Statsols Blog

Thoughts on the ASA P Values Statement

“When a measure becomes a target, it ceases to be a good measure”

Topics:

Why is Sample Size important?

Why Calculate Sample Size?

A good statistical study is one that is well designed and leads to valid conclusions. This however, is not always the case, even in published studies. In Cohen’s (1962) seminal power analysis of the journal of Abnormal and Social Psychology he concluded that over half of the published studies were insufficiently powered to result in statistical significance for the main hypothesis.

Topics:

Monday at JSM 2015, what are you attending?

With JSM 2015 now in full swing here are the talks Statistical Solutions would be attending today, Monday August 10th.

Today we've focused on techniques for handling missing data with a particular focus on modern and novel techniques and applications in survey research and government statistics.

Topics:

An Overview of Multiple Imputation in SOLAS for Missing Data 5.0

In our previous post we discussed the pervasive problem of missing data in data analysis. To recap quickly, in a data set with 5 variables measured at the start of a study and monthly for six months, if each variable is 95% complete with a random 5% of the values missing, then the proportion of cases that are expected to be incomplete are 1-(.95)^35= 0.834. That is, only 17% of the cases would be complete and with traditional complete case analysis, you would then lose 83% of your data.

How It Works?

With Solas 5.0TM, missing values in a data set are filled-in with plausible estimates to produce a complete data set that can be analyzed using complete-data inferential methods and designed to accommodate a range of missing data scenarios in both longitudinal and single-observation study designs.

Topics:

Missing Data - A Pervasive Problem in Data Analysis

Missing data are a pervasive problem in data analysis. Missing values lead to less efficient estimates because of the reduced size of the database, also standard complete-data methods of analysis no longer apply. For example, analyses such as multiple regression use only cases that have complete data, so including a variable with numerous missing values would severely reduce the sample size.

Topics:

Why is Sample Size Important?

A good statistical study is one that is well designed and leads to valid conclusions. This however, is not always the case, even in published studies. In Cohen’s (1962) seminal power analysis of the journal of Abnormal and Social Psychology he concluded that over half of the published studies were insufficiently powered to result in statistical significance for the main hypothesis.

Topics:

Data Integration and Visualization

Today’s complex clinical trials yield data sets that are almost unimaginably large and complex. As a result, the process of transforming trial data into usable knowledge simply cannot be accomplished using traditional presentation methods such as conventional charts and graphs.

Topics:

New lung cancer detection instrument moving to clinical trials stage

Owlstone Nanotech, the developers of a promising new lung cancer detection instrument have announced they are now moving their device into clinical trials. The trials are said to begin later this year in a rapid access lung cancer clinic at Glenfield Hospital in Leicester, England.

Topics:

Institute of Medicine releases report “Sharing Clinical Trial Data: Maximizing Benefits, Minimizing Risk”

Great BLOG Post from By ED SILVERMAN on the Wall Street Journal

Topics:

nQuery Advisor + nTerim used to calculate sample size at St James Hospital, Dublin.

nQuery Advisor + nTerim was used to calculate sample size in a study conducted at St James Hospital, Dublin. The study evaluated the dose intensity and toxicities experienced by patients of normal and increased body mass index BMI treated with FOLFOX chemo- therapy, and demonstrated that overweight patients may tolerate doses based on actual body weight.

Topics: