Statistical significance refers to the probability that, if, in the population from which this sample were drawn the true effect were 0 (or some hypothesized value) a test statistic as extreme or more extreme than the one gotten in the sample could have occurred.
2
votes
0answers
41 views
Two sided Fisher's exact test with uneven number of samples
I'm not a statistician so maybe this question doesn't make sense, but here goes...
I'm trying to write some code that does a 2-sided Fisher's exact test on some data that looks like this:
...
2
votes
0answers
36 views
Algorithm for determining performance speedup/slowdown in a code change vs. historical data?
I work on a large programming team, and I run a suite of performance tests on every change that is made in our program, which basically measure time it takes to run the test. For every code change, we ...
0
votes
1answer
37 views
Reduced models after finding significant interactions
If you run an ANOVA and find that there are significant interactions, do you then pull the variables out individually and re-run the ANOVA?
I am using Type III. I want to see if there is a ...
1
vote
0answers
19 views
GLMM in SPSS: what does significance of the fixed coefficients mean?
I conducted a GLMM analysis in SPSS with y~a+b+a*b.
The output result contains two tables:
the fixed effects, for which the main effects and the interaction ...
0
votes
1answer
33 views
Permutation test null and correct label distribution
Permutation tests can be used to test the likelihood of obtaining a single mean value (composed of the average of k-fold CV) classifier accuracy by chance, such as for a linear classifier using two ...
1
vote
1answer
29 views
Statistical significance between groups of a summation variable
The general problem is that I have an calculated variable that represents agreement across parts. The variable is a summation in the form (part/count of parts)^2 for possible parts. The summation ...
0
votes
0answers
28 views
Sampling for quality control
I would like to do some quality control study for a set of manufactured components. For a given set, I can draw several samples. Each drawn sample can be either good or bad. My plan is to create a ...
1
vote
2answers
75 views
Comparing two sets of time-series (physiological measures)
I need help in finding which statistical approach I need to use.
I have two groups: G1 (disease) and control.
For both groups we measured their blood level every 10 minutes: 0 to 650 min.
We are ...
1
vote
1answer
44 views
Smart way to search through a very large parameter space
I have a system whose performance is based on a rather large parameter set (200 parameters, lets say, of which each can take a very wide range of values). There are tests to evaluate the performance ...
1
vote
1answer
37 views
Statistical test for a significant change in time series (sales) trend after policy change
My apologies if this has been addressed before, however my experience with statistics is a bit limited, particularly when it comes to time series analyses.
My current question relates to the ...
2
votes
0answers
25 views
Calculating demand and testing the effect of days of the week
I am running some data analysis on a site that lets users share a ride. What I am trying to determine is what separates users who are successful in offering rides and users who are less successful. ...
1
vote
2answers
54 views
Multiple t-tests vs. one-way ANOVA
I'm working on a classification problem and I have a very high F1 baseline of 85%. I have trained three classification models and I want to know which one is the best. How can I do so?
I tried two ...
3
votes
1answer
171 views
What statistical test should I use?
I have 10 different biological features (for example: normal, disease 1 , disease 2, ..., disease 9). Tissue samples from various patients were imaged and 60 imaging parameters were measured. A ...
0
votes
0answers
41 views
Mean squared error — internal and external validation
This is probably a very easy question... but I am not quite sure what the right answer should be..
I have validated 3 beforehand selected models. I have done internal cross validation and I have ...
4
votes
2answers
107 views
Bioinformatical problem - specific word enrichment in a given sequence
My bioinformatical problem looks like this:
two sets of gene sequences (size of set A > 1000, size of set B > 1000; sequence length varies from 1000 to 100000).
Set_A_Sequence_1: ACGTACGTACGT...
...
2
votes
0answers
23 views
Using non-significant data for modelling/predictions
Two medical interventions A and B were compared within randomised controlled trial:
differences in progression free survival (PFS, i.e. how long
patient lived with controlled disease, from ...
0
votes
2answers
48 views
Generalization for interpreting a test?
At my college I am doing a lot of testing, such as testing for autocorrelation, White , DW, $t$, $F$ etc.
However, I always have to look up, when to reject and when to accept for example $H_0$
...
0
votes
0answers
42 views
Evaluating if the new process was better than the previous?
Initially things were done in a particular way (A) and I changed to in some key ways to do things a bit differently (B). Now I wish to evaluate whether the change was for the better. What tests can I ...
0
votes
1answer
51 views
How to compute p-value for quadratic fit of (25) discrete data points?
Preamble: I've had a couple of statistics courses @ uni, but can't really say I got "hooked" (I read NNT's Black Swan before starting the degree :), hence the depth of my statistical knowledge ...
3
votes
1answer
44 views
Measuring the quality of an opinion mining algorithm
I am working on a piece of software to detect opinions in text. As a simplistic example, I would like my algorithm to tell me that Andrea has a positive opinion +1 ...
1
vote
1answer
56 views
How to perform T-Test in R including hypothesis
I would like to do a t-test in R. Unfortunately, statistics has never been my best subject, so I'm wondering what the output of t.test in R exactly mean.
For ...
1
vote
1answer
28 views
Comparing two groups
I have two groups - one group which was presented with one picture of a politician with his wife, one group where the politician was alone. Participants in each group also answered questions (as a ...
1
vote
0answers
58 views
What statistical analysis can be used to validate whether a new release of software was really “worth it”? [closed]
Current state of the art when creating/releasing a software product is this:
Leader/protagonist comes up with ideas of what new features should go into the upcoming release of the software
Out of ...
1
vote
1answer
22 views
Comparison of two classifiers based on prec/recall/F1 only?
For two classifiers h1 and h2 I have the precision, recall and F1 score as a percentage (along with the original labeled dataset tested on). If I had access to which samples each classifier classified ...
1
vote
0answers
80 views
Is a p-value of 0.04993 enough to reject null hypothesis?
In a Wilcoxon signed-ranks statistical significance test, we came across some data that produces a $p$-value of $0.04993$. With a threshold of $p < 0.05$, is this result enough to reject the null ...
1
vote
0answers
26 views
How to test for significant difference between 2 binary variables in one sample [duplicate]
I would like to test if there is a significant difference between the pre-test and post-test in a dichotomous variable (0 = "False", 1 = "True"). I'm using only one sample of 30 subjects.
So, my 2 ...
1
vote
0answers
26 views
Statistically comparing two different cache hit algorithms
I am comparing two different cache hit algorithms using four different training and testing sets. The training sets are related: 1 is a subset of 2 is a subset of 3 is a subset of 4. The same goes for ...
0
votes
0answers
29 views
one function for three different types
I have the following data sets and results
the problem is that I need to create one formula based on the below data but when I create the chart I have three different data ,so as I have no clue on how ...
0
votes
0answers
15 views
Calling R code from java library? [migrated]
I'm new to statistics, is there any way through which codes written in R statistics software be called from java library.
I got some idea about JSC - "Java Statistical Class", but still not finding ...
2
votes
1answer
48 views
How would Facebook measure an AB test whose experimental condition affects the control and experimental groups?
Say FB is testing huge, horribly intrusive ads for retirement homes on 90% of its users (call them group A). This angers most people in group A besides 80+ year old users. As a result, most of group ...
2
votes
0answers
33 views
Comparison of dependent but unpaired data sets
I'm trying to find a statistical test that can help me compare the means of two dependent groups.
My data:
parameter values from white matter region in an in vivo rat brain
parameter values ...
1
vote
0answers
35 views
how to determine whether the difference between two items rated on a Likert scale is significant
I have conducted a survey with multiple 5 point Likert scale questions ranging from very unimportant to very important, and I have coded them from 1 = very unimportant to 5 = very important.
I used ...
1
vote
1answer
38 views
Variables with different significance levels in linear model (model interpretation)
What is the correct interpretation in (multiple) linear regression model when independent variables have different levels of significance?
For example, in the regression below the variable $X$ was ...
1
vote
0answers
21 views
Need help to choose the right statistical test for difference among 4 types
Which statistical test can I use to test if DNA damage is different between 4 cell types with respect to each other (comparing 2 cell lines at one time). The data does not seem to be normally ...
1
vote
1answer
74 views
q-value and p-value
I have heard about q-values, in lines of p-values. What is the main benefit of using q-values over p-values? Why is it that p-values have to be adjusted?
Wikipedia only has two lines of mention as ...
0
votes
1answer
38 views
Confidence interval to estimate the quality of a set of observations by matching - nonmatching ratio of second observations
I'll ask my question as if it was a school assignment.
John makes 400 observations. These observations can be of 5 types : A,B,C,D or E
...
3
votes
4answers
435 views
Another p-value fallacy
Wikipedia examples say that a coin is unfair if it generates a sequence 1111111. A high alternation rate, such as 1010101010, would be similarly unfair.
What is a fallacy to think that a coin is ...
0
votes
1answer
80 views
Detecting a (statistically) significant change in time series trend
Suppose I have two time series (Series1 and Series2) which are identical from timePeriod -200 to timePeriod 0. Say that in timePeriod 0 they are both equal to 100. Series1is equal to 200 at timePeriod ...
-4
votes
0answers
25 views
Please show me that with which formula, I can calculate pooled variance for unequal population variance? [closed]
I know it not legal and valid for faq but I cannot put a photo here because of reputation and not logged in here. Sorry. This is last question. After this, I never put link here. Sorry.
My question ...
-2
votes
1answer
54 views
What is the sample standard error formula?
What is the sample standard error formula?
I know only $s$ but I guess this is not it.
I am confused about its formula. Please help me. Thank you.
2
votes
0answers
83 views
New method for meta-analysis to determine agreement between multiple sources
I'm writing a paper on a method to determine the statistical significance of whether a sample of sources are in mutual agreement on specific premises. This is done by counting the number of sources in ...
1
vote
2answers
35 views
bias of peeking at AB test data and adjusting minimum detectable effect
Let's say we're running an A/B test on my website comparing blue button clicks (baseline) to green button clicks.
I use http://www.evanmiller.org/ab-testing/sample-size.html to calculate my required ...
0
votes
0answers
14 views
Merging and analysis of data from replicate time course experiments
Could you please provide advice on the merging and analysis of data from the replicate time course experiments described below?:
Relative amounts of a protein expressed by aliquots of cells (from a ...
0
votes
1answer
28 views
Are suvey responses of ranking significantly different from mean ranking?
I'm a stats dummy, so please use small words. (-:
This might not be a valid test, so I'm sure you'll let me know if that's the case.
I have some survey responses in which the responses are rankings ...
0
votes
0answers
35 views
what does this +/- of “average” mean?
I have a set of data points and I was told that for it to be valid, every data point should be within +/- say 5% of the average of the entire dataset.
I have no problem of checking each data point ...
5
votes
1answer
102 views
Logistic model, what is more important: Anova Chi-sq test or significance of coefficients
I have a logistic model with 8 variables. I ran a chi square test in R (anova(glm.model,test='Chisq')) and 2 of the variables turn out to be predictive when ordered at the top of the test and not so ...
4
votes
0answers
75 views
Testing two trendlines for statistical significance
Background
I am comparing data on how ATPase activity from flight and leg muscle from locusts reacts to different concentrations of calcium. I plotted a scatter graph of each data set on the same ...
1
vote
1answer
32 views
Test on the properties of two betas?
I have a set of observation. When I do an OLS I get a beta. After I remove some values I also get a beta. Now I want to test if the properties of two betas are the same? Pls give me a hint how to do ...
3
votes
1answer
111 views
Interpretation of a Durbin-Watson test?
I have calculated a Durbin-Watson test and got as far as
$$\eqalign{
d&=2.207551844, \\
dL&= 1.6164, \\
dU&= 1.7896.
}$$
I want to test
$$H_0 \gt 0,\ H_1 \le 0.$$
However, I do not ...
1
vote
0answers
34 views
Assessing Significance in Neural Networks
I'm trying to determine statistical significance of inputs on the dependent variable using neural networks. I'm trying to test the null hypothesis that the partial derivatives are equal to zero. I ...
