors. The Components worksheet mainly deals with the impact of changes to the mean of a forecast, and the Effects worksheet shows the impact across all of the assets of including each forecast versus not including it, as a generalization of the “forecast effect” row, which shows only the effect of the forecast on its own value.

Before Running Bayes on a new case, or in a case saved in a previous version of the Estimator, the tables may be populated with N/A. Numerical values will appear after Running Bayes, since the calculation of these tables depend on the interaction of the Bayes calculations.

The Effects worksheet shows the impact of each forecast on the case, i. e. it is the result mean of the case minus the result mean of a case without that forecast.

Example:

In the illustrated example, a single-asset Forecast has been added for Short Term Bonds with a Forecast Mean of 4.5% and a Standard Deviation of 2%. Adding this contrast has the effect of raising the Result Mean for Short Term Bonds by 1.69%, but the other Treasurys (Intermediate and Long Term Bonds) are raised by 3.21% and 4.70%. The US Equities are negatively affected, due to the correlations between the assets, in all cases by over 1%. 

Whereas the Components Worksheet shows the impact of adjusting the Forecast Mean for any forecast, the Effects Worksheet shows the impact of including or excluding the entire forecast.

This example serves as an excellent illustration that sometime Forecasts may have unintended ripple effects on other assets' result means. 

Results Worksheet

The Results Worksheet displays the following:

Relevant Topics:

Charts Worksheet

The Estimator contains several chart options to help you visualize and interpret the estimation results and to aid in reporting. All charts appear on the Charts Worksheet. Select the particular chart from the Chart Type drop down menu. For some of the charts, additional selections, such as particular assets, must be made.

Chart List

All pf the charts included in New Frontier's applications can be edited using Excel's chart editing tools. Typical edits might include adding legends, changing colors or line styles, switching axes, editing the title, legend, axis, or other labels, or adding annotations. Clicking on the chart will cause additional Excel ribbons to appear, which can be used to edit the chart. See an Excel manual for details.

Return Series

Return series consist of returns for a set of assets, expressed as percentages, at regularly spaced intervals over a period in time. The Estimator uses the raw data in the return series to estimate historical means, standard deviations, and correlations. Return series can be saved, loaded, imported from online sources, or entered directly into Excel either manually or through copy/paste.

Return Series Preparation

Return series appear on the Asset Returns Worksheet.  

  1. Use the File>>New>>New Return Series Option to access the New Return Series Wizard. Enter the characteristics of the new return series (below), then click the OK Button.  A grid appears with the dates to the left and a column for each asset. A thick black line delineates the area to be completed. Each cell within the grid populates with "N/A", indicating that the cells can be edited.  

    • Start and End Dates -- Enter the dates of the earliest and latest return observation, even if these vary between assets. The Estimator contains tools for adjusting the date range to fit your needs.  Click on the triangles at the end of the date fields to access a calendar. You can add or remove dates later. Note that the Estimator cannot handle dates earlier than 1900.  

    • Period -- Select year, month, quarter, week, or day depending on the frequency of the return observations. The maximum number of observation dates is 10436 for weeks, 2400 months, 800 quarters, or 200 years. For daily data, review the warning below.

    • Number of Assets -- Enter the number of assets that you wish to include in your return series. Add or remove columns later at your discretion. The maximum number of assets is 200.

  2. Double check the dates to ensure that they match the dates on your return observations, repeating step one as necessary. Regular observations are essential. For instance, you cannot combine bimonthly and weekly observations.

  3. Enter asset names, tickers, descriptions and groups as desired. If you do not want to use groups or descriptions, you can hide the row in the Display Menu.  

  4. Insert collected return observations in the appropriate columns. Copy return observations from other spreadsheets or old return series, use the Yahoo! returns importer, import from Bloomberg, or enter return observations manually. Commonly, users load an old return series and add the most recent return observations either by typing them in or copying them from a spreadsheet. For missing data, enter a letter not a zero; the cell populates with "N/A" in red. The Estimator is limited to 200 assets. The maximum number of observation dates is 10436 for weeks, 2400 months, 800 quarters, or 200 years.

  5. If you wish to add an additional asset, enter the asset name and return observations in a column outside of the black box, and then click the Validate/Resize button in the Run Section of the NFA ribbon.  Estimator resizes the edges of the return series according to row and column headings and redraws the thick black line that delineates the edges.  

    • Remember that the Estimator is limited to 200 assets.  

    • When you validate/resize, the Estimator converts your returns to percentages, so if you want the return to be 1%, enter 0.01.

    • Update the market portfolio and forecasts if relevant.  

    • You can insert a column in the middle of the asset returns, but only one at a time. To insert multiple columns, enter the data outside of the box to the right.  

  6. To exclude an asset without deleting the data, use the checkmarks above the return series column. For details, see the Asset Returns Worksheet.

  7. To delete an asset, delete the column. Highlight the column by clicking on the column letter; right click to call up the menu. Select the Delete option. The column disappears and the box resizes.

    • Be aware that there is no Undo function in any of the New Frontier applications, so deleted data cannot be recalled. Using the check box to remove the asset from the asset universe may be a better solution.

    • Update the market portfolio as necessary.

    • Due to formatting issues, you cannot delete the first column in the return series. Work around this restriction by copying data into other columns, or by using the Asset Selector to reorder assets.

    • Using the delete button on the keyboard instead of the delete option in the menu that appears when you right click, deletes the data but not the column.

    • You can delete multiple columns at the same time provided that they are contiguous. Non-contiguous columns cannot be deleted at the same time.

  8. To delete a date, delete the row. Highlight the column; right click to call up the menu. Select the Delete Option. The row disappears. Be aware that there is no Undo function in any of the New Frontier applications, so deleted data cannot be recalled. The black box that borders the return series will be redrawn. Due to formatting issues, you cannot delete the first row in the return series. An alternate way to remove dates from the return series is to adjust the period on the Historical Worksheet.

  9. If you wish to add an additional date, enter the date and return observations in a row outside of the black box, and then click the Validate/Resize Button in the NFA ribbon. Estimator resizes the edges of the return series based on row and column headings, and redraws the thick black line that delineates the edges.  

  10. Review the return series. Specifically review all cells that report missing data and the Dates Column.

  11. Save your return series for further use.

  12. Set a benchmark return series.

  13. Start historical data adjustment.

Warnings:

Importing Returns from Outside Sources

If you enter tickers in the Asset Tickers row of the Asset Returns Worksheet, the Estimator can import return data from Yahoo! Finance, the Bureau of Labor Statistics (BLS), Financial Modeling Prep (FMP), and Bloomberg. (See the Considerations section below for more information about the data sources.) To access these features, click on Load, and select the Import menu in the Estimator Ribbon.

The Import returns from online data sources option within the Load drop down menu on the NFA ribbon overwrites any data in the columns of recognized tickers.

The Update returns from Yahoo/BLS option only imports data to empty cells or cells that display "N/A". It will not disturb previously entered returns, which is useful for appending data to previously vetted returns.

The Update returns since Last Update option will limit the data import process to returns at the end of each asset return series, since the last update. This is useful for adding new time periods to update a dataset without disturbing previous work, which could include N/A entries that were deliberately created to eliminate undesirable data.

 CPI

If you wish to use the Consumer Price Index from the Bureau of Labor Statistics as your benchmark return series, enter CPI in the Asset Name field in the Benchmark Column and the Series ID from the Bureau of Labor Statistics website in the Asset Ticker field. Select "BLS" as the Ticker Source. As there isn't just one Consumer Price Index, you will need to select the appropriate index for your data.

Sample Series IDs as of October 2011:  (Use Excel's Paste Special--text option to copy into the Asset Returns Worksheet.)

  1. CUUR0000SA0 - U.S. All items, 1982-84=100
  2. CUUR0000SA0L1E  - U.S. All Items Less Food and Energy
  3. CWUR0000SA0 Consumer Price Index - Urban Wage Earners and Clerical Workers
  4. CWUR0000SA0L1E - U.S. All Items Less Food and Energy, 1982-84=100

Considerations:

Related Topics:

Importing CSV Returns

You can import CSV files into the Estimator as asset return series or benchmark return series.   Remember that CSV files are limited and demand more from the application, which can lead to errors.  Please review imported CSV files carefully.

Preparing a CSV Return Series:

Importing a CSV Return Series

  1. Click on the Load Menu in the NFA ribbon.

  2. Select the Import CSV Return Series option from the Import sub-menu.  The Import ReturnSeries from CSV Window appears.

  3. Navigate to the saved file.

  4. Double click on the file, or click the Open button.

  5. Several warnings may appear about assets with the same name or dates that don't match.  You may need to adjust your file before trying again.

  6. Review the data on the Returns Worksheet.

  7. Ensure that the Estimator figured the period correctly.

See Saving Files for information on exporting return series as CSV files.

Bloomberg

The Estimator can import return data from Bloomberg if you have Bloomberg access.  

Setup your Bloomberg access by entering account information.  

  1. Access the Preferences Window by clicking on the Preferences button in the far left of the ribbon.  
  2. Click on the Bloomberg option to access the Bloomberg Tab.  
  3. Check the Enable Bloomberg Per Security Box.
  4. Enter your Bloomberg security information, contacting your IT department and Bloomberg as necessary.
  5. Click on the OK button.  The information you entered remains saved in Preferences until you change it.  
  6. If you have specific terminal information,

Import data

  1. Check that the desired assets, date range, and period appear.  (If not, either start a new return series or add the appropriate rows and columns.)  Click the Validate/Resize Button.
  2. Enter the appropriate BBGID Composites in the Asset Ticker row on the Asset Returns Worksheet.
  3. Ensure that your computer is connected to the internet.  
  4. Either import or update data.

    • The Import returns from online sources option within the Load drop down menu on the ribbon overwrites any data in the columns of recognized tickers.  

    • The Update returns from online sources option, also found within the Load drop down menu, only imports data to empty cells or cells that display "N/A".  It will not disturb previously entered returns, which is useful for appending data to previously vetted returns.

Data that cannot be imported or updated appears as "N/A".

Financial Modeling Prep (FMP)

The Estimator can import return data from Financial Modeling Prep (FMP) if you have access.  

Setup your FMP access by entering account information.  

  1. Access the Preferences Window by clicking on the Preferences button in the far left of the ribbon.  
  2. Click on the Misc Data Sources option.
  3. Enter your Financial Modeling Prep (FMP) API key, contacting your IT department and FMP as necessary.
  4. Click on the OK button.  The information you entered remains saved in Preferences until you change it.  

Import data

  1. Check that the desired assets, date range, and period appear.  (If not, either start a new return series or add the appropriate rows and columns.)  Click the Validate/Resize Button.
  2. Enter the appropriate Tickers in the Asset Ticker row on the Asset Returns Worksheet.
  3. Ensure that your computer is connected to the internet.  
  4. Either import or update data.

    • The Import returns from online sources option within the Load drop down menu on the ribbon overwrites any data in the columns of recognized tickers.  

    • The Update returns from online sources option, also found within the Load drop down menu, only imports data to empty cells or cells that display "N/A".  It will not disturb previously entered returns, which is useful for appending data to previously vetted returns.

Data that cannot be imported or updated appears as "N/A".

Loading

Click on the Load button in the File Menu to access the Load Data File Window. Navigate to select the desired file. Click the Open button. The file populates depending on file type.

Estimator files (*.nfei)

Estimator files contain Estimator cases.  All data entered to the Estimator when you saved the case populates when loaded.

Portfolio files (*.nfp)

A portfolio file stores the asset weights of a portfolio. Loading a portfolio into the Estimator replaces the market portfolio on the Historical Worksheet. Any assets in the portfolio that are not present in the active case are discarded, so use caution if there is a different investment universe in the saved file since the weights of the portfolio may sum to a different total than expected.  

Return Series Files (*.nfrs)

Return Series files contain up to 3000 return observations and corresponding dates. The Estimator can load return series prepared on the Asset Returns Worksheet. Alternately, you can import return series in CSV format or import returns from online sources.

Risk Return Set Files (*.nfrrs)

A risk-return set contains expected returns and standard deviations for a given set of assets, plus a full correlation matrix spanning the set. Loading one into an Estimator session replaces the data on the Forecasts Worksheet. Assets that are not included in the active case are discarded. Though the Estimator can save any of its three risk-return sets (historical, forecasts, or results), and you can load any of the three into the Optimizer, the Estimator loads all risk-return sets as forecasts.  

Benchmarks Return Series

A benchmark return series is a series of returns for a single or a composite asset.  The benchmark return series can be used for adjusting the historic return series by a standard.  This is an optional input, but if you use it, the benchmark return series acts as a baseline for measuring asset performance.  You must decide what to use.  Inflation and risk free assets are popular benchmarks, which is why the Estimator can import the Consumer Price Index from the Bureau of Labor Statistics as a benchmark.  Pension funds have been known to use their liability stream.  Using treasury bill returns is one way to achieve a risk free return series.  

 

Assets Wizard

The Assets Wizard provides functionality to select return series subsets and sort assets in the Estimator. Access the Assets Wizard by clicking the Assets button in the NFA ribbon.

Exclude/include an asset from the estimation by removing the checkmark from the row of boxes.  

Sort the assets by clicking on the column headings. For example, clicking on the Asset Name heading sorts the assets by name. This duplicates the sorting functionality found on the worksheets (double clicking on the Asset Name heading on the Historical Worksheet will also sort assets by name.) The difference is that here you can select an asset row and use the Move Up and Move Down Buttons to customize the sort. You can also save a particular sort by clicking on the Store Order Button. Clicking on the Restore Order Button at a later point will sort the assets according to that previous sort.

Forecasts

Forecasts reflect assumptions about assets' return distributions, derived from other sources than your historical data. They may come from current data, i. e. yield information for bonds, or from more generally held principles of finance. The forecasts described on this page are generally single-asset forecasts. For forecasts relating multiple assets to each other, use forecast contrasts.  Forecasts must include return and risk projections, but correlations are optional.  Alternately, a previously saved risk-return set can be loaded to the Forecasts Worksheet.  

Forecasts are combined with the historical data analysis when the Run Bayes button in the Estimator ribbon is clicked. The result combines the two signals with relative strengths determined by the standard deviations and correlations. Larger standard deviations indicate less certainty, and thus less strong of an influence in the result. Ignoring correlations for the moment, a forecast with an equal standard deviation to the historical standard deviation will produce a result mean (expected return) halfway between the historical return and the forecast return for that asset.

The input forecasts are used according to your further selections on the Forecasts Worksheet.

Forecast Contrasts

Displaying Forecast Contrasts

Display of forecast contrasts is toggled through the Display Menu.  When displayed, forecast contrast entry fields and intermediate result tables appear on the Forecasts Worksheet as well as on the Results Worksheet.  When forecast contrasts are hidden, they are disabled and do not impact the Estimator case.

 

You enter up to 50 contrasts.  Individual contrasts can be turned on or off by checking or unchecking the boxes on top of the column.  Contrasts are also considered off if they have no standard deviation or weights.  When they are on, they appear in a darker blue font.  When they are off, they appear in lighter blue font.  

 

The tops of the columns indicate how the contrast has been weighted.  If a contrast is weighted according to the market portfolio, the top of the column states "Market Weighted".  Similarly, the Estimator labels contrasts with equally weighted groups of assets as "Equal". If either of these labels appears, the contrast's weights will update automatically if the case changes (market portfolio changes, added asset, etc.).  If no label appears, the contrast has been weighted manually and it will not update automatically.

 

The Vanguard sample cases include sample contrasts to explore.

 

What Are Forecast Contrasts?

Forecast contrasts are forecasts for groups of assets that are applied to your assets along with any entered single asset forecasts when the Run Bayes button in the Estimator Ribbon is clicked.  

 

Forecast Contrasts provide a way to include investor views in an estimation process. These investor views are merged with historical information as well as any other forecast information to form the final estimates, which balance all information sources to give final estimates. Contrasts may be familiar to practitioners through the Black-Litterman procedure, and NFA’s implementation of contrast forecasts is entirely analogous to the “investor views” in that procedure.

 

When a view target (mean) differs from its corresponding historical prediction, a contrast will bend the estimator results towards that target. The strength of the view’s influence on the answer can be adjusted through the contrast standard deviation. Thus a vague view which is not tightly focused is assigned a large standard deviation and has a less pronounced effect on final estimates than a specifically focused, high-certainty view, which has a small standard deviation.

 

A complete specification of a contrast includes a portfolio (which may sum to 0% or 100%), a mean (target for the expected return of that portfolio), and a standard deviation, which controls the influence of the view on the result. Larger standard deviations signify less focus and less influence on the result.

 

Although contrast portfolios may legally sum to any number, it is fully general and simpler to consider only contrast portfolios that sum to zero or 100%, since contrast portfolios summing to any other number can be converted into another equivalent contrast with a portfolio summing to 100% by dividing portfolio, mean, and standard deviation by that sum.

 

Sum-to-zero contrasts are useful for comparing one asset, or basket of assets, to another single asset or basket. The portfolio weights can be broken into one sum-to-100% portfolio minus another. The contrast mean then represents the expected difference in returns, or expected premium of the positive portfolio over the negative one. The standard deviation controls the influence on the results.

 

Sum-to-100% contrasts are views on portfolios. A suitably weighted basket of assets is assigned an expected return and standard deviation.

 

Example: Global Market Forecast (Portfolio view: sum-to-100% contrast)

A manager might have information about which way the total market is headed, above and beyond what history tells us. A market-capitalization weighted portfolio would be assigned a target, e. g. somewhat more positive than the historical forecast, if a particularly good quarter is expected for the entire market. Standard deviation could be assigned to be equal to the historical estimate for the market portfolio, to influence the result roughly equally to history. If historical estimates are present, the NFA software displays the historical mean and standard deviation of the contrast portfolio, once entered, for reference.

 

Example: Risk Premium (Group difference view: sum-to-zero contrast)

A manager likely has personal outlooks on various risk premia. Risk factors have been an important subject of study for estimation in finance. To specify a particular risk premium, a basket would be chosen to represent those assets possessing the risk factor, and another basket representing assets without the factor. For example, for the size premium, baskets of small-cap equities and large cap equities can be created. The small assets would be assigned the positive weights of their basket, and the large assets would be assigned negative weights. The mean would target the actual target premium, and the standard deviation would be assigned relative to the historical standard deviation. The estimator results would then show a size premium (expected return of the contrast portfolio) pulled toward the contrast mean.

 

Entering Forecast Contrasts Manually

When forecast contrasts are displayed, one forecast contrast entry column appears on the Forecasts Worksheet.  

 

Equity Premium Example

One way to forecast an equity premium, where the bond weights sum to -100% and the equity weights sum to 100%, is to equally weight the bonds and weight the equities in proportion to their market weights.  Using this method, the contrast portfolio for the default sample case would be:

If you believe that the equity premium will be 8%, enter 8% as the mean. The historic mean for this portfolio is shown as 5.9% and the historic standard deviation is 13.7%. So, entering 8% as the standard deviation would represent a view which is relatively strong when compared to the historical information only. Indeed, with these settings the result mean is 7.5% and the contrast effect is 1.5%, moving the result mean from 6.0% to 7.5%.

 

The Vanguard data sample cases provide additional examples of forecast contrasts.

 

Contrasts Wizard

Click the Edit Contrast button on the ribbon. The Edit Contrasts Window appears. If you want to enter a view (forecast) on a single portfolio, click the Add Portfolio Forecast button.  A dialog window the opens with the complete list of available assets in the left pane. Use the Add and Remove buttons to move the desired assets into the Selected Assets Box.  Select either the Equal Weight or the Market Weight option. Fields then must be entered for the Mean (target value) and Standard Deviation (dispersion) for the contrast. For reference the historical mean and standard deviation of the chosen contrast are displayed. A name for the contrast can be added in the top field. Click the OK button. The contrast weight for the ith asset is then proportional to the market weight. In mathematical terms this is equal to (1iwi)/(Σj1jwj) where

 

A view (forecast) contrasting two portfolios can be entered by clicking on the Add Contrast Forecast button. A dialog appears with the list of available assets at the top center.  Add assets to a group by using the appropriate Add button. At least one asset must be on each side. Select either the Equal Weight or the Market Weight option.  Complete Forecast Mean (target value) and Forecast Standard Deviation (dispersion) Fields. Watch the sign of the forecast mean. The return of group A is forecast to exceed the return of group by the forecast mean. For reference the historical mean and standard deviation of the chosen contrast are displayed. A name for the contrast can be added in the top field. Click the OK button. The contrast weight for the ith asset is then proportional to the market weight within its portfolio. This is mathematically equal to (signiwi)/(Σj1sign j = sign iwj) where

 

Maintaining Contrasts

Market Portfolio

Purpose

The market portfolio acts as the reasonable prior referenced by the Estimator for several historic data adjustment methods, can be used to calculate forecast contrasts, and can be used to derive a benchmark return series.

 

Weighting

Depending on what the market portfolio will be used for, you may want to equal weight the market portfolio, enter capitalization weights, or weight the assets according to another criterion.  By default, the Estimator sets an equal weighted market portfolio.  

 

If you enter a specific weight for an asset, that weight shows on a white background.  The Estimator automatically equal weights the remaining assets in the portfolio, which show on a blue background, and leaves those you entered alone.  For you adjust the asset universe frequently, this removes the need to adjust the market portfolio every time as long as you’re content to have all or part of your market portfolio equally weighted.

 

Mechanics

Period

When you load a return series file or previous Estimator case, the Period Table on the Historical Worksheet populates according to the dates contained in the file.  The Period field beneath the columns displays the number of possible observations, missing or observed, in the period used by the return series.  Whether the frequency of the historical dataset is daily, monthly, quarterly, or annual, the Estimator produces annual estimates by annualizing return series according to a standard approximation: monthly returns multiplied by 12 and standard deviations multiplied by the square root of 12.  Other frequencies are handled similarly.  

 

Drop down menus beneath the From and To column headings on the Historical Worksheet display the beginning and ending dates for the estimation problem.  These columns populate automatically with the first date that appears in each asset's return series.  When return series start on different dates, the Period Field calculates from the oldest return observation, and the more recent dates appear in red.  Similarly, when return series end on different dates, the Period Field calculates to the most recent observation, and the older dates appear in red.  The Missing Data field on the Results Worksheet reads "Missing Data" when any missing data appears within the date range specified in the From and To columns.

                          Table 1                                                                                                   Table 2

 


In Table 1, several of the assets have returns stretching back to January of 1978.  The red dates indicate the earliest return observation for the remaining assets.  The Estimator calculates the period from January of 1978.  As you change the date in the From drop down menu, the dates and period change to reflect the newly selected date.  Table 2 shows the same assets, but with the From date adjusted to June of 1979.  Now all but one of the assets have observations, and the period is reduced to 199 months.

 

Longer return series provide more statistical reliability, as long as the entire period is relevant to the intended investment period for the model portfolios to be generated by the Optimizer.  Ideally, include several investment cycles for each asset.  Bear in mind that though the Missing Data Algorithm produces estimates in the presence of missing observations, its accuracy diminishes with larger percentages of incomplete data, particularly when the data is in sequence.  Examine your data to determine what period adjustments meet your needs and make sure there is enough relevant information in the dataset to produce adequately precise estimates.

Related Topics:

  • Running an Estimation Problem

  • Missing Data Algorithm

  • Return Series Files

  • Historical Worksheet

  • Results Worksheet




 

 

Series Adjustment Value

The Series Adjustment Value is a constant that can be used during Historic Data Adjustment.  The Value Field activates when the Benchmark Average or Adjust by Fixed Constant options are selected from the Series Adjustment drop down menu in the ribbon.  (The Benchmark Relative Option doesn't require a Series Adjustment Value.)

 

Risk Scaling Factor

The Risk scaling factor is turned off by default and can be enabled in the Display Menu. When first enabled, it shows a factor of 1.0 for each asset's standard deviation, meaning that no adjustments have been made to the result standard deviations.

Changing the value of a risk scaling factor means that the result Standard Deviation for the corresponding asset will be scaled according to the factor provided. This feature is provided as a convenience to include cases where an asset's standard deviation uses a different method to estimate its risk.

Normally it is not recommended to adjust the values of the risk scaling factor or the result standard deviations.

Asset Groups

Assets in the Estimator and Optimizer can be assigned to groups, such as stocks and bonds.

 

Display Groups

To display or hide fields pertaining to groups, select Asset Groupings in the Display Menu.

 

Assign and Add Groups

Assign groups on the Asset Returns Worksheet.  Add a new group by typing the name in one of the cells of the Asset Group row.  Once a group has been added to the list, you can select the appropriate group for each asset from the drop down menu.  For instance, in the default sample case, the assets are assigned as either a stock or a bond.  Those two options appear in the drop down menu when a cell in the Asset Groups row of the Asset Returns Worksheet is selected.  You can select either of those, or you could type in a third group name instead, which would make that group appear in the drop down menu.

 

Using Groups

After assigning each asset to a group, you can sort by groups in the Asset Selector.  Asset group assignment carries over to the Optimizer, where groups can be useful for applying constraints or selecting portfolios according to total weight ratios.  For example, you can find portfolios with specific stock/bond ratios if two of the groups are stocks and bonds. Group assignments will carry over to the Optimizer if the saved .nfei file is loaded in the Optimizer to transfer the inputs, if NFA Copy/Paste is used (and the Estimator and Optimizer are within the same instance of Excel), or if Launch is used. There are many ways in which groups are useful in the Optimizer. See the Optimizer documentation for further details.

Historic Data Adjustment

The historic data adjustment options provide a means to condition the risk and return estimations derived from the historic return series. The numerous statistical methods that can be applied are described below.

Return Estimation

Choose the appropriate option for estimating the historical returns from the Return Estimation drop down menu in the ribbon.

For further information on return estimation, consult these publications:

Stein Estimation:

Implied Returns:

Risk Estimation

Choose the appropriate option for calculating the historical standard deviations from the Risk Estimation drop down menu.

For further information on risk estimation, consult ther following references:

Series Adjustment

Series adjustment provides options for altering the return series according to constants or a benchmark. In order to use the Benchmark Relative and Benchmark Average Options, you must select a benchmark return series. This is most often used for inflation-adjustment by setting the CPI or something similar (see importing from outside sources). Choose the series adjustment from the Series Adjustment drop down menu.

After making your choices, click on the Run Estimator button. The Historical Worksheet and the Historical Table on the Results Worksheet populate with the results according to the selected options. You can alter the data that results from historical data adjustment as you desire, but New Frontier recommends special training. In particular, if you wish to enter your own correlations, contact New Frontier for guidance. Proceed to the Forecasts Worksheet to input forecasts as desired.  

Missing Data Algorithm

Return series may have gaps in the available time periods or varying start and end dates. For example, a small cap fund may not have as long a performance record as a large cap growth manager, or you may decide that a particular return observation is invalid due to error or accounting differences among time periods.  Missing data is marked by red "N/A"s on the Asset Returns Worksheet. When there are missing data within the period specified on the Historical Worksheet, "missing data" messages appear in the Historical Worksheet's Data field as well as the Missing Data field on the Results Worksheet.  The Estimator invokes the Missing Data Algorithm to extrapolate missing data (means, standard deviations, and correlations).

The Missing Data Algorithm makes several assumptions about the data. Missing data is said to be Missing Completely at Random (MCAR) when the probability that an observation is missing does not depend on any of the data. This is a strict assumption that is generally not valid for financial data series. Here we make a less strict assumption that the missing data are Missing at Random (MAR), which says that the probability that an observation is missing may depend on observed data from that time period, but not on the missing value itself. The algorithm in the NFA Estimator is valid for data missing at random. The MAR assumption says that the relationships in the observed data are preserved during periods of missing data, but that the missing periods may be somehow different from the observed periods. This is a much more plausible assumption for financial data than MCAR, which insists that missing data is identically distributed to the observed data.

Historically there have been several methods for estimation in the presence of missing data. The most naïve of these is to eliminate all records with missing data. This approach is referred to as the “complete case analysis". This approach will lead to biased estimates if the data are MAR but not MCAR, and may throw away much information. The obvious correction to this is to use the “available case analysis", in which means and standard deviations are estimated using all the observed data, and correlations are estimated using all jointly observed records for the asset pair in question. This approach may again lead to biased estimates for the mean when the data are correlated and MAR, and although estimates may be more precise, has the additional difficulty that the resulting covariance matrices often fail to be positive-semidefinite, and are thus invalid.  Another approach to estimation with missing data is commonly known as “hot deck imputation", in which missing records are filled in with other randomly chosen observations from the same asset. This again does not take advantage of the correlation structure among the variables.

 

The NFA missing data algorithm is a more sophisticated approach to estimation with missing data. A multivariate normal model is fit to the data using maximum likelihood techniques. The outputs of the maximum likelihood procedure are exactly the mean and covariance of the data. They are both adjusted for the missing data: the means are adjusted using information from the observed variables and the correlations, the variances are inflated to account for the uncertainty due to the missingness, and the correlations are consistently estimated given all the other information. When possible, the estimates are made in a closed form using a noniterative technique, which will yield the same results as the iterative Expectation-Maximization (EM) algorithm described below, but much more quickly.  However, the pattern of "missingness" must be monotone for it to be possible to use this closed form maximum likelihood technique.  “Monotonicity” means that each missing data pattern contains the previous one, i. e. is missing only for assets which are also missing in all subsequent patterns with more missing values. If the missing data patterns are more complex and nonmonotone, the Estimator employs the EM algorithm. This algorithm starts with initial estimates, and iteratively refines these estimates until convergence. It can be quite slow to converge when the fraction of missing information is large.

The missing data algorithm is meant to fill in small gaps in the data, and New Frontier does not recommend its use to fill in large stretches of data series. When large stretches are missing, we recommend attempting to find another data series to use as a proxy or changing the start and/or end dates of the analysis.  

References:

Little, R. J. A. & Rubin, D.B. 1987 Statistical Analysis with Missing Data. New York: Wiley.

Schafer, J. L. 1997 Analysis of Incomplete Multivariate Data. London: Chapman & Hall.

Dempster et al. 1977. "Maximum Likelihood Estimation from Incomplete Data via the EM Algorithm (with discussion)" Journal of the Royal Statistical  Society,  B39, 1-38.  

Forecast Data Adjustment

The Bayesian estimation methods included in the Estimator are statistical techniques that have been customized by NFA for financial situations. These particular Bayesian estimation methods are useful for including current forecasts, more generally held investor views, or any other quantifiable external information, in the Optimizer inputs. The content of this added information may differ significantly from estimates based on historical data.  

Different sources of information may vary in certainty or precision. For example, forecasted return uncertainty may be much greater for emerging markets than for long-term corporate bonds. The long-term corporate bonds forecast should thus have a stronger impact on the final estimates, since it is more precise. The forecast standard deviations provide a means of customizing the input estimation process to consider current information and levels of forecast certainty separately for each individual source of information.

Select how the input forecasts are used in the Bayes Forecasting drop down menu on the Forecasts Worksheet. If using forecasts and data in the analysis, which should be the normal state of affairs, the NFA Bayes option will be the final choice to create the result inputs for the Optimizer. The other options in this menu allow the user to examine the historical and forecast sides of the analysis separately.

The Run Bayes button causes the Estimator to calculate the results according to the choice in the Bayes Forecasting drop down menu. When the Forecast or Historic options are selected, all Run Bayes does is copy your forecasts to the Forecast Data Table on the Results Worksheet; the results are unaffected by any Bayes estimation. The NFA Bayes computation combines the historic and forecasts using specially designed advanced statistical methods. In all the methods, the resulting risk and return estimates populate the Results Table on the Results Worksheet.  

Because the NFA Bayes method uses the correlations with the historic and forecast returns, the results are not always intuitive. The forecasts with high confidence influence all of the results through the correlations. If the correlations dictate that two assets' returns rise and fall together, or move oppositely, the Estimator has to balance that relationship with the historic and forecast returns. For example, if you forecast a high return for Asset A with high confidence and a low return for Asset B with low confidence, but the correlations indicate that these two assets run in tandem, the resulting return for Asset B is likely to be high despite your forecast.

Moving to the Optimizer

The Optimizer is the central application of the Asset Allocation System. The inputs prepared in the Estimator are intended for use in the Optimizer. There are several ways to move information from the Estimator into the Optimizer. The necessary inputs for the Optimizer include the Means (Expected Returns), Standard Deviations (Risks), and Full Correlations.

Related Topics:

Reporting

The Reports button on the NFA ribbon opens the Reports Designer. The Reports Designer provides a list of prepared charts, tables, and paragraphs that can be used in generating a report. Start a report from scratch, or open a previously prepared template. Use the tools and elements described below to develop the correct report for you.

Report Format:

Choose the format of the resulting report from the Report Format drop down menu. The Reporter can generate both Word documents and PowerPoint presentations. However, once you begin to prepare a report, switching between PowerPoint and Word destroys any formatting, such as page breaks, that you may have set.

Within the PowerPoint format, you can set the background of your PowerPoint report by instructing the Reports Designer to use the master slides of another presentation.  

Report Elements provided by NFA:

For users who have used previous versions of the Reporter, don't be confused if your User Defined Report Sections Box populates with a different list than the one above. The User Defined Report Sections Box populates with the report elements that you imported and saved while using the previous version. This feature protects the material you may have edited in the Reports Designer previously (master slides and user defined report elements).  Sections prepared by NFA can be imported into Reports Designer from C:\Program Files\NewFrontier\8.x\reports (or wherever you installed the Asset Allocation System) using the importing tool described below. Until these elements have been imported, you will be unable to access them or use them in templates.

Reporting Tools:

Saving Files

Please note that options and settings that affect the results of a case are always stored with the corresponding case file. Other options, such as display options, are stored locally for each user.

Click the Save button on the NFA ribbon to access the Save Data File Window. Select the appropriate file type in the Save As Type drop down menu. The Estimator generates the following file types:

 

Estimator data set (*.nfei)

a complete Estimator case
Estimator data sets can be loaded by the Estimator for future use. They also can be loaded to the Optimizer as optimization inputs. Be aware that any notes entered in the light orange boxes at the bottom of the Historical, Forecasts, and Results Worksheets will not save.

Return series (*.nfrs)

historical return information for one or more assets
benchmark return series or historical returns of every asset in the case

Portfolio (*.nfp)

market portfolio weights

 

Risk-Return Set (*.nfrrs)

expected returns and standard deviations for a given set of assets with a full correlation matrix
Each Estimator case contains three risk-return sets (historical, forecasts, and results), any of which can be saved.

The Estimator contains the ability to export CSV files of the historical returns or benchmark return series. Select the Export Return Series Option from the File menu. The Export ReturnSeries to CSV Window appears. Select the file name and destination. Click the Save Button. The Choose Return Series Window appears. Select either the historical asset returns, the benchmark return series, or the complete return universe. The complete return universe includes the benchmark and assets that have been excluded in the Asset Selector. The data saves as a CSV file. Be aware that CSV files do not contain asset descriptions. If you want to include that information, use a *.nfrs.

To save in Excel, activate the Excel File ribbon and use the saving options there. If you have enabled the Warn Before Attempting to Save in Excel Option in the Preferences Window, a ConfirmDialog Window appears. Though saving in Excel is supported, there are several limitations. First, future versions of the Estimator may not open the case correctly. Second, cases saved in Excel contain only what is included on the Inputs Worksheet. Any assets currently removed from the investment universe in the Asset Selector do not save in Excel cases.  

Copying and Pasting

For the most part, copying and pasting behaves as you would expect it to in Excel. However, there is a difference between the normal Excel tools and the NFA tools.  

The Copy function in the Edit Section of the ribbon copies the entire case -- all  information in the Estimator at the time, onto a clipboard. This information can be pasted into another Estimator session by using the NFA Paste option, as long as you are within a single instance of Excel. You can also copy the Estimator case into an Optimizer case within the same Excel instance. Launching creates a clean Optimizer case, so if you wish to use an Optimizer case that already contains constraints and reference portfolios, NFA copy/paste is a better choice. To copy and paste the entire case to an Optimizer in a different instance of Excel, save the Estimator case as a .nfei file and load from the Optimizer. This has the same effect as using NFA copy/paste.

To copy a section of the case, utilize Excel's copy and paste functions. The Excel copy function can also be used to copy portfolios or other data into a blank Excel Spreadsheet for comparison purposes.  

Multiple and Partial Correlations

In addition to Optimizer Inputs (Mean, Standard Deviations, and Correlations), the Estimator calculates estimates of Multiple and Partial Correlations, which can be viewed in the Results Worksheet. These statistics provide more information about the relationships between asset pairs and the ensemble of assets as a whole, and can be used when considering including or excluding assets based on their risk characteristics.

Mutiple Correlations show the joint correlation of each assets with all of the other assets. It is equal to the square root of the R-squared statistic from Multiple Regression, which shows the strength of the relationship between a variable and its best prediction based on all of the other variables, or the proportion of the variance explained by the other variables. Therefore, assets with low multiple correlation scores are less well explained by the other variables in the case, and providing more unique signal to the case. Assets with values of multiple correlation close to 1.0 (or -1.0) will provide less in the way of risk reduction to the case.

Mathematically, the multiple correlation for an asset can be computed from the correlation matrix. It is computed as the square root of the triple matrix product of the row vector of correlations between that asset and the other assets, times the inverse of the correlation matrix of the other assets, times the column vector of the correlations between the asset and the other assets.

The multiple correlations can be found in a column to the right of the Means and Standard Deviations on the Results Worksheet. 

The partial correlation matrix can be viewed by toggling the drop-down at the top of the correlations on the Results Worksheet, all the way to the right. By default this drop-down is set to display the full correlations. 

Partial correlations show the strength of the linear relationship between a pair of assets in the presence of all of the other assets. Equivalently, the statistic measures the correlation between the residuals of two regressions, where each of the two assets is regressed against the other assets (than the pair). Partial correlations show what remains after eliminating the relations due to common relationships with other assets. Note that these calculated statistics are for informational purposes only, and not suitable for use as Optimizer inputs.

Asset Correlations

The Asset Correlations Chart displays the correlation between the returns of the two selected assets over the selected date range.  A best fit trend line (using the ordinary least squares method) is superimposed.

Asset Ranges

The Asset Ranges Chart displays the resulting return variation of each asset in a bar whisker chart.  Marks appear at one and two standard deviations from the estimated return.

Assets Risk and Return

This chart shows the results, each asset's estimated risk and return, as a scatter plot in mean-variance space, i. e. the horizontal axis is standard deviation and the vertical axis is expected return.  The Results Table on the Results Worksheet provides the exact numbers.

Growth of Asset(s)

The Growth of Asset Chart and the Growth of Assets Chart both display the cumulative historical growth of assets over the selected date range.  A baseline value of 1.0 is applied.  The first chart displays the growth of one asset.  The second compares the growth of two selected assets.

Histogram

The histogram displays the frequencies of returns for an asset during the set range.  It allows you to approximate the probability density function (distribution) of the data and assess its normality.  You can adjust the date range, either by date or by number of periods, and the number of bins in the histogram.  The horizontal axis marks the midpoints of the bins.

Historical Returns

The Historical Returns Chart displays the returns of the selected asset over the designated date range.

Rolling Correlations

The Rolling Correlations Chart displays the rolling correlation between the returns of the two selected assets over the selected date range.  Adjust the number of observations included correlation calculation in the Number of Rolling Periods Field.  For example, if you enter "24" in the Number of Rolling Periods Field for a case using monthly data, the Estimator finds the correlations from two years prior to the end date until the end date.

Error Handling

An error message appears when the Estimator notices an incongruity. These are exceedingly rare in the Estimator.  

If an error message appears and the cause of the error is not immediately apparent, click the More Information button. A more thorough description appears. Some of the less common errors may have less complete descriptions. You may also find it useful to review topics in this help manual.

Common error resolutions:

Check our website for frequently asked questions and support.  (Client login required.)  

The Copy to Clipboard Button on the error message window can help you report the error to NFA. Clicking that button copies the text of the error message into your clipboard, so you can easily paste into an email message. In order to provide version information as part of a support request, click on the Copy to Clipboard button on the About Window, accessed by clicking on the logo in the top left hand corner of the application.

Troubleshooting Tools

Several troubleshooting tools appear in Windows Start Menu, NFA Asset Allocation System folder.

Launch Preferences brings you to the Preferences Window.  Within the Preferences Menu, you can:

HASP Key Firmware Upgrade updates the firmware if necessary. This should be unnecessary for most users.  Make sure that your HASP key is attached to the computer before applying.  

Use the NFA Key Updater to request and receive updates to the license on your HASP key.   

  1. The Sentinel HASP RUS Window appears.   
  2. Select the Collect Key Status Info tab.  
  3. Click the Collect Information button.  The Save Key Status As window appears.  
  4. Change the file destination as desired; the default is the Desktop.  Assign a name to the file (*.c2v).  Click the Save button.  
  5. A status message appears on the Collect Key Status Info tab.  If successful, the file appears at the designated file destination.  E-mail the file to licensing@newfrontieradvisors.com.
  6. When NFA replies with a HASP update file (*.v2c), save the file to the Desktop or another folder.  (We recommend that you don't use Outlook Web Access to download the file).  
  7. Right click on the file.  Select the Update NFA HASP Key option. The Sentinel HASP RUS Window appears with the file name in the Update File field of the Apply License File tab.  
  8. Click the Apply Update button.  

System Information opens the System Information application that contains information about your computer that will enable you to answer questions from support personnel. The buttons at the bottom of the window allow you to copy the data or e-mail it directly to New Frontier.  

Debugging Log

NFA may ask you to prepare a debugging log as part of a support operation. If NFA requests a debugging log, it can be created through the Preferences Window. Select the Debug Tab. Check the Enable Debugging Box. The rest of the window activates. Enter the folders in which you want to save the debugging logs.

Alternately, debugging can also be enabled through the main Start Menu.

Known Issues

When you ask the application to identify available cores in preferences, the "best settings for my computer", your computer selects the number that are currently available, which can change within seconds. This means that depending on when the application checks the preferences, your computer could be running on fewer cores than are available. If you have a multi-core machine, we recommend entering your number of physical cores manually on the same tab in preferences. (Internal Reference # 9366)

Double clicking or triple clicking on a button on the ribbon causes the operation to run two or three times. To avoid this problem, use a single click. (Internal Reference # 9349)

The Asset Allocation System is incompatible with Bloomberg Excel Tools v.3 build 6284. When this add-in is enabled, the Asset Allocation System will start to open before crashing without an error message. The solution is to disable the Bloomberg Excel Tools add-in.

 

Add-In Not Loaded

  1. When the NFA add-in does not load, first check to see if the New Frontier add-in is disabled.

    • Access the File menu on the ribbon.  

    • Click on the Options option at the bottom of the list to the left. The Excel Options Window appears.

    • Click on the Add-Ins option at the bottom of the list to the left.  

    • Select Disabled Items in the Manage drop down menu at the bottom of the window.  

    • Click the Go Button.  

    • Select any New Frontier items that appear in the Disabled Items Window.  

    • Click the Enable Button.  

    • Close all Excel windows.  

    • Launch the application.

  2. If New Frontier add-ins did not appear in the disabled items list, try closing and restarting the application.

  3. If restarting the application does not work, try rebooting the computer.

  4. If you got the add-in not loaded error immediately after installing version 8.x and rebooting didn't fix the problem, try a repair.  This option is found in your program list, usually right next to the uninstall option.  Restart your computer before trying to open the application.

  5. If you got the add-in not loaded area immediately after installing version 8.x and repairing didn't fix the problem, uninstall and reinstall the software.  Restart your computer before trying to open the application.

  6. If the problem persists, contact New Frontier at support@newfrontieradvisors.com.