Questions tagged [small-sample]

Refers to statistical complications or problems due to having few data. If your question is about a small sample relative to the number of variables, please use the [underdetermined] tag instead.

Filter by
Sorted by
Tagged with
3
votes
1answer
27 views

Ramifications of small + unbalanced group sizes, small number of groups for fixed & random effects models?

I have a variable (call it 'group') that I would like to treat as a random effect in a logistic regression. However, the number of groups is small (9 groups, larger than the recommended absolute ...
0
votes
1answer
67 views

Penalized or standard logistic regression?

I am trying to conduct multiple logistic regression. My independent variable has 22 events (yes) and 310(N0) (total sample 332). I am trying to include 20 independent variables (to minimize ...
0
votes
0answers
32 views
+50

Hypothesis test for discrete random vector with few samples

Consider a random vector $X \in \mathbb{R}^{d}$ with support $\text{supp}(X) = \{1,2,3,4\}^d$, and let $P_X$ denote its known probability mass function. Note that $\lvert \text{supp}(X) \rvert = 4^d$. ...
0
votes
0answers
18 views

Small sized training set and results varying based on cross-validation split

I need to try to build a classifier based on around 30 instances. The outcome can also be that the dataset is not large enough for this purpose, however I'm not sure on how can I justify this outcome ...
0
votes
0answers
42 views

Machine Learning with few observations

Is common to say that Machine Learning techniques represent are purely data driven methods, and them are effective only if we have a large amount of data. I focused here on supervised/predictive ...
0
votes
0answers
18 views

Can we do a Spearman's corelation between a continuous and an categorical ordered variable (0,1,2,4)?

just a question that may be already answered here, is it possible to perform a Spearman's rank correlation ( to find a correlation) between a continuous variable and a categorical ( ordered) variable ...
0
votes
0answers
31 views

Do correlation estimates have increased error for small sample data?

When we calculate the correlation between two random variables, we seem confident that the estimated correlation is 100% accurate since I never heard of estimation error being a problem for ...
2
votes
0answers
22 views

In practice how well does asymptotic normality of the MLE hold?

There is a lot of theory about asymptotic normality of the MLE and many people use the result to generate confidence intervals given finite sample data. But a key question here is how large a sample ...
1
vote
0answers
15 views

Entropy of large sample $X$ and small sample $Y$ comparison

Distribution $X$ of a real continuous random variable is unimodal and slightly non-normal with $1,000$ observations. Distribution $Y$ has the same characteristics (not perfectly identical in moments ...
0
votes
1answer
27 views

Copula from small samples

Which copula estimation approach performs better when the empirical data to be modeled has a small sample size? Parametric copulas (Gaussian, t-, Gumbel, Clayton, etc), or Non-parametric (empirical) ...
3
votes
1answer
27 views

How well does GAN (generative adversarial network) perform for small samples?

GAN is an unsupervised learning algorithm that pits a discriminator and generator against one another so that they iteratively compete to enhance the overall model's ability to model/replicate a given ...
1
vote
1answer
22 views

Small paired samples comparison: which approach should I prefer?

I have the following small dataset, that consists of scores before and after a certain treatment for 15 individuals: ...
2
votes
1answer
43 views

Aggregate-level difference-in-difference analysis

Thank you in advance. I am new to difference-in-difference (DID) analysis. I want to conduct a research project examining an educational policy shock to local school districts. I have aggregated ...
0
votes
1answer
22 views

Correlated data series with single repeated value with a few outliers

I'm dealing with about 4,000 stationary time series, most of which I was able to reasonably fit to a distribution based on the KS test. About 200 of the time series, however, were not so well-behaved ...
0
votes
0answers
16 views

What's the distribution of maximum likelihood estimate on linear regression parameters with small sample size?

$y = k_1x_1 +k_2x_2 + \sigma\epsilon$ $\epsilon \sim D$, wehre $D$ is a known distribution e.g. $N(0,1)$. With $n\rightarrow \infty$, $\frac{1}{\sqrt{n}}((k_1,k_2,\sigma) - (\bar{k_1},\bar{k_2},\bar{\...
5
votes
2answers
84 views

Cross Validation in small datasets

I have a really small dataset (124 samples) and I'd like to try out if I get some interesting results with some machine learning algorithms in R. What I've done: I splitted my data set into 75% ...
9
votes
0answers
108 views

Is bootstrap problematic in small samples?

In "3 Things That Bother Me" (1988), Ed Leamer writes: Bootstrap estimates of standard errors are based on the assumption that the observed sample is the same as the true distribution, ...
3
votes
0answers
26 views

Sample size vs F1-score, which is more important (small sample size)

I work in a filed were there are many publications based on classifiers trained on small samples sizes (but large amount of features). In most cases the sample size can only be increased by a few ...
0
votes
0answers
23 views

Adjusting mean for very small population size

I have survey data from 8 respondents out of a population of 10 (very small I know). I know that FPC applies as we have more than 5% of the population in the sample. I can calculate the mean for a 0-...
0
votes
0answers
17 views

Unexpected behaviour of Anderson Darling test for normality for low sample size

I’m testing the power of the Anderson Darling test to detect deviations from standard normal distributions. I’m calibrating the AD test statistic numerically using python and I noticed an unexpected ...
2
votes
1answer
24 views

Using different multiple regression models that each change the available data

So I'm trying to analyse the difference in taxes paid between listed and unlisted companies. However, the sample consists of around 6000 unlisted and only 70 listed companies (there are only 210 in ...
1
vote
0answers
21 views

Calculate group with highest defective rate

I have data on several types of machines, each with a different rate of failure. I have samples of failures/non-failures for each machine type. The samples are small relative to the population range ...
0
votes
0answers
9 views

Insufficient n > p for forecasting with an RNN

What is the best approach to handle insufficient sample size when forecasting for multiple sequences simultaneously with an RNN? My training set has n=956 (time points) and p=262 (sequences). I'm ...
0
votes
0answers
22 views

correcting for small sample sizes

I have been toying with some data relating employment outcomes to choice of college major (which I got from a FiveThirtyEight Git repository). I have included a scatter plot where each point ...
1
vote
0answers
17 views

Logistic regression with small and differing sample sizes

I asked this question on Stack Overflow and was encouraged to come here for more help regarding methodological limitations. Previous question: I ran the model in SAS and I can't make sense of the ...
0
votes
0answers
11 views

Logistic GLM: Confidence Interval of response for small sample

I'm trying to find a confidence interval for P (the response) in a logistic regression, for some $X$ values ( $logit(p) = X\beta$ ). Previously I have used the delta method, either in the logit scale ...
0
votes
0answers
10 views

How much can I get from only one datapoint? [duplicate]

I will be soon ending my bachelors degree and choosing masters major. In my interest is newly opened major and I managed to get information about last years recruitment process, namely how many people ...
0
votes
1answer
34 views

Can PCA be used when n = p, where n = 50?

I have a sample size of 50 items with 50 variables (continuous level), and want to minimise the dimension of my data in order to extract the "character" of each item through a small amount ...
1
vote
0answers
47 views

Linear regression with small N [duplicate]

I was wondering if it makes sense to run a linear regression when my dependent variable only has 20 observations in total (I do have it for 6 years). This is the scenario: 20 observations consists ...
1
vote
0answers
11 views

Can I use regime-switching when bootstrapping relatively few data (<50 samples)?

Consider a large set of data, each with a series of 25-50 independent, non-negative observations and the following characteristics: a) most series have positive values only, b) some series have <10 ...
1
vote
0answers
17 views

What effect size to use for n<20 within-designs (with EEG data)? [closed]

I am conducting a meta-analysis on language related EEG data. Participants listen to different types of stimuli and then the amplitudes of the elicited brain reactions are compared with a simple ANOVA....
1
vote
0answers
31 views

Train/Test with very small datasets, is it viable? . (n=20 for 5 classes) [duplicate]

¡Good evening! I have a small dataset of 20x5 groups =100 entries of 90 variables, and im trying to fit some classification models. But i always have worked with way, way bigger datasets, and with ...
0
votes
0answers
31 views

Feature selection and multidimensional modeling in minimal datasets. R (Multinomial Logistic Regression)

Well, im stuck with a problem with a "small sample size dataset". I used to work with data with n>>p and with models that allow me to build 66-33 train/test datasets to construct and ...
1
vote
0answers
30 views

Too small sample size for Wilcoxon signed rank test, alternatives?

I have a statistical question about my research. I performed photosynthesis measurements on leaves. I have 6 increasing light intensities, and for every light intensity, I measured the photosynthetic ...
1
vote
0answers
20 views

fMRI: Is there a minimum sample size for performing Principal Component Analysis for dimension reduction? [closed]

I'm performing a functional MRI study and I need to analyze the relationship between 198.350 variables (connectivity between pairs of brain areas) with certain condition (1/0), in a sample of 90 ...
1
vote
1answer
47 views

Proper statistical method for small dataset with temporal structure

I was observing 6 trees for 3 years and recorded leaf phenological phases. I am particularly interested in how the date of autumn leaf colouring effects the bud burst date in the following year (see ...
1
vote
2answers
22 views

One vs all statistical test

I have 3 groups of samples e.g. Group A, Group B, and Group C. I want to find out whether the mean of Group B and C are equal and different from Group A. Which statistical test should I use? All ...
1
vote
1answer
24 views

Hurst estimation in small samples

I'm trying to estimate the Hurst exponent of a time series which I believe behaves as a fractional Brownian motion. My problem is that all the estimation methods I have found so far (r/s, Whittle, etc....
0
votes
0answers
33 views

Tiime series forecasing methods for small sample

I have real time data source that emits numeric values every 5 seconds. I wanted to raise alert whenever, for example the last 5 consecutive values, deviate more than a certain level. As you can see ...
1
vote
1answer
20 views

Calculation of the probability to find a test result of a single measurement outside a defined range from small sample size

Background I am developing single use sensors to test a concentration of an analyte in a sample. I am interested in the reproducibility of the individual sensor batches and the subsequent probability ...
0
votes
0answers
33 views

How to estimate the required test set size for multiclass classification

Due to weird circumstances I have: 50,000 data points to train a model on. These data were not sampled randomly from the population, so I can't use them for my test set. 500 randomly selected data ...
1
vote
0answers
37 views

What method should I use to cluster small data set?

I would like to cluster a small data sets [23 genes, 50 samples], but I don't know what method I should use... could you give me any recommendation? I have applied hierarchical clustering (Wards ...
1
vote
0answers
30 views

AI algorithm blind test - sample size

My company works in healthcare consulting, and are working with medical practitioners to explore how AI might be able to assist the remote, early diagnosis of central nervous system disorders such as ...
0
votes
0answers
42 views

Parametric or nonparametric

I am writing my thesis in economics and trying to prove there is a correlation between 2 variables Data collected with Likert scale questionnaire (1-5 scale) I summed up the data and got scale ...
0
votes
1answer
140 views

Small dataset and optimal parameters for XGboost

I am in the process of tuning the features for my xgboost such as ordinal (label) encoding and one-hot encoding. For example, run the model with column A one-hot ...
0
votes
0answers
22 views

How many observations are preferred for a difference-in-difference analysis?

I'm doing a difference-in-difference analysis using export data split by four SITC codes. I have 442 observations in total and my dependent variable is total exports for the four codes which has 58 ...
1
vote
1answer
17 views

Can I carry out a Propensity Score Matching with a general population of 90 observations and a treatment group of 20?

My population consists of 90 administrative zones that divide the city. Of those zones, only 20 received the treatment. After carrying out PSM, I have 17 zones in the treatment group and 17 in the ...
0
votes
0answers
22 views

Can I use repeated measures ANOVA on small sample size (n=14)?

The data I'm trying to analyze is of a single arm, repeated measures measurements (n=14). Obviously, it it difficult to assume normality on such a small dataset. When running Shapiro-Wilk test, 40% of ...
1
vote
1answer
23 views

What stats should I use to evaluate dichotomous data over time for a small sample?

I have pilot data with 9 participants, and I'm trying to look at the change in the number of participants who meet a clinical threshold (i.e., yes, no) of symptoms across three time points. Does ...
2
votes
1answer
36 views

How to ascertain statistical significance for nonparametric tests if the sample size is small

In literature about nonparametric rank tests in event studies, I often encounter a variety of test statistics and authors often attempt to convince their readers that their methods overcome certain ...

1
2 3 4 5
11