Ralitza Gueorguieva, Ph.D., a senior research scientist in the Department of Biostatistics at the Yale School of Public Health, spent more than two years writing a book on statistical models for correlated data analysis. The book, Statistical Methods in Psychiatry and Related Fields, is being published by CRC Press this month. It is Gueorguieva’s first book.
Congratulations on your new book, “Statistical Methods in Psychiatry and Related Fields.” Can you generally describe the book’s content?
RG: The book describes, at a non-technical level, modern statistical models for the analysis of correlated data when outcomes are repeatedly assessed within individual or on related individuals. The examples used for illustration are from clinical trials and observational studies in psychiatry and related fields. Important issues such as missing data, multiple testing, covariate adjustment, assessment of mediator and moderator effects, study design and sample size considerations are covered. Software programs, data sets and output are available on a supplementary website.
What does this book contribute to the literature on statistical methods in psychiatry?
RG: Data collected in psychiatry are typically complex because outcomes are indirectly measured, there is large subject-to-subject variability, substantial missing data and multiple outcomes. Advanced statistical methods are required to properly take into account these features of the data, yet there are few scattered publications in the psychiatry literature that describe statistical methods both with enough accuracy and at a language understandable by applied researchers. The purpose and the intended contribution of this book is to put together all necessary information for the use of appropriate statistical models for correlated data, and increase the use and appreciation of such methods.
Who is the intended audience for this book?
The most challenging part was striking the right balance between being technically correct in the description of the methods and maintaining a clear and understandable presentation style.
Ralitza Gueorguieva
RG: The intended audience are applied researchers with minimal knowledge of statistics, although the book could also benefit collaborating statisticians.
What was the most challenging part of writing this book?
RG: The most challenging part was striking the right balance between being technically correct in the description of the methods and maintaining a clear and understandable presentation style. Having multiple illustrative examples helped in this process.
How long did it take to write? Is it your first book?
RG: Two and a half years. Yes, this is my fist book. I am very excited to send it on its way and looking forward to the feedback that I will receive.