Firefeather

293 reputation

214

bio	website
	location	Columbus, OH
	age	29
visits	member for	2 years, 7 months
	seen	Apr 26 at 14:50
stats	profile views	48

Statistical Packages I Use:

Other Related Software I Use:

College and Professional:

The Ohio State University - Department of Statistics - Statistics PhD student
Brigham Young University - College of Physical and Mathematical Sciences - Department of Statistics - BS Actuarial Science
Formerly worked as an Actuarial Analyst
Actuarial exams P and FM complete

Statistical Topics I Know (Frequentist approach where applicable):

Study design
- Experimental designs
  - Factorial
  - Fractional factorial
  - Randomized block designs (RCBD, GRBD)
- Observational study designs
  - Cross-sectional studies
  - Longitudinal studies, specifically Cohort / Panel studies
  - Retrospective studies
  - Prospective studies
  - Case-control studies
  - Nested case-control studies
Linear regression
ANOVA
Logistic and probit regression
Tobit regression (self-taught)
Truncated regression (self-taught)
Nonparametric methods (and confidence intervals, where applicable)
- Scoring systems
- Permutation tests and confidence intervals
- Nonparametric tests and confidence intervals
- Nonparametric bootstrap testing, confidence intervals, and regression
Smoothing techniques
Adjustment for multiple comparisons
Power, sensitivity, and specificity

	293 reputation	bio	website		visits	member for	2 years, 7 months
214 badges		location	Columbus, OH		seen	Apr 26 at 14:50

summary answers questions tags badges favorites bounties reputation activity

72 Actions

suggestions reviews revisions comments badges posts accepts all

Apr 26	comment	What happens to the covariance matrix when the errors are independent? Note the requirement of the assumption that the error terms all have the same variance; that is, $E(u_i) = 0 \forall i$ and $E(u_i^2) = \sigma^2 \forall i$. This is necessary for saying the covariance matrix has the same $\sigma^2$ value on all the diagonals.
Mar 20	awarded	Self-Learner
Mar 5	awarded	Notable Question
Feb 5	awarded	Popular Question
Oct 11	comment	Can we see shape of normal curve somewhere in nature? I'd argue that the Galton box is not an example of the Normal distribution, but instead, an example of a binomial distribution (with $p \approx 0.5$). After all, "discrete" is a closer description of the distribution than "continuous", and the distribution is bounded. Instead, the Galton box demonstrates the appropriateness of Normal approximation to a binomial distribution (or, equivalently, the Central Limit Theorem applied to the total of a sample from a Bernoulli distribution).
Jul 16	awarded	Popular Question
Jun 4	comment	How can I compute Pearson's $\chi^2$ test statistic for lack of fit on a logistic regression model in R? @Macro, you're very welcome! I wish I could ask more questions where I don't provide the answer, and answer more questions that I didn't ask. But jbowman's right about a pattern: my contributions to the community are tending toward talking to myself. :) (At least I'm contributing somehow to the community, right?)
Jun 4	comment	How can I compute Pearson's $\chi^2$ test statistic for lack of fit on a logistic regression model in R? @Macro, please see this official link: blog.stackoverflow.com/2011/07/… (it's linked on the Ask a Question page in the checkbox label at the bottom: "Answer your own question – share your knowledge, Q&A-style"). I had this question while I was doing homework (having chosen to use R instead of Minitab, though Minitab was demonstrated in class), but I didn't have enough time to type up the question and wait for a response. I figured out this workaround, and decided to share it with the community.
Jun 1	answered	How can I compute Pearson's $\chi^2$ test statistic for lack of fit on a logistic regression model in R?
Jun 1	asked	How can I compute Pearson's $\chi^2$ test statistic for lack of fit on a logistic regression model in R?
Apr 2	comment	What method is suitable for short-term forecast for a trendless, oscillatory, bounded time series? @Shelagh, perhaps, and nothing keeping people from answering you. However, the process will remain a "black box" to you, difficult to troubleshoot or explain to others who rely on your work. Best wishes!
Mar 22	awarded	Organizer
Mar 22	revised	What method is suitable for short-term forecast for a trendless, oscillatory, bounded time series? Removed irrelevant tags, made the title more specific
Mar 22	comment	What method is suitable for short-term forecast for a trendless, oscillatory, bounded time series? @Shelagh, it seems to me that the root of your problem is that you lack a firm understanding of the basic concepts of time series analysis. Answering this question may help you temporarily, but you'll be better off in the long run if you study an introduction to time series.
Mar 22	suggested	suggested edit on What method is suitable for short-term forecast for a trendless, oscillatory, bounded time series?
Feb 24	awarded	Citizen Patrol
Feb 23	revised	Poor predictions from lm.ridge? Added ridge-regression tag, a little formatting cleanup, and narrowing the question a little, introduction of the code block
Feb 23	suggested	suggested edit on Poor predictions from lm.ridge?
Dec 16	awarded	Popular Question
Nov 15	comment	Determining the confidence interval for a non-normal distribution I don't think you necessarily need to try a bootstrap confidence interval. Tests of Normality will say the data come from a non-Normal distribution often when your CI method is robust to that assumption. You have a large sample size, meaning a CI based on the t distribution will be fairly unaffected by any non-Normality.