Statistician (Data Scientist)
As a Statistician (Data Scientist), you will:
Review, update and run an existing set of Python-based natural language processing (NLP) text classification programs on the identification of opioids and co-occurring substance use disorders. Design and implement new NLP and machine learning classification programs on the identification of specific substances found in hospital electronic health records (EHR) data and death certificates. Design and implement a plan for testing and re-training/fine-tuning the programs as needed. Work with a team of clinicians, epidemiologists, and health scientists to annotate additional clinical data, as needed, to improve classification accuracy. Provide guidance for a validation study designed to test different iterations of structured and unstructured data algorithms and document performance. Create documentation to enable external users to run the text classification programs on their own clinical data files. Contribute analytic and writing support to abstracts, papers, reports and presentations. Provide technical assistance to internal and external researchers to apply the algorithms and analyze findings upon request. Basic
Qualifications:
A degree that included 15 semester hours in statistics (or in mathematics and statistics, provided at least 6 semester hours were in statistics), and 9 additional semester hours in one or more of the following:
physical or biological sciences, medicine, education, or engineering; or in the social sciences including demography, history, economics, social welfare, geography, international relations, social or cultural anthropology, health sociology, political science, public administration, psychology, etc. Credit toward meeting statistical course requirements should be given for courses in which 50 percent of the course content appears to be statistical methods, e.g., courses that included studies in research methods in psychology or economics such as tests and measurements or business cycles, or courses in methods of processing mass statistical data such as tabulating methods or electronic data processing. or A combination of education and experience -- courses as shown in A above, plus appropriate experience or additional education. The experience should have included a full range of professional statistical work such as (a) sampling, (b) collecting, computing, and analyzing statistical data, and (c) applying statistical techniques such as measurement of central tendency, dispersion, skewness, sampling error, simple and multiple correlation, analysis of variance, and tests of significance. Minimum
Qualifications:
Applicants must have at least one year of specialized experience at or equivalent to the GS-13 in the Federal service as defined in the next paragraph. Specialized experience is experience which is directly related to the position which has equipped the applicant with the particular knowledge, skills and abilities (KSAs) to successfully perform the duties of the position to include experience applying textual analysis (including building NLP pipelines, machine learning classifiers, and named entity recognition tools) to analyze textual data from complex survey data.
Estimated Salary: $20 to $28 per hour based on qualifications.
Review, update and run an existing set of Python-based natural language processing (NLP) text classification programs on the identification of opioids and co-occurring substance use disorders. Design and implement new NLP and machine learning classification programs on the identification of specific substances found in hospital electronic health records (EHR) data and death certificates. Design and implement a plan for testing and re-training/fine-tuning the programs as needed. Work with a team of clinicians, epidemiologists, and health scientists to annotate additional clinical data, as needed, to improve classification accuracy. Provide guidance for a validation study designed to test different iterations of structured and unstructured data algorithms and document performance. Create documentation to enable external users to run the text classification programs on their own clinical data files. Contribute analytic and writing support to abstracts, papers, reports and presentations. Provide technical assistance to internal and external researchers to apply the algorithms and analyze findings upon request. Basic
Qualifications:
A degree that included 15 semester hours in statistics (or in mathematics and statistics, provided at least 6 semester hours were in statistics), and 9 additional semester hours in one or more of the following:
physical or biological sciences, medicine, education, or engineering; or in the social sciences including demography, history, economics, social welfare, geography, international relations, social or cultural anthropology, health sociology, political science, public administration, psychology, etc. Credit toward meeting statistical course requirements should be given for courses in which 50 percent of the course content appears to be statistical methods, e.g., courses that included studies in research methods in psychology or economics such as tests and measurements or business cycles, or courses in methods of processing mass statistical data such as tabulating methods or electronic data processing. or A combination of education and experience -- courses as shown in A above, plus appropriate experience or additional education. The experience should have included a full range of professional statistical work such as (a) sampling, (b) collecting, computing, and analyzing statistical data, and (c) applying statistical techniques such as measurement of central tendency, dispersion, skewness, sampling error, simple and multiple correlation, analysis of variance, and tests of significance. Minimum
Qualifications:
Applicants must have at least one year of specialized experience at or equivalent to the GS-13 in the Federal service as defined in the next paragraph. Specialized experience is experience which is directly related to the position which has equipped the applicant with the particular knowledge, skills and abilities (KSAs) to successfully perform the duties of the position to include experience applying textual analysis (including building NLP pipelines, machine learning classifiers, and named entity recognition tools) to analyze textual data from complex survey data.
- Department:
1530 Statistics - Salary Range:
$121,316 to $157,709 per year
Estimated Salary: $20 to $28 per hour based on qualifications.
|
|
 | |
