Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

A proprietary cross-platform general-purpose statistical software package.

-1
votes
0answers
9 views

Log estimates PROC GLIMMIX Poisson - convert back to original scale [on hold]

I am running a mixed model in SAS using PROC glimmix, to analyze longitudinal count data (Poisson distribution, autoregressive covariance structure), and I'm interested in interpreting the fixed ...
0
votes
0answers
3 views

Cumulative Incidence Plots - Weibull Model - Time Dependent Covariates

I am seeking to create a Cumulative Incidence Plot for a Weibull model with baseline and time-varying covariates. I am using SAS PROC LIFEREG to for this model but there are two issues-one of which is ...
0
votes
0answers
27 views

Difference between PROC CATMOD and PROC GENMOD for log-linear regression

I am reading "An Introduction to Categorical Data Analysis, Second Edition" by Alan Agresti. Data I am trying to fit is presented in Table 7.3 in the book. The log-linear regression by PROC GENMOD is ...
0
votes
0answers
13 views

Decision Tree with unbalanced dataset in SAS

I have a dataset with a binary target variable. This variable is highly imbalanced i.e. the # of True case is ~1% and # of False cases is ~99% The other limitation I have is that I can only use ...
0
votes
0answers
8 views

Mantel Test of Proportion : Aggregating categories different significance

I have a dataset representing for a specific marketing event editions (1 event per 1 year), the number of partecipants, and the outcome of their partecipation If In sas I use the Mantel Exact test to ...
0
votes
1answer
16 views

Can I force the direction of hazards ratio?

I am doing a survival analysis using Cox's proportional hazards model with several predictive variables. Some of the estimated hazards ratio goes in an implausible direction, which contradicts what we ...
0
votes
0answers
21 views

Events/Trials Syntax vs. Single-Trial Mixed Model - Beta-Binomial Model

I'm a touch confused about modeling an events/trials outcome when the Bernoulli trials are not independent, such as when a series of Bernoulli trials are observed from the same person. I cannot find a ...
1
vote
0answers
33 views

Confidence region for multinomial distribution with k=7 - including 5 zero values in dataset

I have a multinomial distribution with $k=7$ and an observed dataset $n_i = \{62, 35, 0, 0, 0, 0, 0\}$. While it was quite expected that $n_i = 0$ for $i \in \{3,4,...,7\}$, there was no way to ...
0
votes
1answer
23 views

Type of transformation needed for Clustering in SAS E-Miner

I'm performing a cluster analysis with a dateset that contain over 100 varibles (after imputing, replacing and eliminating correlated vars ..) Before hiting the clustering, for the transformation ...
0
votes
0answers
10 views

C&RT Rule Set missing rules?

I configured a C&RT 2-class classifier model from a dataset and then saved the results to a table that I exported to a server running SAS. I used "Generate->Rule Set" on the C&RT model to see ...
0
votes
1answer
64 views

How to Translate Sampling SAS Code into R ? [closed]

I am trying to translate a SAS sampling method into r and wondering if there is a comparable r method that I can leverage for the following SAS code. ...
0
votes
1answer
32 views

Is 3x3x2x2 ANOVA possible?

I just don’t want to look dumb suggesting it. I have 4 categorical IVs with a continuous DV. Two IVs with 3 levels and two with two levels. Am I right to start off by testing via ANOVA assuming the ...
2
votes
0answers
18 views

Cannot get Terpstra-Jonckheere to match between R and SAS

I am trying to replicate some SAS code in R, and I'm having some issues with the Terpstra-Jonckheere test. Here is my R code: ...
0
votes
0answers
7 views

Comparing two KM estimates outputs without raw data

Some raw data has gone missing, but I have the outputs of two KM curves - Both their survival estimates and patients at risk. Is there any way for me to use just the estimates to test the difference ...
0
votes
1answer
34 views

SAS proc mixed Degree of freedom

I have a dataset in this format: Factor A is a between subject factor (with 2 levels - High and Low). Factor B is a within subject factor (with 3 levels - High , Moderate and Low). I want to run a ...
2
votes
0answers
45 views

Repeated randomized 4 by 4 latin square

I have a field setup with 4 treatments in a latin sqaure setup repeated 5 times. A B D C C A B D B D C A D C A B This field setup is enclosed. The setup is ...
1
vote
0answers
33 views

Accounting for complex survey design for structural equation modeling

I am using proc calis procedure in SAS to perform structural equation modeling (SEM). I have a nationally representative survey data with person-level weights, strata and cluster variables. However, I ...
0
votes
0answers
34 views

Box-Cox Transformation on Single Variable and Interpretation of the Transformed Variable's Mean and Standard Deviation

I'm revisiting the Box-Cox transformation in one of my stats books, and I started playing around with the SAS macro %BCTRANS2 (Source: http://support.sas.com/resources/papers/proceedings12/430-2012....
1
vote
1answer
25 views

Multiple measurements within one feature

From US health insurance data, I have 300k prescriptions for an injected biologic from many patients . For each prescription there's a quantity variable, described by the data vendor as "The number ...
1
vote
0answers
14 views

Using weighted or unweighted wPCA scores in Logistic regression model-SAS

Im working on data that I should weight the data using a weight variable that I have and I want to evaluate the association of dietary pattern and obesity. So first I run Proc factor and use the "...
0
votes
1answer
68 views

SAS glimmix (poisson, ar(1)): generating fixed effects table?

I am running a mixed model in SAS using PROC glimmix, to analyze longitudinal count data (Poisson distribution, autoregressive covariance structure), and would like to produce fixed effect estimates ...
0
votes
0answers
25 views

90/10 Peak Weather Probability Demand Forecast

I'm looking into different forecast scenarios based on peak yearly weather. If I have 20 years of peak temperatures (max temperature per year), how would I come up with the max weather value that ...
0
votes
1answer
47 views

Use propensity score or logit propensity score as distance metric for control group selection?

My question is a bit of a general one (and my first on here). I'm researching different matching methods for selecting a control group in an observational study, and when checking SAS's options for ...
1
vote
0answers
17 views

interpretationInput variables ARIMA

Could anyone help me with the interpretation of the deltas: The dependent variable lnY (with y=number of calls) is differentiated 7 times, given a weekly seasonality. Independent variables: '...
0
votes
1answer
41 views

Residual Plot and QQ Plot

Is this a good residuals plot and QQ plot to verify the constant variance and normality assumption?
1
vote
1answer
107 views

Variable selection - K Fold cross-validation or Lasso regression?

I have a set of about 40 predictor variables for a set of 20K subjects. The outcome is a binary yes/no response, so I would like to end with a logistic regression model. My thought is to use PROC ...
0
votes
0answers
11 views

What are the characteristics of a good cluster?

I am analysing a data set using Clustering Algorithm in SAS Enterprise Miner. I have tried to change various settings to get the best results. But,I dont really know how to decide whether the model ...
0
votes
1answer
25 views

Logistic regression prediction out of boundaries in SAS

I have a big issue with my logistic regression in SAS. ...
3
votes
0answers
54 views

bias adjusted confidence interval for correlation coefficient

I stumbled across confidence intervals for $\rho$ in a statistics textbook. This was not part of the class, but I found it interesting. My textbook has a formula for this with a Fisher transformation, ...
2
votes
0answers
39 views

Insignificant “time variable” in GLM?

I'm used to GLM modelling with a time variable, eg. Month or Year, main reason being it is often used as a proxy for an immeasurable variable, or simply data you can not easily obtain, econometrically ...
0
votes
0answers
11 views

Paired Groups comparisons over 3 tests

I have data for a psychological study that follows patients across 6 sessions. The subject takes an intake test, the same test after the 3 session, and the same test again after the 6th session. Now, ...
1
vote
0answers
34 views

FGLS vs M estimator

I have been reading a lot that in Robust Regression, there are 2 ways of handling heteroskedasticity. 1)WLS - In SAS PROC ROBUST procedure, M estimator and Iteratively Reweighted Least Square. 2) FGLS ...
0
votes
0answers
37 views

Which test should I use when looking at pre/post tests for a small sample?

I am working on an evaluation for my internship site. We do a falls prevention program for older adults that shows exercises to build lower and core body strength. Additionally, we address their fears ...
0
votes
0answers
28 views

SAS – Compare same week in different months

I have been using the IF.first approach to create different interval points to compare data across a spread of months. However, I now need to do the comparison of orders purchased between weekly ...
1
vote
1answer
31 views

Approach to analysing big data [closed]

I’m trying to analyse quite a largish dataset. The sasdb7 is around 11GB and the csv is around 9GB. This is after merging the datasets, cleaning and removing unnecessary columns. I am comfortable ...
1
vote
1answer
595 views

Interpreting the Somers' D statistics

I'm running a logistic regression model by using SAS PROC LOGISTIC. In the Association Statistics table that SAS provides as analysis output there is the Somers' D stat. Could you provide an ...
0
votes
1answer
14 views

Accounting for person-time exposed in a binomial GLMM

I have a large data set where we have 5 calendar years data for each person, and we have information about the number of outcomes (taking values 0,1,or 2) each year. We have to account for the ...
6
votes
1answer
209 views
0
votes
0answers
48 views

How to calculate betas of logistic regression if effect sizes are known?

I want to simulate responses using built in JMP Simulate Responses feature for learning purpose. I use binomial distribution and I assume that I know effect sizes of factors beforehand. So I know ...
0
votes
0answers
174 views

Estimating hourly temperature from daily max, min and average temperature

I would like to estimate the hourly temperature of a large meteorological dataset where I have daily maximum, minimum and mean temperature for each day. Using all these three variables (max, min, and ...
0
votes
1answer
28 views

Why are IV with odds ratios =1 included in the model?

I am running a logistic regression where the outcome is sale success. I include different IVs, and variables such as talk time to the customer and the amount a customer is paying receive an odds ratio ...
0
votes
1answer
41 views

How many dummies should I create

I have sales data for different locations. My outcome variable is making a sale (1,0) and my IVs are about 200 different locations, handling time etc.. I ran a logistic regression using the class ...
0
votes
1answer
72 views

Data Analysis SAS - mean vs median

I am new to all this so I am sorry beforehand if this is very straightforward or silly! I was wondering if someone could help me sort this out. This is my SAS output: I have 35 observations (35 ...
0
votes
1answer
56 views

Which fold will be chosen after applying k-fold cross validation? [duplicate]

I think I barely understand how k-fold CV is working and I have a question about it. For example, when I run 5-fold cross-validation (in SAS), I use 5 subsets of the training data, and end up with 5 ...
0
votes
0answers
41 views

Using percentiles instead of mean for the parameter of the response variable in regression

I want to do a linear regression in SAS between two variables. What I would get is the parameter for the mean of my response variable (and the 95% confidence interval for the parameter), but that is ...
0
votes
0answers
17 views

Noninferiority in a multilevel model

I am working on a randomized trial in which patients were randomized to one of two groups and followed over time, they were assessed at 5 time points including baseline. The outcomes include ...
0
votes
1answer
30 views

tau2 estimation using reml in SAS

I would like to obtain tau2 estimation using REML by making use of PROC MIXED procedure in SAS to compare the estimation result obtained from rma function in R. I have used the following SAS code; ...
1
vote
0answers
75 views

Logistic regression and unbalanced sample [duplicate]

I am running a logistic regression in SAS where the outcome variable is a binary on sale success (IVs are: location of the customer, Vendor, handling time, experience level of sales person etc.). ...
4
votes
4answers
359 views

Why does lmer (unlike SAS) output a non-zero variance of random effect if it is also included as fixed: (1|site) + site?

(I am completely editing my post. The root question is the same, but I am now posting simulated data to illustrate my issue). I ran (I beleive) the same model in both proc mixed and R (lmer) but have ...
0
votes
0answers
40 views

Is the supremum test of cumulative martingales residuals OK to assess proportional hazards of both groups and covariates?

Is the supremum test of cumulative martingales residuals (as implemented by assess in SAS PROC PHREG, and other software) OK for testing PH of both continuous ...