As a researcher your area of expertise is not statistics. Yet the preparation of a successful article involves conducting effective research, analyzing data and presenting the results… all of which require a high level of mathematical and statistical expertise. Hiring a statistical consultant lets you focus on becoming an expert in your field of study rather than try to master statistics. .I can help you develop a successful article from initial idea to submission to a journal and can offer assistance with any or all of these steps:
- Research Methodology - get your research started on the right track and you'll save yourself loads of time and energy later on in the process. I can show you how to avoid common mistakes and assumptions.
- Research Design - the reliability of you results is crucial to your success. I can show you the best ways to design research to test your hypothesis
- Variables are the basis of the predetermined theory being tested. They must also be operationalized. I'll be there to give you experienced guidance and the necessary statistical expertise.
- Sample Size Calculation and justification - It is often difficult to select the right sample size. Too small a sample - and you may not be able to give good evidence for your hypothesis. Too large a sample, and you waste time, effort and money collecting data. I can work with you to do an appropriate power analysis so that you select an appropriate sample size and can justify it to your committee.
- Statistical techniques - there are many statistical methods that serve a wide variety of purposes I'll work with you to select the one that answers your questions, so that your substantive questions drive the statistical analysis, rather than the other w around. These methods include:
- Linear regression
- Dichotomous logistic regression
- Ordinal logistic regression
- Multinomial logistic regression
- Quantile regression
- Poisson regression and other methods for count data
- Various types of survival analysis
- Multilevel models of various kinds
- LogLinear models
- Factor analysis
- Principal component analysis
- Multidimensional scaling
- Cluster analysis
- Additve models
- Multiple imputation
- An extensive array of graphical procedures
- Validity and Reliability of Results - valid research requires much more that simply collecting data and conducting statistical analysis. I can help you determine the reliability and validity of your instruments.
- Interpretation of Results - Accurate interpretation of results and presentation of results in an appropriate format can make or break your article. I can help you pull your research together into a compelling presentation that is reliable and valid.
This is a talk I've given at Northeast SAS Users Group (NESUG) and at SAS Global Forum (SGF)
In statistics and research design, there are two types of study: Experiments and observational studies. Some...
Regression is a set of statistical techniques for relating a dependent variable to one or more independent...
I've designed a great experiment And collected all my data. I've no idea what it all means I'll get to that...
Often, when reading a statistics book, you will see some variation on the phrase "independent data". Many...
Macros can be a very complex topic, but some very simple macros can make life easier for a data analyst or...
When it comes to measures of central tendency or location, the arithmetic mean and the median get a lot of...
There are many books that teach you to use SAS or that teach you to use R. There is at least one book that...
Two terms that are frequently confused are moderation and mediation: Definitions...
[latexpage] The chi-square test can refer to several different types of tests. Here I will discuss the...
This is a talk developed by David Cassell and me, and given at NESUG and SGF and WUSS
Question: Is the method of determining outliers by flagging data that are more than 3 standard deviations away...