#### Q: When performing an analysis using Taylor Series methods, how does AM deal with single PSU's in a STRATA?

A: When you have a single PSU in a stratum, you cannot calculate the within-stratum variance. We use the heuristic approach of assuming that the within-stratum mean is the same as the overall mean, enabling AM to make the calucation.

#### Q: Hello, I have found this software to be very easy and self-explanatory to use with the NELS:88 data set. However, I can not figure out how to (1)generate a bivariate correlation matrix with multiple variables and (2) how to generate output of statistical significance of bivariate correlations. I have been able to generate simple bivariate correlations one at a time, but without any test of probability. Since NELS data is weighted, SPSS tests of stat, significance become worthless. Can AM do these two procedures? Thanks.

A: To get a matrix of bivariate correlations you select "correlations" from the statistics|basic statistics menu. Drag multiple variables into the dependent variable box, and you will get a matrix of correlations among these variables. In this procedure independent variables define subgroups, and correlations are reported within each subgroup.

The correlations procedure does not currently produce standard errors or significance tests. I know that it is inconvenient, but running a bivariate regression will give you the same significance test. I suggest the following approach:

1. run a correlation matrix.
2. Identify the bivariate correlations of interest (say, between x and y)
3. select statistics|basic statistics|robust regression
4. make y your dependent variable and x your independent variable, and appropriately specify the weight, strata identifier and cluster identifier
5. press go.
6. repeat for all pairs of variables of interest

Please note: the latest version available on the web allows you to copy, modify and re-run an analysis. Right click on the completed run icon for this option.

#### Q: At the NCES SASS training this summer, they said that AM isn't yet prepared to use BRR. Is that still the case? I've downloaded the software and read the documentation, but I can't tell.

A: AM Currently supports balanced repeated replication and several jackknife replication methods. please see the documentation.

#### Q: -I am performing plausible values regressions for each literacy domain (prose, document, and quantitative) using the 65 or older subsample from 1992 NALS dataset. My three predictor variables are dage, education (dummy coded), and drace (dummy coded). I have used the "final weight" as my weighting variable. -I am going to use my prediction equation to estimate literacy in another large, nationally representative dataset and test some relationships between literacy and healthcare utilization. -Should I, and if so is it possible to, use the replicate weights in a plausible values regression? It seem as though the plausible values regression can only handle one weighting variable and thus the final weight is the best choice. If I do not use the replicate weights, is the error associated with my estimate of predicted literacy proficiency accurate?

A: The plausible values procedures, as with most procedures in AM, use a variance estimator based on a Taylor-series approximation of the sampling error. The estimates are as good as the jackknife estimates based on replicate weights. If specified correctly, your standard errors will be right.

The Taylor series estimates require that you specify the variable identifying sampling strata and the variable identifying primary sampling units in addition to the weight variable. In the NALS data set, these variables are named TSLVSTR and TSLVPSU, respectively. You must also specify the weight varialbe, which is named NFLWGHT.

If you right click on these variables (one at a time) and select "Edit Metadata", you will be offered a chance to specify the "design role" of the variable. This allows you to set the default weight, strata, and cluster identifiers, which will be automatically included in each analysis, unless you specify otherwise. You must save the dataset to make these changes persist across sessions.

#### Q: I have a small dataset from the NELS:88 N4P data file. I ran several crosstabs with the appropriate weight, strata and cluster. The output for one of my crosstabs reported the ns but had zero values for the proportion and se. My crosstab was gender (column) and race and college attendance (rows). The first time I ran the crosstab it ran fine. What happened here? Thank you for your support.

A: This is a bug in the copy and re-run option. It has been fixed in beta version 0.04.4, which is dated October 25, 2002. It will be published to the website by October 28.

#### Q: I'd like to get a very simple x-tab, with standard errors, in the same operation, with the row variables: Men Women Everybody My input variable is called COMPSEX, and has 2 values. I tried to create a new variable with 3 values, and was rejected. The collapsing strategy obviously doesn't work. I'll keep trying, but in the meantime, has anybody got any ideas?

A: Currently, AM tables procedures do not produce marginal estimates in the same run as cross-tabs. You can accomplish this by doing two separate runs--first do a run with no crossing variables, then do a run with the crossing variables that you want.

If you want to make sure that the runs are all based on the same data (missing data might cause values to be omitted) you can do the cross-tab first--then, from the Completed Run Queue, right click on the run icon and select "Create Sample Indicator." This will add a variable to your database that takes on a value of 1 if the observation was used in the crosstab. You can then filter the data based on this variable.

#### Q: I assume I am correct that a new variable cannot be created from more than 1 existing variable in a SAS transport file, right? I would like to create a variable in a cascade that involves reference to (1) the number of undergraduate credits earned, and (2) highest degree earned. The 2 variables are called TCREDB and HDEG. The new variable would be called CREDRET This is the way the SAS cascade would look: if hdeg>3 then CREDRET=1; else if hdeg=3 then CREDRET=2; else if (tcredb=>60 and hdeg=1) then CREDRET=3; else if hdeg=2 then CREDRET=4; else if (29 if (10 if (0<=tcredb<=10 and hdeg=1) then CREDRET=7; Again, am I correct that nothing like this could be done in AM?

A: You can do this. In the new variable dialog, put in a variable name and label. For the definition, write code that looks like the following (I've done your first three categories as an example):

1*(hdeg > 3) + 2*(hdeg=3) + 3*((tcredb>=60)*(hdeg=1))

...and so forth. Remember, the conditional statements evaluate to 1 if true and zero otherwise, so multiplication of two conditions is the same as AND and addition is the same as OR.

#### Q: Last summer, I attended the NAEP seminar in Potomac. At the seminar, you demonstrated a few analyses by using the NAEP 2000 CD. My question is: After importing the data from SPSS to AM, we edit metadata. In particular, ORIGWT is converted to a WEIGHT variable; REGRP1 is converted to a strata variable, and SCRPSU is converted to a cluster variable. (This process is valid for NAEP 2000 data) However, when I want to run statistics on NAEP 1992 data, I cannot see the REGRP1 variable to convert to a strata variable. Only, ORIGWT and SCRPSU are available when I am editing metadata. So, does it mean that I do not need a strata variable for NAEP 1992 data set? Thanks...

A: The 1992 data have the following variables:

1. JKPAIR, which is the strata identifier

2. JKUNIT, which identifies the pseudo-PSU (cluster variable).

You should use these along with the weight variable for your analyses.

#### Q: I have two questions: 1) I ran several correlations. My output displays the coefficients but not the p-values. How do I get the p-values displayed? 2) I am using NELS:88. I assigned the following proposeties: school id as the cluster variable, strataid as strata, and f3pnlwt as weight. I did not normalize the weight. Should I? My output shows that my analysis is being weighted up to the population. The sample size is in the millions. Am I doing something wrong. Thank you for your assistance.

A: 1. AM does not currently provide significance tests for bivariate correlations. However, if you want a test of the significance of the correlation between two variables, you can run a bivariate regression and check the significance of the coefficient of the predictor variable.

2. When you use weights for most datasets they weight up to the population. The weighted N then represents an estimate of the population size, rather than a sample size. The standard errors and significance tests are all appropriate, so there is no reason to "normalize" the weights. Nothing that you are doing is wrong.

#### Q: Is there any alternative way we can use AM to do chi test? Say, in NSOPF: 99. I have two gender groups: male and female, and want to investigate if there is any gender difference between their use of technology, which are collapsed into 4 groups, use website and email both, use website, use email, use neither of them.Thanks a lot.

A: AM does not currently do chi-square tests. I plan on adding these capabilities to a release that will come out over the summer.

A: It sounds as though you are trying to download the patch, rather than the main system. I realize that the website is not that clear on this issue. You should click on the computer, and it will download a file of approximately 10 megs.

Please let us know if this does not work.

#### Q: I wanted to use this software for conducting probit analysis but I have beenunable to as I could not import the data. The reason was that it supports data from commercial softwares only(like spss and SAS. If there is some method by which I can use my tab delimited notepad file for making the program understand my data I will be able to use it. Kindly guide me accordingly.

A: You can import data from a fixed-format ascii file. Fixed-format means that all the variables are always in the same column. To import, you will need a dictionary file and your data file. The syntax for the dictionary file is in the help system under Getting Started.

At a minimum the dictionary file requires the following information:

FILE = "filename" (put the real path and name of your files here)

VARIABLES

name1 1-2 type=r
name2 3-3 type=b
(names should be the name of your variable, next give the start and end columns, and type should be "b" if the variable is an integer in the range of -126 - 126, and "r" otherwise. You can also add variable labels, formats and other information. Please see the help system)

#### Q: Several.. When first trying to run a regression model from NELS:88 SPSS data, I got the message "gaussj-singular matrix-2. the data will not support est. of this model"> Then I tried to run a correlation matrix and got the message "maximul levels exceeded"> Then when I tried to run simple frequencies or a simple two-variable regression, it seemed to run, it went to netscape, but my computer freezes and I get no output. I downloaded the software with MS explorer but my default browser is Netscape. I don't know if that is related to the problem of not getting output.

A: 1. The singular matrix message is valid. You probably had variables that were perfect linear combinations of one another. For example, if you put in three dummy variables from a variable that had three levels, plus a constant, the sum of the dummy variables would equal the constant.

2. The error message is valid. All of the variables that you would like to correlate should go in the dependent variables box. The independent variables should be grouping variables,and you will get separate variance matrices for each group. I believe that the maximum number of groups is currently set to 50.

3. I assume that you are using netscape 7. That automatically uses a different java plugin than the one that installs with AM. We will have a fix out soon, but in the mean time, you should use internet explorer (my apologies).

#### Q: I know that AM is used with large scale assessments and surveys in education, but can I also use it for other data-sets with complex sampling designs like the NHIS(national health interview survey)? Any information you could provide would be greatly appreciated.

A: absolutely. You use it with health datasets as you would any other dataset. If you have any specific questions about how to do this, please feel free to e-mail them to me.

#### Q: Dear support team, How can I run 2PL Model, on the dataset which is currently stored in SPSS? In other words:do you have any examples of IRM (or any other)sequence, that can calculate item parametrs rather than encode existing parametrs?

A: The released version of AM does not estimate IRT models, so you should use Conquest, Parscale, Multilog, or one of the others for now.

We are currently testing an IRT model, which should become available this fall.

#### Q: 1. In SPSS, log likelihood decreases as more predictor variables are added (logistic regression). Does log likelihood in AM play the same role? What is the use of the one log likelihood figure shown in AM logistic regression output? 2. SPSS (logistic regression) computes odds ratios for all independent variables. Does AM do the same? 3. Why does AM use z-statistics instead of t statistics? Thank you very much for your help.

A: 1. The log likelihood increases as more predictor variables are added, in both SPSS and AM. AM does not currently report the beginning log likelihood statistics (associated with the null model that includes only an intercept). The single figure is used only for comparisons across models. However, most data does not use a simple random sample, so the log likelihood (from either AM or SPSS) is of little use in testing model specifications.

2. AM does not output odds ratios, though they are a simple transformation of the coefficient estimates. If you want them, output to a spreadsheet and do the calculations there.

3. All results from complex samples are based on asymptotic theory, and are valid for large samples. AM reports z-statistics for this reason. In SPSS the t-statistics are not correct if the sample is complex (i.e., unequal probablity of selection, stratified, or weighted)

#### Q: I normally work with a laptop that has network and internet access. When I tried to run AM on the laptop in stand-alone mode, I got the following error message: "Unable to Set Socket Snd Timeout." and then AM stopped responding. I suspect it is related to launching IE for the web browser output. Is there something I need to change in my IE settings for AM to work in stand-alone mode? Thanks for your help. I like your software!

A: This problem can occur with the Windows 98 operating system (I don't know about older ones).

If the user is disconnected from the network, but retains their network configuration, the operating system thinks it is still attached to a network. AM tries to talk to the output browser through a socket, and the system stalls out waiting.

To fix the problem, go to the operating system and get a command line. Then type:

ipconfig /release

When you reconnect to the network, run

ipconfig /renew

#### Q: I saved the Web browser output that displayed on the screen after running an AM procedure as an .htm file using file\save as, but the .htm file doesn't open in Excel. The only thing that displays when I attempt to open the file in Excel is "This web page uses frames, but your browser doesn't support them." The .htm file opens in Word and Windows Explorer with no problem. The .htm files that AM automatically creates after a run do open in Excel with no problem, but whenever I save the displayed screen output from a run as an .htm file myself, it doesn't. Should that be the case?

A: Unfortunately, that is currently the case. The output system uses frames-it has a simple java program in the top frame (the one with the AM logo). When you save the output, it saves the page that indicates the frames. Anything opening it needs to be "smart" enough to go find the frames.

Fortunately, there is a simple solution. At the beginning of each session, set your output file by selecting "Results | Web Browser Output |Select File" before you start analysis. All output wil go to the file that you specify, and that file does not use frame--it's just the output.

If you forget to do this, you can specify the output file at any time, then go to the Completed Run window, right click on any runs you'd like output from, and select "Results". The results will be written to the newly designated output file and will be displayed.

#### Q: I ran regressions using the NELS:88 dataset, and in several of my results tables, the standard error and z score columns listed "-1.#IO" and the p>z column listed "-1.#QO". Are these errors or notations meaning something specific? Thanks!

A: This means that the standard errors could not be estimated, most likey because of perfect collinearities in the model. The most common error that causes this is creating a set of dummy variables, and including all the dummy variables plus a constant term in the model. When you do this, the sum of the dummy variables equals one (because one of them is always equal to one, so the sum always equals one). Try eliminating one of the dummy variables.

#### Q: 1. Multinomial regression (Generalized)window has two sections for predictor variables -a section for independent variables and another one for variance predictors. What is the difference between the two sections? 2. Does AM show variance explained when using logistic regression? Thanks.

A: 1. Normally, a multinomial logit model assumes that equal variance across subjects. However, in a choice model, some people may be better informed than others. Hence, we would expect their choices to be more predictable than their less-informed counterparts. The variance predictors allows you to model this.

2. While I know that some packages offer various measures of explained variance for ordinal variable models, I never quite understood why. The variance of a continuous variable carries some information, but for a binary or ordinal one it does not. We will at some point introduce some measure of the extent to which the model reduces prediction error, but we have not yet.

(Sorry for the delayed response. I was unable to check the site for questions over the weekend because the hurricane took out my power)

#### Q: Is there something equivalent to SPSS's EXAMINE command? I want to get standard deviations and means for all the variables in an analysis I am doing, but only for the cases included in that analysis.

A: yes there is, and it is quite easy to do. Run the analysis of interest. Right click on the Completed Run Icon. One of your choices is Create Sample Indicator. When you select that, you will be prompted for a variable name to hold an dummy variable, which will take on a value of one for those cases that were included in the analysis.

You can then set a filter (select Data | Filter Observations) to limit analyses to that subset. Suppose you named your sample indicator FOO. the expression that you would type into the filter window would be (FOO=1). The filter will persist for all analyses until you clear it or close the dataset.

A: Test

#### Q: I did a General Import and got the data file, called CrosstabX, into AM. The name of the table and the variables appeared on screen. I double clicked on the name of the table and got a "select * from CrosstabX." I clicked "OK." However, unlike the previous times, the data did not make the transition to the next screen, the one that allows the user to do statistics, graphics, etc. The screen was blank, and the statistics function told me that it had no data to work with. I'm baffled, because I can't figure out why it worked the last time and not this time. The database is attached. In an effort to make it work better, I took out the column headings -- Case ID, Sex, Weight, Height. Can you figure out what I'm doing wrong? It may be something obvious.

A: your database specified all fields as text fields, rather than Numeric. AM does not yet support text variables, and simply skips them when importing. Therefore, it effectively imports a dataset with no variables.

You can fix this problem by changing the field type to numeric in Access's "design view"

#### Q: Hi: I just installed the AM Software and the data transfer addendum to the software. My browser cannot open the documentation. Any suggestions? thanks

A: The documentation (and browser output system) requires that the Java plugin successfully install with the software. For users of Windows NT, 2000, and XP, this will require administrative privileges.

If you do not have administrative privileges on your machine, the java plugin will not install and the neither the help nor browser output will work.

The solution to this problem is to have a system administrator reinstall the software for you.

If this is not the problem, or if this does not solve the problem, please e-mail me and we will sort this out.

#### Q: Hi, I just downloaded the Program and wanted to take a look at the manual realizing that you have an online manual. Do you also have a downloadable manual, such as a PDF file etc.? Thanks

A: The manual that is online is also downloaded and installed when you install the program. Open AM and press F1--this will bring up the manual in your browser.

Also, note that the manual is the context-sensitive help system, so if you press F1 while a dialog box is open or a menu item highlighted, the manual will open to the relevant page.

We had a user's manual that is now out of date. please let me know if you'd like a copy--it might be of some help getting started. You can send an e-mail to am.air.org to request it.

#### Q: I am working with the NELS:88 data and have specified the correct psu, strata, and weight. I am confused about how degrees of freedom are computed for regression (and logistic regression) analyses using the Basic Statistics options in AM. Please help me understand the denominator degrees of freedom for the Adjusted Wald test of model fit (which are given) and the degrees of freedom for t statistics associated with partial regression coefficients. Thanks.

A: The denominator degrees of freedom in the (adjusted) Wald tests are calculated as the number of PSUs (clusters) less the number of strata (unless a stratum has a single PSU), less the number of regressors.

Please see the Help system for more discussion. When the dialog box is open to do a Wald test, press F1 for help on the Wald test. You might be particularly interested in the "Details" page. The references page provides some helpful citations.

#### Q: I have been using the AM software to determine standard errors and it works fine to create frequency tables. However, I also would like to determine the standard errors for the count, not just the percent, frequency. Is there a way to do this with AM? Thanks in advance for your help.

A: Yes. After you run the frequency table, right click on the completed run icon in the completed run queue. One of your options will be "show totals." Click that and you will get a table of totals rather than percents.

#### Q: I'm trying to analyze NELS 88 data using AM. In ECBW, I created a tag file of 4 variables and output it as a Microsoft Access file. It actually came out in text (.txt), and I deleted the first line, which contained both alpha and numeric characters. Then I imported the text file into Access. Using Design View, I named each of the columns. Then I imported the Access file into AM. Things seemed to be going well. The AM screen showed the table and each of six variables (4 substantive and 2 IDs). I double clicked on the table name and got "select * from NELstudentX." However, when I entered this command, only the first of the six variable names appeared on the screen – the Access automatic ID number. To see whether the system would work with this variable, I ran descriptive statistics on it and got the right results. So the question is, why won't AM obey the command to select all six of the variables in the table? What should I do?

A: the problem occurs because the access fields are defined as text fields. AM does not currently support text fields. You can fix the problem by going into the design view and changing each field from "text" to "numeric"

#### Q: I see that the facility to create NALS tables using cutpoints between levels is available only through the MML procedures, not when using plausible values. I had a request today from a NAdLitS user for such a capability. Would it be a lot of work to add this feature to the plausible values statistical procedures?

A: We can add that feature in the next version. In the mean time, it is simple enough to create dummy variables that take on a value of 1 if the respondent is in the literacy level, and zero otherwise. If you do this for each plausible value, you can run the plausible values means procedure.

#### Q: I've installed AM software and imported a NELS data file from SPSS. The variable list looks correct. Now I am trying to run a statistical procedure. For example, when I click on "Frequencies" I can add a variable to columns and a variable to rows, but I'm not able to add anything to any of the other fields except "title". When I click "ok" I get a message, "1 dependent variable is required." What am I doing wrong? Also -- for some reason, the help manual is not loading. thanks for your help.

A: The dependent variable in the frequency procedure is the column variable. You must specify a column variable.

For the weight, strata, and cluster fields, you must drag and drop them.

Alternatively, you can right click on the appropriate variable in the variable list, and select "Edit Metadata." Fill in the appropriate "Design role." For example, right click on the weight variable and select "weight" for the design role. These will then load automatically when the statistical procedure dialog comes up.

About the help (and output) system: You must have administrator rights on your machine when you install it. The problem may occur because the java plugin (which requires administrative rights) did not install correctly.

#### Q: I just downloaded the 6.0 Beta to a new computer at ED. When I went to import, the drop-down did NOT offer a SAS.xpt option. Previous versions of AM did. I can't work without it. What gives? How do I get it? I need an answere ASAP or I have to go home and do the work there. Thanks.

A: we have improved the import capability. you must also download the DFTransfer component. Then, you will be able to import both .xpt and native SAS (.sas7dat) files, along with 150 other file formats (pretty cool, huh?)

#### Q: I have got two questions with regard to the use of the AM package (in both cases I thought the answer is NO but I would like to confirm): 1. Could one use estimate logit models with plausible values as outcome variables? 2. Could one do the above or do regression models by groups, say by countries (I would like to analyse the PIRLS data and this feature would be quite helpful if it is available). Many thanks. am interested in using the AM software to analyse the PIRLS data, which include 30-some countries. I wonder whether I could run the regression models

A: The answer to the first question is no, not directly. I may add that capability in the next release if there seems to be call for it. You could obtain the estimate by running the logit separately five times, and combining the results as described in the PIRLS technical manual.

To run regression models separately by groups, you currently have to set a filter to select one country at a time, and run the model separately for each country.

As an aside, you may be interested in the Demonstration site for our new on-line analysis too, AIR Lighthouse. The sample site (http://lighthouse.air.org/timss) gives you the ability to analyze TIMSS and PIRLS data, and will give you separate analyses by country without any real effort.

#### Q: I have tried to do MNL analysis,unfortunaltey the program didn't run. It keeps asking "2Replicate weights variables are required" and I don't know what I should do. I couldn't even fill/type anything on the 'weight' form. Could you please also explain what is JK2, JK1, BRR and FAY options in the Replication Method? and what will be the impact on my analysis? If I have a GENDER variable which input is 1=male and 0=female, how can I use this in my analysis? Thank you so much for your kind attention.

A: The multinomial logit procedure appears on the menu with two variance estimation options: one using replication methods, the other using a taylor-series method (under Basic Statistics). The appropriate choice depends on the data set that you are analyzing.

- If your data set includes replicate weights, you should probably use a replication procedure.
- If your data set includes strata and PSU identifiers, you should probably use a Taylor-series method
- If your data set has neither, you probably have a simple random sample, or a data set that was not properly constructed. If the sample was drawn as a simple random sample (possibly with unequal weights), you can use the Taylor-series procedures.

You can specify the weights in one of two ways:
1. Drag them into the appropriate box from the variable list; or
2. right click on the variable in the variable list. To specify an overall weight, select "Edit Metadata" and press the "weight" radio button under "design role." To specify replicate weights, select "Specify replicate weights," and drag the appropriate variables into the dialog box that pops up.

The difference between the replication variance estimation methods (JK1, JK2, etc.) has to do with how the weights are constructed, and how the variance calculations are done. You can find the details in the help system, under Tools|Variance Estimation|Jackknife and Tools|Variance Estimation|Balanced Repeated Replication

On the gender variable--the answer depends on how you want to use it. Is it the criterion or dependent variable? If so, drag it into the dependent variable box. If it is an independent variable, drag it into the independent variable box. If you believe that prediction variance differs between groups, drag it into the variance predictors box.

I hope this helps.

#### Q: I am using the NELS database and after importing from SPSS when I run crosstabs for say RACE and School TYPE with design variables included, I get a warning, that Stratum has single PSU cluster. What does this mean? This seems to happen especially with the NELS NP2 data. thanks

A: To estimate the variance within a stratum, you must have at least 2 primary sampling units (PSUs). If there is only one, AM will will estimate the variance around the overall mean, rather than the stratum mean.

you can right-click on the completed run icon to get a list of single-PSU strata. As long as this list matches what you believe is in your data, your estimates should be fine. Essentially, the approach that AM uses treats those strata as though they are from an unstratified sample.

#### Q: I have installed AM version 0.06.01 and when I run a procedure I get the follwing warning: "The browser is loading slowly or not loading". I ask the computer to continue loading but after several attempts I still get the same warning. Also, the results screen does pop up but it is empty. What am I doing wrong here. I am using my office computer at a large university and I haven't had problems running other programs. I also have system administrator permision so that shouldn't be the problem. I can't wait to use the software. Best Regards

A: The reason that you get the "browser loading slowly" message is exactly that--the browser is taking a long time to load. A java applet within the browser opens a socket to recieve information from AM, and in doing so, queries the network. Hence, if you network is slow (possibly due to heavy traffic), the browser can load slowly.

If you get the picture of the coffee-cup and sun in the browser, you simply need to click the "continue waiting" button one more time, and your results will appear. After that, do not close the browser--subsequent output will be sent more promptly.

If you do not get the coffee cup, but instead get a "missing picture" icon in the top frame of the browser, you have not installed the Java Plugin, which loads with AM. Reinstall that plugin, and you should be OK.

If neither of these fixes the problem for you, please write me and we'll pursue this further. In the mean time, select "text output" instead of HTML output from the dialog box with which you specify the statistical run-- the results will be written to a text file rather than HTML, and will come up in a text editor. It is a bit ugly, but at least you'll have results.

#### Q: Hi, I am trying to learn how to analyze the NELS:88 data set. I was following the directions in their manual about the sample for using the Am software. But I got stuck!!! When I try to check if the file that I imported from spss has the correct frecuencies, my computer/the software freezes - it shows a label that says "Robust Frecuencies and Crosstabs" and says:Begin, marking valid records, calculating estimates. And after a couple minutes shows a message that says that it is running slow, but afterwards says that it is unavailable. I re-downloaded the software but it is still doing the same thing. I really would apreciate any HELP. Thank you

A: It sounds like you did not completely install the software. After you install the AM, wait a minute or two and a "java plugin" will start to install. You must accept the license agreement and complete that installation to use the web-browser output.

At some institutions, users do not have administrative rights to their machines. If that is the case at your institution, the java plugin will not install, and you must ask someone with adminsitrator privledges to install it for you.

#### Q: In AM, how can I filter for more than one variable? For example: var1 >= 3 and var2 >=3 By the way, using "and" or "&" does not seems to work in AM. I tried using parentheses, etc., and still it did not work.

A: Hi,

I apologize for the expression parser--we will replace it as soon as we can. You must use mathematical expressions, rather than logical ones.

Comparison result in a 1 if true and zero otherwise. therefore, to create a variable that is

var1 >= 3 and var2 >=3

you would enter

(var1 >= 3) * (var2 >= 3)

which only evaluates to one if both expressions are true (otherwise you are multiplying by zero).

If you want to do the same thing, but with either one condition OR the other, you would use

(var1 >= 3) + (var2 >= 3)

Let me know if you have any further problems.

#### Q: This program is not installing completely. The final response states "unable to set base registry key." Please help.

A: You will need to have adminstrative privileges on your computer. The program installs along with the Java plugin for your browser. (AM presents output and the help system through the browser, and the plugin is required to make this work smoothly). Therefore, you should probably ask someone in your IT department to install it or give you administrative rights.

#### Q: I just downloaded the software for the general import function so that I can import a STATA 8 data file. I first go to import, then general import, then look for stata 8 files. When I select the stata file for import, I get the message that my "Database is invalid for Stata."

A: The software does not currently import Stata version 8, and it is not on the import menu. However, it does import Stata version 7. In Stata Version 8 you can save your file as a Stata Version 7 file by issuing the command "saveold"

#### Q: Is it possible to use AM with NSOPF:99? If so, are there any special instruction I need. Thank you

A: It certainly is possible. I believe that dataset includes both replication weights and strata and cluster identifiers. If I remember correctly, the latter are VSTRATA and VREP. I don't remember the name of the overall weight variable.

You can use the replication procedures with the replicate weights, or the taylor-series procedures (mostly under "Basic Statistics" on the statistics menu) by specifying the appropriate "design variables." Design variables are the replicate weights for the replicate procedure, or the strata, cluster, and weight identifier for the taylor series procedures.

Please e-mail me if you have any further questions.

#### Q: Can AM output an observation level file containing the predicted values from any of its linear, logistic, or multinomial regression procedures?

A: Currently, AM offers this option for some of the linear regression procedures. Right-click on the completed run icon to do create the predicted value. You can then use one of the export features (File|Export) to explort the observation-level file.

e-mail me if you have questions.

#### Q: Is Am able to filter more than one observation at a time e.g (RPTSAMP=1 and SCHTYPE=1) Thanks

A: Yes. However, the parser is not very friendly--you have to use mathematical operators. Each conditional expression (such as RPTSAMP=1) results in either a 0 or a 1. Non-zero values are kept in the sample.

If you want RPTSAMP=1 AND SCHTYP=1, you would enter
(RPTSAMP=1)*(SCHTYP=1), which would result in a zero if either were true. Similarly, addition accomplishes the work of "OR"

We hope to put a much more powerful and easy-to-use programming language in a subsequent version.

Please e-mail me if I can be of any more help.

#### Q: Under procedures for creating new variables and filtering, has AM figured out a way to do "or"?

A: Or is +. Each expression evaluates to a one or a zero, so a variable that equals 1 if the x = big or x= tall and zero otherwise would be

((x=tall) + (x=big) > 0

#### Q: I created a bargraph and saved it as a .jpg file, and also resaved the .am dataset, hoping the graph specification would get saved along with the .am datafile just like the .sAM model specifications do. But the graph specification didn't get saved. Whenever I want to redisplay the graph in AM I have to recreate it. What am I doing wrong?

A: You are not doing anything wrong. You cannot currently save graph specifications--you can save the graph itself in a variety of formats, but you must re-run it if you close the database.

Also, for statistical models, you must explicitly save the .sAM file by right-clicking on the completed run icon, and selecting the appropriate menu option--it does not save automatically when you save the dataset.

There is some good news: we are currently designing a programming language for AM that will not only allow you to write and save specifications, it will also provide access to AM's internals--maximization routines, matrix math, etc. This will make the program much more flexible. As always, it will remain free.

#### Q: I am Familiar with SUDAAN and often use that woth surveys such as the National Health Interview Survey. Will AM work with the NHIS and similar surveys?

A: absolutely. You may even find it a bit easier to use. If you have any questions about how to use it, please feel free to e-mail me.

#### Q: I am new to AM but am pretty familiar with SUDAAN. Anyway, I am trying to run a dummy coded regression but am getting an error message:"Gauss-Sungular Matrix-2: The data will not support this model." Can you tell me what I am doing wrong? Thank you.

A: Hi,

That message indicates that the regressor matrix is not of full rank.

When using dummy variables, the most common cause of this condition is including one variable for each category, rather than excluding one category. When you do this, the set of dummy variables is perfectly collinear with the constant term. Instead, you should exclude one category and interpret the coefficients associated with the others as the difference from the excluded category.

Please write me if you have any further questions or if this is not clear.

#### Q: I am new to your software. I'm trying to use MML regression with a public release NAEP data set. I have successfully imported the data from SPSS. However, I have not been able to create a test or subtest. After importing the data, I click "update metafile" and try to run a file that is as follows TEST="mytest1" ID=1 SUBTEST="read1" ID=1 FILE="E:\data\R34NT1AT.DAT" VARIABLES R017001 959-960 TYPE=B R017003 962-963 TYPE=B R017004 965-966 TYPE=B R017006 971-972 TYPE=B When I try to run the program I get a message saying "There are no valid observations." Do you have any examples of how to create tests and subtests? Any idea what I'm doing wrong?

A: There is a file that installs with the software:

"C:\Program Files\American Institutes for Research\AMBeta\Data\DemoData\jondemo.dct"

The help system (press F1) also describes how to create tests and subtests.

If the example and documentation are insufficient, write me back and let me know which NAEP dataset you are using--I may have a dictionary file ready to go. If not, I can give you more detail about how to create on.

#### Q: I did sectioned density plots on some TIMSS math score variables with gender on the horizontal axis, but the distributions in the plots are being severly truncated at the tails. The horizontal spread of the darkest bar for each density plot comes nowhere close to the min and max of the distributions. Is there a problem?

A: The sectioned density plot does not display the minimum and maximum values on the bottom bar. Each bar (or _section_) appears at a certain relative freqency threshold. The more sections, the smaller the increment. The darkest bar ends where the first relative frequency increment is passed. Very long, thin tails only show up when you use an unreasonably large number of sections.

#### Q: I am using ECLS-K and the C5PW0 weight. Is there a way to get simple descriptive statistics for a set of variables? I can only get the mean for my DV at each level of my IV. (In other words, I have five variables and I would like only five means/SDs.) Also, is there a way to get standardized coefficients from AM? The rest of the regression was fine for me. Thanks!

A: You can drag as many variables as you like into the dependent variable box in the descriptive statistics procedure. This should give you the table you want.

AM does not generate standardized coefficients. If you really want them you can output to a spreadsheet and calculate them there.

#### Q: I imported a SAS v8 file into AM v.06.02 and also specified an external file containing the formats (formats.sc2) in Add File, then clicked on Done. However, the formatted values do not appear when I run crosstabs. Is there something more I need to do so AM will use the formats?

A: yes. Unfortunately, SAS was not fothcoming with descriptions of their format catalogue data format. Therefore, you first have to save the formats as a SAS dataset:

proc format data=XXX cntlout=yyy;

Then, when you run the import you will be promted for format files. Add the SAS format data set file to the list, and it should work.

Please e-mail me at this address if you have any further problems.

#### Q: I am having a problem with importing a SAS v9.1.3 dataset with permanent formats. When I get to the "SAS Format Finfer" screen, I click the "Add File..." button to specify the location of my formats file. The problem is that the available file types are SC2, SD7, and SAS7BDAT; However, when I create permanent formats, SAS v9.1.3 on Windows XP creates a formats.sas7bcat file. Thus I can never include my formats. Can you please update the data transfer component to allow for SAS7BCAT format files? I would be happy to send you the SAS code along with the dataset and format file if that would help.

A: Hi,

The import function uses third-party software that we have licensed for distribution with AM. We plan on updating it within the next year; however, you can include your current formats. To accomplish this, run:

proc format library= cntlout=

to create an output data set (make sure it is a version 7 dataset you create). You can import formats from this library.

Let me know if you need more help. e-mail me directly at the address above.

Thanks

#### Q: I have developed scales as measures of my independent variables and I want to run an alpha reliability scale analysis. What procedure do I follow in AMSTAT?

A: AM does not currently calculate Cronbach's alpha. That statistic is typically not reported with a standard error, so you will have no problem if you compute it in SPSS, SAS, or Stata.

Please write back if you think that this would be generally useful enough to warrant inclusion in a future release.

#### Q: Hello - I'm working with the NELS dataset and eventually I plan to use AM software to adjust the standard errors for design effects. I will then import the adjusted correlation matrix into AMOS (a structural equation modeling program). In the process of conducting some preliminary analyses, I noticed that, using the same data, SPSS and AM generate correlation matrices whose values don't match. The problem appears to be that in SPSS I used the default pairwise deletion of missing data whereas AM uses a listwise approach (which results in a large sample loss). Is there a way to analyze data in AM using pairwise deletion of missing data? Thanks!

A: Unfortunately, currently the only way to get AM to calculate correlations with pair-wise deletion is to calculate each correlation separately.

#### Q: I just began using AM and there does not seem to be an option for web output under the Results tab. Currently when I run an analysis the results open in excel but the colums are not aligned. Can you help me figure out how to get the results to open in the web browser?

A: it sounds like the browser output system did not install correctly. Some users have been having this problem recently because their institutions do not give them sufficient rights to install the software correctly. We are working on a solution for the next release, so that users without administrative rights on their computers will be able to install the software themselves.

In the mean time, the solution is to ask your system administrator to re-install the program for you. It is usually a good idea to check that the browser output and help system function properly before letting the system admin leave your office.

Let me know if this does not solve your problem.

#### Q: Sorry to bother you again, but I want to set multiple filters and I am not sure how. Can you explain?

A: No problem at all.

Just use mathematical notation. So, for example, if you want all cases where A > 0 AND B > 0, you write

(A > 0)*(B > 0)

If either condition is not true, it evaluates to 0, and the entire expression becomes zero, excluding the case from analysis.

If you want to A > 0 OR B > 0, you write

(A > 0) + (B > 0)

Please let me know if you need any further help.

#### Q: please send me the manual to run AM softwatre & othe software support that may be required to run AM. I've already downloaded it but can not use it properly without the user guide.

A: I am sorry that you are having trouble. We do not have a current user's guide, but all the documentation is available online. You should be able to access it by pressing F1 from within AM--it will come up in your browser. If it does not, you may have to reinstall the software, making sure that you have administrative rights on the computer first.

The manual can also be browsed online at am.air.org (select "Manual" from the home page).

If this is not sufficient, we do have a very old version of a user's guide that may be of some limited help. If you'd like a copy, please e-mail me at this address.

#### Q: 1. I am not sure what to type in for strata, cluster, and weights when running the analysis. 2. There is a t-test option, but how about ANOVA. 3. How do I get var/cov matrix information? 4. Can AM do CFA/SEM or ML-SEM? Thank you for your assistance.

A: 1. When a sample is stratified, clustered, or weighted variables indicating the strata, cluster (psu) and weight typically appear on the data file. This information about the sample design enables AM to accurately estimate the standard errors.

2. ANOVA can be implemented using the regression procedures. Run a regression with a dummy variable representing each group (excluding one group, which is represented by the constant term.

3. Covariances of the estimates are available by right clicking on the completed run in the Completed Run Queue (top right window, select menu option). The descriptive procedure will give you correlations and variances, from which you can calculate the covariances if you need them.

4. confirmatory factor analysis/ structural equation modeling? AM can do a limited set of specific models, but does not currently have a general capability to estimate these.

#### Q: Can I use AM for PIRLS 2001 dataset from NCES? Thanks.

A: Yes. Check the PIRLS manual or contact NCES or the International Study Center at Boston College to find the names of the design variables (strata, cluster, weight).

Also, you may want to check out http://lighthouse.air.org/timss where you can analyze the data on line. Let me know what you think after you try it.

#### Q: I have just installed the software & Java applet (Win XP). However, when I click the help menu, the manual does not load - what have I done wrong? Thanks

A: The many new security features in windows has made this a relatively common problem. Here are the most likely culprits:

1. if you don't have administrator rights on your computer, then the help applet did not install properly. Have someone with administrator rights install it.

2. Your browser may be not allow java to run. Go into your security settings and tell it to allow java applets to run without prompting. In the default configuration, IE will give you a barely perceptible prompt asking if you want to allow the program to run, simply telling it "yes" works if this happens.

In either case, the browser output system will nto work either until you get it straigtened out. Please contact me at this address if you have any further trouble.

#### Q: There is probably a very simple answer to my question that I am just missing, but I am driving myself crazy trying to figure out how to do this... How can I perform a simple T-test to compare the means between two groups? I have filtered the data to get the different means, and I see that T-test is an option by right-clicking on the completed runs of the descriptive analyses, but for the life of me, I cannot figure out how to compare the means between two groups. Please advise! Thank you!

A: It is simple. Run descriptive statistics. Your dependent variable will be the one whose mean you are interested in. Your independent variable will be a categorical variable that defines the two groups that you want to compare (no filters necessary).

After you do the run, right click on t-test. Then, click on the first mean. When you click on the second mean you will see the t-test result.

Please write me at this address if you have any further difficulty.

#### Q: The AM software keeps crashing when I'm trying to do analyses for my thesis. I've successfully used the software for doing similar analyses in the past. I'll describe the problem as completely as I can. I have reinstalled both the beta program and the data transfer component. I'm using Windows XP. I have an SPSS data file of less than 2000 lines, from the NELS:88-2000 database. I'm trying to run Frequencies with one dependent variable and 7 independent variables, outputting to a text file. The routine will run successfully with 4 independent variables. When I add a fifth, I get a Windows message saying, "Windows - Virtual Memory Minimum Too Low." The message indicates that more memory is being made available, but in a few seconds the program crashes. The routine is in the process of "Calculating Robust Variance Matrix" when it falls apart. Any help you can provide will be greatly appreciated. As you can imagine, the successful completion of the data analysis for my thesis is dependent upon my ability to use the AM software. I suspect it may be a problem with my laptop, even though I can't identify what it might be. I'm hoping you can point me in the right direction. Thanks VERY much!

A: Hi,

Sorry that it has taken so long to get back to you.

The problem that you are encountering is that your machine is running out of memory. AM should not crash when this happens, but the current version does (sorry .. a fix will be available soon). The reason that this happens is that the table that you are trying to create is simply too large. I'll bet that the fourth variable that you are adding has very many unique values, leading to matrices that are enormous. Try creating variables that have just a few categories.

The new version should be available in a couple of months, and this problem will go away.

#### Q: I am trying to import a file with around 28000000 observation(size 1.5Gb , .csv file) and I am getting a "Import failure : might be bad file file of wrong type" message , please help.

A: Hi,

AM uses third-party software for the import procedures. I have imported very large files, but never 28 million records. Is this data that you can send to me? If so, I can try to track down the problem.

#### Q: Hello, I have a question about BRR in AM. Where I can find the way to use BRR in AM? I searched the online manual..But It seemed that I did not find it. Please let me know where I can find it.. Have a nice day

A: You will find some information and futher citations in the online help. See Tools/Variance Estimation/Balanced Repeated Replication

#### Q: Dear Sir, I have two questions. The first question is about graphs. Actually I have several BRR weights. so I want to use them in graphs. I am not sure whether AM can allows me to draw histogram or boxplots. The second question is about dataset. Is there any method to save and export the data in which BRR weights are reflected? Have a nice day

A: Question 1: AM can do Sectioned Density Plots, which replace box-plots and histograms. It is not clear whether you want to graph the weights themselves, or have them reflected in the data that you graph. If you want to graph the weights, you can do that from the graph menu. If you want graphs that reflect the weights, run the replication procedure of interest (say, the descriptives procedure), then right click on completed runs and request a bar or line chart.

Question 2: The export procedures will export any variables that you request, including the BRR weights.

#### Q: I have two questions about AM. 1. After making the crosstable with two categorical variables, I want to do some tests like chi-square test. Is there any method to do in AM? 2. It seems that I can do t-test for comparing estimates of population parameter to one another. Is possible to do ANOVA(Analysis of Variance)? Have a nice day

A: 1. Currently AM does not have a test to determine whether the pattern of data across cells is likely to be random (what the chi-square would test). A traditional chi-square on a complex sample would not be an appropriate test. I'll put such a test on a "to do" list to add to the program.

2. An ANOVA can be accomplished via the regression procedures. Create dummy variables for each category or interaction of interest and introduce them into the regression. Please note that usual F-tests will not be valid in a complex sample, but you can use the Wald test in AM.

Please write me back if I can be of more help.

#### Q: I am trying to filter observations with the ECLS-K dataset. Specifically, I want to select children that have a non-zero reading, science, and math score. I've tried various versions of the following command to no avail. It will work when I enter only one, for example just "C5SSCALE >0" but I can't figure out how to include all components. Any thoughts on if this is possible? (C5SSCALE >0) and (C5R2MSCL >0) and (C5R2RSCL >0)

A: The current parser only uses mathematical notation. Your code should look like this:

(C5SSCALE >0) * (C5R2MSCL >0) *(C5R2RSCL >0)

If all conditions are true, the result is nonzero (1 in this case) and the case is retained. Otherwise, it evaluates to zero and the case is filtered out.

#### Q: I am using data from waves 1 and 3 of the National Longitudinal Study of Adolescent Health. I am fairly sure that I have the apppropriate sample weight, strata, and cluster variables. Can I simply plug these into AM software to do a logit analysis that will give me correct standard errors?

A: Best question all week (because I like the answer)...

yup.

#### Q: I am trying to analyze bank account data using your software. The fields in my table are Current balance, NSF Fees Assessed, and NSF Fees Paid. I would like to see if there is a correlation between a drop in current balance and the other 2 fields. Can you help me with what type of analysis I should use and which would be the dependant/independant variables please?

A: Sorry for the delay in getting back to you. You should select

Statistics|Basic Statistics|Correlations

from the main menu, then put all of the variables for which you would like correlations in the dependent variable box.

If you'd like this broken down by subgroup, put the categorical variables in the independent variable box.

#### Q: I selected one set of replicate weights but want to change my selection. When I right click and go to "set replicate weights", is there any easy way to deselect the replicate weights? I can't seem to drag them out of the replicate weight dialog box nor to delete them from there. The only way that seems to work is to go to "edit metadata", change the role to something other than "none," click "ok" then go back into metadata and change the role to "none." Thanks in advance.

A: Believe it or not, we just had not considered this scenario. I apologize, but you have found the only way to do it.

We will certainly put this on the list of features to be added in the near future.

Thanks

#### Q: Please excuse the simplicity in my question but I'm really naive of statistical matters (still an undergraduate in college). I want to run an F-Test, with two IVs and one DV. I can't figure out where it is in your software. Does AM have F-test in its software?

A: There is no F-test because that is only appropriate in a simple random sample. The Wald test statistic will serve this purpose in a complex sample.

#### Q: I have a Mac Powerbook G4 running OS 10.3.9. When I try to download the AM software it loads a file "AMInstall.exe" on my desktop but my computer doesn't know what application to use to read the .exe. Advice?

A: Sorry for the delayed resonse. AM will not yet run on a MAC. I hope to port it over eventually.

#### Q: First, I am so happy to have found this software for my NAEP analysis. And Thank You for making it FREE! Ok, so I here are my questions. I just want to confirm that I am doing this correctly. I will be using NAEP Geography data from 2001, 1994, and a pilot assessment done in 1989. So far, I have the 2001, 4th grade data set in AM but am not sure how to proceed exactly with setting all the parameters. From what I can tell, I just go to "statistics," select my variables, AND then where prompted in that window, define the "Strata," "Cluster," and "Weight" by adding the correct variables (which accroding to my ETS contact are "REPGRP1," "JKUNIT," and "Weight," respectively. OR am I mistaken and need to "edit metadata and Set replicate weights? I'm grateful for any help. Thank you.

A: First, let me apologize for the delayed response. I have been traveling. I usually answer these within a day.

Both approaches work. The advantage of going the "Edit Metadata" route is that these will become the default values for all runs, so you won't have to drag them in each time.

You have identified the correct design variables for NAEP.